system

Abstract

We provide the system. [Solution] Analytical methods, A task generation means that generates tasks using the data collected by the analysis means, A task distribution means for distributing tasks generated by the task generation means to each person in charge, A progress management means that receives and analyzes the task progress status from each of the aforementioned persons in charge, A display means that displays the data collected by the progress management means in real time, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When each department collaborates to handle a case, there are problems such as loose identification of tasks due to busyness and relationship values, or tasks being left unassigned in order to reduce the scope of responsibility. Furthermore, tasks may not be properly allocated depending on the relationship values between the persons in charge (newcomer → senior, etc.), which is a factor hindering the efficiency of the work.

Means for Solving the Problems

[0005] This invention provides an analysis means for analyzing documents using a natural language processing engine. Furthermore, it provides a system comprising a task generation means for generating tasks using data collected by the analysis means, a task distribution means for distributing the generated tasks to each person in charge, a progress management means for receiving and analyzing the task progress from each person in charge, and a display means for displaying the collected data in real time. This system facilitates task identification, efficient distribution, and progress management among departments and individuals, thereby improving the efficiency of operations.

[0006] "Analysis means" refers to a device or process that uses a natural language processing engine to analyze a document and extract key keywords and phrases from it.

[0007] "Task generation means" refers to a function or process that generates specific tasks based on the data collected by the analysis means.

[0008] A "task distribution means" is a function or device for appropriately distributing generated tasks to each person in charge, taking into account the person's skill set, current workload, and job title data.

[0009] A "progress management system" is a function or device for receiving task progress reports from each person in charge, and for analyzing and managing the progress.

[0010] "Display means" refers to a device or function for displaying data collected by the progress management means in real time. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. 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), or Bluetooth (registered trademark).

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] The system of this invention is configured to enable efficient task identification and distribution when various departments collaborate to handle a project. The system consists of three main elements: a server, terminals, and users.

[0033] First, the server receives sales manuals and project summaries sent from each department's terminal. These documents are analyzed using a natural language processing engine to extract important keywords and phrases. For example, if the sales manual contains the phrase "client visit," the server uses this information to generate a task for "client visit."

[0034] Next, the server manages the generated tasks. Based on the preceding information, a specific task list is generated by the task generation mechanism. The server then appropriately distributes tasks to each person in charge based on this list. When distributing tasks, factors such as the person in charge's skill set, current workload, and job title are taken into consideration.

[0035] On the terminal, each department's assigned personnel check and execute their tasks. For example, if the sales department is assigned the task of "creating a proposal," the person in charge will obtain detailed task information through the terminal and create the proposal. The progress of this process is reported from the terminal to the server in real time.

[0036] The server receives progress data from each team member and analyzes it using progress management tools. Based on this analysis, delays and problems in ongoing tasks are detected early. Furthermore, progress data is displayed in real time, allowing team members and managers to check the overall progress through a dashboard.

[0037] For example, the server assigns the task "Contract Review" to the legal department. The legal department staff member checks this task on their terminal, reviews the contract, and then enters the progress into the system. The server receives this information and updates the overall task list.

[0038] This system streamlines task identification, distribution, and progress management compared to traditional manual methods. Each team member can check the progress of their tasks in real time and make necessary adjustments quickly. This significantly improves overall work efficiency.

[0039] In general, the system of the present invention provides a powerful tool for effectively and efficiently managing tasks when various departments collaborate to handle a project.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The terminals are used by staff members in each department to upload sales manuals and project summaries to the server. The uploaded documents are in PDF or text file format.

[0043] Step 2:

[0044] The server receives the uploaded material and sends it to a natural language processing engine. This engine analyzes the material and extracts key keywords and phrases.

[0045] Step 3:

[0046] The server generates specific tasks using a task generation mechanism based on the analysis results. The generated tasks include information on the necessary resources and the departments involved.

[0047] Step 4:

[0048] The server saves the generated task list to a database. The saved task list is then used in subsequent processing.

[0049] Step 5:

[0050] The server collects and analyzes information such as each user's skill set, current workload, and job title. Based on this information, it appropriately distributes tasks using a task distribution mechanism.

[0051] Step 6:

[0052] The server notifies each assigned person's terminal of the assigned task. The notification includes detailed information about the task.

[0053] Step 7:

[0054] The terminal displays the tasks received by each person in charge. The person in charge checks their tasks and proceeds to execute them.

[0055] Step 8:

[0056] Users (assigned personnel) input task progress into the system via their terminals. This information is updated in real time.

[0057] Step 9:

[0058] The server receives progress data and analyzes ongoing tasks using progress management tools. It generates alerts if delays or problems occur.

[0059] Step 10:

[0060] The server visualizes progress data and displays it in real time to each person in charge and administrator through a dashboard. The display includes overall progress and the status of individual tasks.

[0061] In this way, the system of the present invention efficiently identifies, distributes, and manages the progress of tasks when each department collaborates to handle a project. This leads to increased efficiency in operations.

[0062] (Example 1)

[0063] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0064] Traditional manual task management methods presented problems when multiple departments collaborated on a project, such as the inefficient identification, distribution, and progress management of tasks. Furthermore, it was difficult to appropriately distribute tasks considering each person's workload and skill set, often resulting in decreased overall work efficiency. To address this, a more effective and efficient task management system is needed.

[0065] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0066] In this invention, the server includes means for receiving and analyzing data, task generation means for extracting keywords from the analyzed data and generating tasks, task distribution means for distributing tasks to assigned personnel using the generated task list, means for receiving the progress of tasks performed by each assigned personnel, progress management means, and display means. This enables efficient task identification, distribution, and progress management, and allows for appropriate task distribution that takes into account the workload and skill sets of each assigned personnel.

[0067] The "means for receiving and analyzing documents" refer to the methods for receiving documents such as sales manuals and project summaries sent from terminals in each department onto a server, and then analyzing these documents using a natural language processing engine.

[0068] A "task generation method" is a means of extracting important keywords and phrases from analyzed data and generating specific tasks based on them.

[0069] A "task distribution method" is a means of appropriately distributing tasks to assigned personnel based on a generated task list, taking into account the assigned personnel's skill set, current workload, and job title data.

[0070] "Means for receiving progress reports" refers to the means by which each person in charge reports the progress of their tasks from their terminal to the server in real time.

[0071] A "progress management method" is a means of analyzing received progress data to detect the progress and delays of tasks at an early stage.

[0072] A "display method" refers to a means of visualizing data analyzed by progress management methods in real time, allowing each person in charge and manager to check the overall progress status through a dashboard or similar means.

[0073] This invention is a system for efficiently identifying and distributing tasks when various departments collaborate to handle a project. This system consists of three main elements: a server, terminals, and users.

[0074] First, the server receives sales manuals and project overviews sent from each department's terminal. These documents are analyzed using a natural language processing engine such as Google Cloud Natural Language API, and important keywords and phrases are extracted. For example, if the sales manual contains the phrase "client visit," the server will use this information to generate a "client visit" task.

[0075] Next, the server manages the generated tasks. Task generation is achieved using custom Python scripts or the Task Management API to create a detailed task list based on the aforementioned analysis results. The server then appropriately distributes tasks to each assignee based on this list. When distributing tasks, factors such as the assignee's skill set, current workload, and job title are considered. This data is managed, for example, in an SQL database.

[0076] On the terminal side, each department's assigned personnel check and execute their tasks. Each person obtains detailed task information through their terminal and proceeds with execution. For example, if a sales department employee is assigned the task of "creating a proposal," they will use a task management app on their terminal (e.g., Trello or JIRA) to obtain detailed task information and create the proposal. The progress during this process is reported to the server in real time.

[0077] The server receives progress data reported by each team member in real time and analyzes it using progress management tools (e.g., a Grafana dashboard). Based on this analysis, delays and problems in ongoing tasks are detected early. Progress data is displayed in real time, allowing each team member and manager to check the overall progress through the dashboard.

[0078] For example, the server assigns the task "Contract Review" to the legal department. The legal department staff member checks this task on their terminal, reviews the contract, and then enters the progress into the system. The server receives this information and updates the overall task list.

[0079] This system streamlines task identification, distribution, and progress management compared to traditional manual methods. Each team member can check the progress of their tasks in real time and make necessary adjustments quickly. This significantly improves overall work efficiency.

[0080] Specific examples and prompt statements

[0081] Specific example 1:

[0082] The server receives documents from the sales department and analyzes them using a natural language processing engine to extract the important phrase "client visit." Based on this, the server generates a "client visit" task and assigns it to a sales representative. The representative checks the task details on their terminal and conducts the client visit. The progress is reported to the server in real time.

[0083] Example of a prompt:

[0084] "Please provide a detailed explanation of the server's processing procedures for analyzing sales department documents, generating tasks, and distributing them."

[0085] Specific example 2:

[0086] The server assigns the legal department a task called "contract review." The legal department staff member checks the task on their terminal, reviews the contract, and then enters the progress into the system. The server receives this information and updates the overall task list.

[0087] Example of a prompt:

[0088] "Please explain in detail the entire process from assigning tasks to the legal department to updating their progress."

[0089] These explanations will allow for a concrete understanding of each processing step, enabling the effective operation of the system.

[0090] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0091] Step 1:

[0092] Receipt of materials

[0093] The server receives sales manuals and project overview documents sent from terminals in each department.

[0094] Specific actions include each terminal uploading files to the server. For example, the sales department might send an Excel file containing details of a new project to the server.

[0095] Input: Sales manuals and project overview documents

[0096] Output: Received files

[0097] Step 2:

[0098] Analysis of the materials

[0099] The server analyzes the received data using the Google Cloud Natural Language API.

[0100] The analysis process extracts important keywords and phrases from the text. For example, the phrase "client visit" might be detected.

[0101] Input: Received file

[0102] Data processing: Text analysis and keyword extraction of documents using a natural language processing engine.

[0103] Output: Extracted keywords and phrases

[0104] Step 3:

[0105] Task generation

[0106] The server generates specific tasks based on the extracted keywords and phrases.

[0107] Tasks such as "client visit" are created in detail using custom Python scripts, etc.

[0108] Input: Extracted keywords or phrases

[0109] Data Calculation: Applying Keyword-Based Task Generation Logic

[0110] Output: Generated tasks

[0111] Step 4:

[0112] Task distribution

[0113] The server then appropriately distributes tasks to each person in charge based on the generated task list.

[0114] Tasks are distributed considering the assigned person's skill set, current workload, and job title data. For example, tasks are assigned to the appropriate person by referring to the person data stored in the SQL database.

[0115] Input: Generated tasks, assignee's skill set, current workload, job title data

[0116] Data calculation: Selecting personnel using database queries

[0117] Output: Assigned tasks

[0118] Step 5:

[0119] Task confirmation and execution

[0120] On the terminal side, the person in charge of each department checks the assigned task and retrieves detailed information.

[0121] The person in charge performs the task through their terminal. For example, a sales representative checks the task "Create a proposal" and then actually creates the proposal.

[0122] Input: Notification of assigned task

[0123] Data processing: Displaying task details

[0124] Output: Task execution status

[0125] Step 6:

[0126] Progress report

[0127] The person in charge reports the progress of the task to the server in real time via their terminal as the task progresses.

[0128] For example, after a "client visit," enter the status as "completed" in the terminal.

[0129] Input: Task progress information

[0130] Data processing: Update progress status

[0131] Output: Updated progress data

[0132] Step 7:

[0133] Progress management and display

[0134] The server receives the reported progress data in real time and analyzes and displays it using a Grafana dashboard.

[0135] This allows for early detection of delays and problems, and provides visibility into overall progress. Administrators can view detailed progress through the dashboard.

[0136] Input: Updated progress data

[0137] Data processing: Analysis of progress data and display on dashboards.

[0138] Output: Real-time progress dashboard

[0139] This system enables efficient task identification, generation, distribution, and progress management, thereby improving overall business efficiency.

[0140] (Application Example 1)

[0141] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0142] Traditional factory task management was often done manually, which was not only inefficient but also made it difficult to track work progress in real time. Furthermore, assigning appropriate tasks to each machine quickly was challenging, leading to a decline in overall production efficiency. In particular, when various work instructions existed, extracting and distributing appropriate tasks became complex, and assigning tasks while considering the skill sets and job titles of the personnel involved was an extra step.

[0143] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0144] In this invention, the server includes an analysis means, a task generation means, a task distribution means, a progress management means for receiving and analyzing task progress from each person in charge, a display means for displaying the data collected by the progress management means in real time, a task extraction means installed in a machine in the factory and equipped with a natural language processing engine for extracting work tasks from work instructions, and a task monitoring means for distributing the extracted tasks to the machine and monitoring their progress in real time. This enables efficient task extraction, appropriate task distribution, and real-time progress monitoring of work.

[0145] 1. "Analysis tools" are system components that analyze documents and data and extract important information.

[0146] 2. A "task generation means" is a system component that generates work tasks based on collected data.

[0147] 3. A "task distribution means" is a system component that appropriately assigns generated work tasks to each person or machine.

[0148] 4. A "progress management system" is a system component that receives and analyzes the work progress status from each person in charge or machine.

[0149] 5. "Display means" refers to a system component for displaying data collected by the progress management means in real time.

[0150] 6. A "task extraction means" is a system component equipped with a natural language processing engine that extracts work tasks from work instructions.

[0151] 7. A "task monitoring means" is a system component that distributes extracted tasks to each machine and monitors their progress in real time.

[0152] Modes for carrying out the invention

[0153] This invention provides a system that utilizes applications installed on machinery within a factory to achieve efficient extraction, distribution, and progress monitoring of work tasks. This system consists of three main components: a server, terminals, and users.

[0154] server

[0155] The server receives work orders sent from each department and analyzes them using a natural language processing engine. Important tasks are extracted from the analyzed data, and a detailed task list is generated based on these. The generated tasks are then appropriately distributed to each machine and person in the factory. Task distribution takes into account machine capabilities, current load levels, and the skill sets and job titles of the personnel. Progress data is received from each person and machine using a progress management system and analyzed in real time.

[0156] terminal

[0157] Terminals are assigned to machines and personnel within each factory. Personnel and machines check and execute their assigned tasks through these terminals. For example, specific tasks such as "assemble product A" or "quality inspection of product B" are assigned. Progress is reported from the terminals to the server in real time, and the server updates the task list based on this information.

[0158] User

[0159] Users (factory managers and workers) can check the overall progress in real time through the dashboard. Because progress data is displayed, delays and problems with tasks can be addressed quickly. This system significantly improves efficiency compared to traditional manual task management and allows for effective monitoring of overall work progress.

[0160] Hardware and software used

[0161] Hardware: Machinery, servers, and terminals within the factory.

[0162] software:

[0163] Spacy (natural language processing engine)

[0164] allocation_module (task allocation logic module)

[0165] task_monitor (task progress monitoring module)

[0166] Specific examples

[0167] For example, in an electronics assembly plant, if there are work instructions for "assemble product A" and "quality inspection of product B," the assembly robot will be assigned the "assembly" task, and the inspection robot will be assigned the "quality inspection" task. The progress of these tasks is reported to the server in real time and can be viewed on a dashboard.

[0168] Example of a prompt

[0169] "To efficiently carry out the assembly of product A and the quality inspection of product B within the factory, we want to assign appropriate tasks to machines and personnel. First, please create a system that extracts tasks from work instructions, then assigns those tasks to machines and personnel, and monitors progress in real time."

[0170] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0171] Processing flow of the system program that implements the application example

[0172] Step 1:

[0173] The server receives work orders sent from each department. The input is work orders sent to the server in electronic format. The server saves the received work orders. The output is the saved work order file.

[0174] Step 2:

[0175] The server analyzes saved work orders using a natural language processing engine (spacy). The input is the saved work orders. The server extracts important keywords and phrases from the work orders. Specifically, it extracts noun phrases from the document and selects those related to "work." The output is a list of the extracted keywords and phrases.

[0176] Step 3:

[0177] The server generates a task list based on extracted keywords and phrases. The input consists of keywords and phrases extracted by a natural language processing engine. The server uses this information to create specific work tasks. Specifically, it generates task objects based on the keywords. The output is the generated task list.

[0178] Step 4:

[0179] The server distributes the generated task list to the corresponding machine and person in charge at each terminal. Inputs include the generated task list and information about each machine and person in charge (skill set, current workload, job title data). The server uses this information to appropriately assign tasks. Specifically, it matches appropriate tasks with their targets based on specified conditions. The output is the task list assigned to each machine and person in charge.

[0180] Step 5:

[0181] The terminal displays tasks received from the server, and the person in charge or the machine begins working on those tasks. The input is a list of assigned tasks sent to the terminal. Specifically, the terminal receives and displays the task list. The output is the person in charge or the machine confirming the task details.

[0182] Step 6:

[0183] The server receives progress reports from terminals and updates the progress status in real time. The input is progress data sent from the terminals. The server receives this data and updates the progress status. Specifically, it records the progress data in a database and updates the overall progress list. The output is the updated progress list.

[0184] Step 7:

[0185] The server displays progress data on a dashboard in real time. The input is an updated progress list. Specifically, it graphically displays the progress list on the dashboard. The output is a dashboard where each person in charge and administrator can check the status in real time.

[0186] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0187] The system of this invention is configured to ensure efficient task identification and distribution when various departments collaborate to handle a project. The system consists of three main elements: a server, a terminal, and a user, and further incorporates an emotion engine that recognizes the user's emotions.

[0188] First, the server receives sales manuals and project summaries sent from each department's terminal and analyzes them using a natural language processing engine. The keywords and phrases extracted through the analysis are then converted into specific tasks by a task generation mechanism. If the sales manual contains a phrase such as "client visit," the server will generate a task for "client visit."

[0189] Next, the server saves the generated task list to a database and appropriately distributes tasks using a task distribution mechanism based on each person's skill set, current workload, and job title data. The distributed tasks are notified to the person's terminal. On the terminal, each person checks the assigned task and proceeds to execute it.

[0190] During a task, the user inputs the task's progress into the system via a terminal. This progress data is received by the server and analyzed using progress management tools. If delays or problems occur, the server detects them and generates an alert. Furthermore, because an emotion engine is incorporated, it analyzes the user's facial expressions and statements to collect emotional data.

[0191] The server also uses emotional data recognized by the emotion engine as an element of progress management. For example, if an employee experiencing fatigue or stress is causing delays in a task, the task is redistributed taking this emotional data into consideration. This promotes the efficient progress of tasks.

[0192] Progress and sentiment data are visualized in real time and displayed to each team member and manager via a dashboard. This allows for an at-a-glance overview of overall progress, the status of each task, and the emotional state of the team members.

[0193] For example, the server assigns the task "contract review" to the legal department. When a legal department employee reviews and completes this task on their terminal, if the emotion engine detects the employee's stress level, the server analyzes this and, if necessary, reassigns the task to another employee. This process reduces the employee's workload and ensures the smooth progress of the task.

[0194] Thus, the system of the present invention enables more efficient and flexible work execution by considering not only the task identification, distribution, and progress management when each department collaborates to handle a project, but also the emotional state of the person in charge. As a result, the overall efficiency of operations is greatly improved.

[0195] The following describes the processing flow.

[0196] Step 1:

[0197] The terminals are used by staff members in each department to upload sales manuals and project summaries to the server. The uploaded documents are in PDF or text file format.

[0198] Step 2:

[0199] The server receives the uploaded material and sends it to a natural language processing engine. This engine analyzes the material and extracts key keywords and phrases.

[0200] Step 3:

[0201] The server generates specific tasks using a task generation mechanism based on the analysis results. For example, it adds tasks such as "visit client" and "draft contract" to the list.

[0202] Step 4:

[0203] The server saves the generated task list to the database. The task list also includes a detailed description of each task and the resources required.

[0204] Step 5:

[0205] The server collects data on each user's skill set, current workload, and job title, and uses this information to appropriately distribute tasks using a task distribution mechanism. For example, difficult tasks are assigned to experienced users, while relatively easy tasks are assigned to newer users.

[0206] Step 6:

[0207] The server notifies each assignee's terminal of the assigned task. The notification includes detailed task information, deadline, and related resource information.

[0208] Step 7:

[0209] The terminal displays the tasks received by each person in charge, and the person in charge checks their own tasks. The person in charge checks the details of the task and proceeds to execute it.

[0210] Step 8:

[0211] The user (assigned person) inputs task progress and emotional state into the system via a terminal. The emotional state is analyzed by an emotion engine.

[0212] Step 9:

[0213] The server receives progress data and sentiment data and analyzes it using progress management tools. For example, it generates alerts for tasks that are behind schedule.

[0214] Step 10:

[0215] The server readjusts task distribution based on emotional data. For example, it redistributes tasks from employees who are detected as stressed or fatigued to other employees.

[0216] Step 11:

[0217] The server visualizes progress and sentiment data in real time and displays it to each team member and manager through a dashboard. The displayed information includes overall progress, individual task status, and the team member's sentiment status.

[0218] Thus, the system of the present invention efficiently identifies, distributes, manages progress, and manages the emotional state of employees when each department collaborates to handle a project. This leads to increased work efficiency and appropriate management of the workload and stress levels of employees.

[0219] (Example 2)

[0220] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0221] Traditional task management systems fail to consider the emotional state of the person in charge, in addition to managing the progress of tasks. This can lead to inadequate management of the workload and a decrease in work efficiency. Furthermore, there is a problem in that appropriate measures cannot be taken when tasks are delayed due to the stress or fatigue of the person in charge.

[0222] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0223] In this invention, the server includes analysis means, task generation means, task distribution means, progress management means, emotion recognition means, task redistribution means, and display means. This enables task management and redistribution based on the emotional state of the person in charge.

[0224] "Analysis methods" refer to the means of receiving and analyzing sales manuals and project outlines sent from each department.

[0225] A "task generation method" is a means of generating specific tasks using data collected by an analysis method.

[0226] A "task distribution method" is a means of distributing generated tasks to each person in charge.

[0227] A "progress management method" is a means of receiving and analyzing the task progress status from each person in charge.

[0228] "Emotion recognition means" refers to a method for analyzing the emotional state of the person in charge and collecting that data.

[0229] A "task redistribution method" is a means of redistributing tasks based on data collected by an emotion recognition method.

[0230] "Display means" refers to means for displaying data collected by progress management means and emotion recognition means in real time.

[0231] The system of this invention is designed to enable efficient collaboration among departments, task identification, distribution, and progress management. This system primarily consists of servers, terminals, and users, and further incorporates an emotion engine to recognize user emotions. The following describes each element of the system and the program's processing.

[0232] server

[0233] The server receives sales manuals and project summaries sent from each department and analyzes them using a natural language processing engine (e.g., AWS® Comprehend or Google Cloud Natural Language). The analyzed data is then converted into specific tasks by a task generation system. For example, if the phrase "client visit" is included, the server generates it as a task for "client visit".

[0234] The generated tasks are stored in a database and distributed using a task distribution system based on each assignee's skill set, current workload, and job title data. Assigned tasks are then notified to the assignee's terminal. While a task is in progress, the server receives progress data and analyzes it using a progress management system. If delays or problems occur, an alert is generated.

[0235] Furthermore, the system uses an emotion engine to analyze the user's emotional state (e.g., fatigue and stress) and collects data using emotion recognition tools. Based on this data, tasks are redistributed to reduce the workload on team members and promote efficient task progress. Progress and emotion data are visualized in real time and displayed through a dashboard.

[0236] terminal

[0237] The terminals used by staff in each department receive task notifications sent from the server and display the task list. Staff members use their terminals to check their assigned tasks and enter their completion status. The terminals can send task progress data and staff member sentiment data to the server.

[0238] User

[0239] Users operate the system and send sales manuals and project summaries to the server via their terminals. The assigned personnel check their tasks and update their progress as needed. Furthermore, an emotion engine analyzes the user's emotional state and redistributes tasks as necessary.

[0240] Example of a prompt

[0241] "Send the sales manual and project summary to the server for analysis and generate a new task."

[0242] "Redistribute tasks based on the progress and emotional data of the assigned personnel, and help resolve delays and problems."

[0243] The above is a specific example of the system's operation. The system of the present invention is configured to enable efficient collaboration among departments and significantly improve the efficiency of operations.

[0244] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0245] Program processing flow

[0246] Step 1: Sending Data

[0247] Users use terminals in their respective departments to send sales manuals and project summaries to the server. Input is in PDF or document format, and output is the server saving the received files. Specifically, the sales department uploads the latest customer list and visit plan to the server in PDF format.

[0248] Step 2: Analysis of the month

[0249] The server analyzes the received data using a natural language processing engine (e.g., AWS Comprehend or Google Cloud Natural Language). The input is the stored data, and the output is the extracted keywords and phrases from the analysis. For example, it can extract phrases such as "customer visit" and "presentation material creation" from a customer list document.

[0250] Step 3: Task Generation

[0251] The server generates specific tasks using a task generation mechanism based on the analysis results. The input is the analyzed keywords and phrases, and the output is the generated tasks. Specifically, from the keyword "customer visit," tasks such as "schedule customer visit" are automatically generated.

[0252] Step 4: Task Distribution

[0253] The server saves the generated task list to a database and distributes it to each person in charge using a task distribution mechanism. The input is the generated tasks, the skill sets of the people in charge, and their job titles, and the output is the distributed tasks. The legal department is assigned the task of "contract review," and the sales department is assigned the task of "customer visit."

[0254] Step 5: Task Notification

[0255] The server notifies the assigned task on the employee's terminal. The input is the assigned task, and the output is the notification message sent to the employee's terminal. Specifically, a notification titled "New Task: Confirm Customer Visit Schedule" will appear on the terminal of the sales department employee.

[0256] Step 6: Execute the task and enter the progress.

[0257] Users check their assigned tasks on their devices and proceed with execution. Input is the task's progress, and output is the transmission of progress data to the server. For example, if an employee enters "Customer visit completed" on their device, the progress status is updated.

[0258] Step 7: Progress Management

[0259] The server receives progress data and analyzes it using progress management tools. The input is progress data, and the output is the analysis results of the progress status and any necessary alerts. If a delay is detected, the server sends a "Task Delayed" alert to the person in charge.

[0260] Step 8: Collecting and analyzing emotional data

[0261] The emotion engine analyzes the user's facial expressions and speech to collect emotional data. The input is the user's emotional state (e.g., facial expressions and voice), and the output is the analyzed emotional data. If an employee experiences stress during their work, this state is recorded in the system.

[0262] Step 9: Redistributing tasks

[0263] The server redistributes tasks as needed based on emotional data. Inputs are emotional data and progress data, and output is the redistributed tasks. If a high-stress employee is behind schedule, the task is reassigned to another employee.

[0264] Step 10: Real-time visualization

[0265] The server visualizes progress and sentiment data in real time and displays it through a dashboard. The input is the collected progress and sentiment data, and the output is the display of the visualized dashboard. Each person in charge and manager can check the "progress bar" and "stakeholder's sentiment status" in real time.

[0266] The above describes the specific actions taken at each processing step of the system.

[0267] (Application Example 2)

[0268] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0269] Current task management systems often distribute tasks based solely on the skill set and workload of the assigned person, without considering their psychological burden or emotional state. As a result, this can lead to decreased motivation and reduced work efficiency. Furthermore, real-time monitoring of progress is limited, making flexible task redistribution difficult. This invention aims to solve these problems, streamline task management within factories, and achieve flexible management that takes into account the health and well-being of the assigned person.

[0270] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0271] In this invention, the server includes an analysis means, a task generation means that generates tasks using data collected by the analysis means, a task distribution means that distributes the tasks generated by the task generation means to each person in charge, a progress management means that receives and analyzes the progress of the tasks distributed by the task distribution means, an emotion engine means that recognizes the emotional state of the user, and a display means that displays the data collected by the progress management means and the data collected by the emotion engine means in real time. This makes it possible to distribute and manage tasks while taking into account not only the skill set and workload of the person in charge, but also their psychological state.

[0272] "Analysis methods" refer to the functions and processes for collecting and analyzing various types of data.

[0273] A "task generation method" is a function that creates specific tasks based on collected and analyzed data.

[0274] A "task distribution mechanism" is a function that assigns generated tasks to the appropriate person or robot.

[0275] A "progress management system" is a function that receives and analyzes the progress status of assigned tasks.

[0276] The "emotional engine" refers to a function that recognizes the emotional state of personnel or robots and collects it as data.

[0277] "Display means" refers to a function for visually displaying progress data and sentiment data.

[0278] A "natural language processing engine" is a technology used to analyze documents and extract meaning and keywords.

[0279] A "skill set" is a collection of skills and expertise possessed by an individual or robot.

[0280] "Current workload" refers to the amount of work and tasks that the person in charge or robot is currently handling.

[0281] "Rank data" refers to information about the rank and position of the person in charge or the robot.

[0282] The system of this invention streamlines task management within a factory and enables flexible management that takes into account the health status of the person in charge. The system consists of three main elements: a server, a terminal, and a user, and further incorporates an emotion engine that recognizes the user's emotions.

[0283] First, the server receives documents and instructions from within the factory and analyzes them using a natural language processing engine (e.g., Google Cloud Natural Language API). This analysis allows the task generation system to generate specific tasks. For example, if a phrase such as "quality inspection of product A" is included, the server will generate a task for "quality inspection of product A".

[0284] Next, the server saves the generated task list to a database and appropriately distributes tasks using a task distribution mechanism based on each robot and operator's skill set, current workload, and rank data. In this process, the server assigns tasks to the robot or operator with the most available capacity. The assigned tasks are then notified to the operator's terminal.

[0285] The person in charge and the robot execute the assigned tasks and report the progress to the server. The server analyzes the progress using progress management means and generates an alert if there is a delay or problem. Furthermore, since an emotion engine is incorporated, emotion data of the person in charge and the robot is also collected. The emotion data is collected, for example, using sensors and voice analysis microphones. This makes it possible to detect psychological load and stress levels.

[0286] The server integrates and analyzes the collected progress data and emotion data, and redistributes tasks as necessary. For example, if a certain person in charge is in a high stress state, their tasks can be reassigned to other persons in charge. This appropriately adjusts the load on the person in charge and promotes the smooth progress of the work.

[0287] The progress data and emotion data are visualized in real time and displayed to each person in charge and the administrator through a dashboard. This enables one to grasp at a glance not only the overall progress and the status of each task, but also the emotional state of the person in charge and the robot.

[0288] As a specific example, there are tasks such as "quality inspection" and "equipment maintenance" in a factory. This system extracts these tasks using a natural language processing engine and assigns them to appropriate robots and persons in charge. With the emotion engine, it is possible to reassign tasks when the stress level of the person in charge is high.

[0289] Examples of prompt sentences include

[0290] "Generate tasks for quality inspection and equipment maintenance within the factory, and distribute them to the robots in an optimal form. Also, consider the stress level and progress of each robot and display them on the dashboard. The progress data is stored in a hypothetical database."

[0291] and so on.

[0292] This will streamline task management within the factory and enable flexible management that takes into account the health status of personnel and robots. Furthermore, it will improve operational efficiency while minimizing psychological stress.

[0293] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0294] Step 1:

[0295] The server receives documents and instructions from within the factory. The received data is parsed by a natural language processing engine (e.g., Google Cloud Natural Language API). The input is documents and instructions from within the factory, and the output is keywords and phrases that indicate extracted tasks. To execute this, the server analyzes the text data and identifies the necessary tasks.

[0296] Step 2:

[0297] The server generates specific tasks based on keywords and phrases extracted by the natural language processing engine. The task generation mechanism fulfills this role. The input is the keywords and phrases extracted in the previous step, and the output is a list of specific tasks. The server creates each task based on the text analysis results.

[0298] Step 3:

[0299] The server saves the generated task list to the database. The input is the task list, and the output is the task list stored in the database. The server performs database operations to record the task list.

[0300] Step 4:

[0301] The server distributes the tasks generated using the task distribution means to the responsible persons or robots. The distribution criteria are the skill sets, current loads, and hierarchical data of the responsible persons or robots. The input is the task list and the information of each responsible person or robot, and the output is the list of tasks distributed to the responsible persons or robots. The server analyzes the status of each responsible person or robot and performs an optimal distribution.

[0302] Step 5:

[0303] The terminal notifies the responsible persons or robots of the tasks distributed to them and proceeds to execution. The input is the distributed task list, and the output is the task information notified on the terminal. The terminal notifies the responsible persons or robots of the tasks and monitors the execution status.

[0304] Step 6:

[0305] The responsible persons or robots execute the tasks and report the progress status to the server via the terminal. The input is the progress status data, and the output is the progress status data sent to the server. The responsible persons or robots complete the tasks and report their progress.

[0306] Step 7:

[0307] The server receives and analyzes the progress status data using the progress management means. The input is the progress status data, and the output is the analyzed progress data and alert information. The server evaluates the status of the ongoing tasks and generates alerts if necessary.

[0308] Step 8:

[0309] The emotion engine means recognizes the emotional states of the responsible persons or robots and collects data. The input is the emotion data (e.g., from sensors or voice analysis), and the output is the emotion data sent to the server. The emotion engine analyzes the psychological states of the responsible persons or robots.

[0310] Step 9:

[0311] The server integrates progress and sentiment data and redistributes tasks as needed. Inputs are progress and sentiment data, and output is a redistributed task list. Based on this data, the server readjusts the load balancing.

[0312] Step 10:

[0313] Using a display mechanism, progress data and sentiment data are shown on a dashboard in real time. The input is integrated progress data and sentiment data, and the output is the information displayed on the dashboard. The server makes this information visually accessible to monitors and administrators.

[0314] Through these steps, the system can efficiently and flexibly manage tasks within the factory, while also appropriately managing the psychological burden on personnel and robots.

[0315] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0316] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0317] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0318] [Second Embodiment]

[0319] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0320] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0321] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0322] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0323] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0324] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0325] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0326] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0327] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0328] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0329] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0330] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0331] The system of this invention is configured to enable efficient task identification and distribution when various departments collaborate to handle a project. The system consists of three main elements: a server, terminals, and users.

[0332] First, the server receives sales manuals and project summaries sent from each department's terminal. These documents are analyzed using a natural language processing engine to extract important keywords and phrases. For example, if the sales manual contains the phrase "client visit," the server uses this information to generate a task for "client visit."

[0333] Next, the server manages the generated tasks. Based on the preceding information, a specific task list is generated by the task generation mechanism. The server then appropriately distributes tasks to each person in charge based on this list. When distributing tasks, factors such as the person in charge's skill set, current workload, and job title are taken into consideration.

[0334] On the terminal, each department's assigned personnel check and execute their tasks. For example, if the sales department is assigned the task of "creating a proposal," the person in charge will obtain detailed task information through the terminal and create the proposal. The progress of this process is reported from the terminal to the server in real time.

[0335] The server receives progress data from each team member and analyzes it using progress management tools. Based on this analysis, delays and problems in ongoing tasks are detected early. Furthermore, progress data is displayed in real time, allowing team members and managers to check the overall progress through a dashboard.

[0336] For example, the server assigns the task "Contract Review" to the legal department. The legal department staff member checks this task on their terminal, reviews the contract, and then enters the progress into the system. The server receives this information and updates the overall task list.

[0337] This system streamlines task identification, distribution, and progress management compared to traditional manual methods. Each team member can check the progress of their tasks in real time and make necessary adjustments quickly. This significantly improves overall work efficiency.

[0338] In general, the system of the present invention provides a powerful tool for effectively and efficiently managing tasks when various departments collaborate to handle a project.

[0339] The following describes the processing flow.

[0340] Step 1:

[0341] The terminals are used by staff members in each department to upload sales manuals and project summaries to the server. The uploaded documents are in PDF or text file format.

[0342] Step 2:

[0343] The server receives the uploaded material and sends it to a natural language processing engine. This engine analyzes the material and extracts key keywords and phrases.

[0344] Step 3:

[0345] The server generates specific tasks using a task generation mechanism based on the analysis results. The generated tasks include information on the necessary resources and the departments involved.

[0346] Step 4:

[0347] The server saves the generated task list to a database. The saved task list is then used in subsequent processing.

[0348] Step 5:

[0349] The server collects and analyzes information such as each user's skill set, current workload, and job title. Based on this information, it appropriately distributes tasks using a task distribution mechanism.

[0350] Step 6:

[0351] The server notifies each assigned person's terminal of the assigned task. The notification includes detailed information about the task.

[0352] Step 7:

[0353] The terminal displays the tasks received by each person in charge. The person in charge checks their tasks and proceeds to execute them.

[0354] Step 8:

[0355] Users (assigned personnel) input task progress into the system via their terminals. This information is updated in real time.

[0356] Step 9:

[0357] The server receives progress data and analyzes ongoing tasks using progress management tools. It generates alerts if delays or problems occur.

[0358] Step 10:

[0359] The server visualizes progress data and displays it in real time to each person in charge and administrator through a dashboard. The display includes overall progress and the status of individual tasks.

[0360] In this way, the system of the present invention efficiently identifies, distributes, and manages the progress of tasks when each department collaborates to handle a project. This leads to increased efficiency in operations.

[0361] (Example 1)

[0362] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0363] Traditional manual task management methods presented problems when multiple departments collaborated on a project, such as the inefficient identification, distribution, and progress management of tasks. Furthermore, it was difficult to appropriately distribute tasks considering each person's workload and skill set, often resulting in decreased overall work efficiency. To address this, a more effective and efficient task management system is needed.

[0364] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0365] In this invention, the server includes means for receiving and analyzing data, task generation means for extracting keywords from the analyzed data and generating tasks, task distribution means for distributing tasks to assigned personnel using the generated task list, means for receiving the progress of tasks performed by each assigned personnel, progress management means, and display means. This enables efficient task identification, distribution, and progress management, and allows for appropriate task distribution that takes into account the workload and skill sets of each assigned personnel.

[0366] The "means for receiving and analyzing documents" refer to the methods for receiving documents such as sales manuals and project summaries sent from terminals in each department onto a server, and then analyzing these documents using a natural language processing engine.

[0367] A "task generation method" is a means of extracting important keywords and phrases from analyzed data and generating specific tasks based on them.

[0368] A "task distribution method" is a means of appropriately distributing tasks to assigned personnel based on a generated task list, taking into account the assigned personnel's skill set, current workload, and job title data.

[0369] "Means for receiving progress reports" refers to the means by which each person in charge reports the progress of their tasks from their terminal to the server in real time.

[0370] A "progress management method" is a means of analyzing received progress data to detect the progress and delays of tasks at an early stage.

[0371] A "display method" refers to a means of visualizing data analyzed by progress management methods in real time, allowing each person in charge and manager to check the overall progress status through a dashboard or similar means.

[0372] This invention is a system for efficiently identifying and distributing tasks when various departments collaborate to handle a project. This system consists of three main elements: a server, terminals, and users.

[0373] First, the server receives sales manuals and project summaries sent from each department's terminal. These documents are analyzed using a natural language processing engine such as the Google Cloud Natural Language API, and important keywords and phrases are extracted. For example, if the sales manual contains the phrase "client visit," the server will use this information to generate a task for "client visit."

[0374] Next, the server manages the generated tasks. Task generation is achieved using custom Python scripts or the Task Management API to create a detailed task list based on the aforementioned analysis results. The server then appropriately distributes tasks to each assignee based on this list. When distributing tasks, factors such as the assignee's skill set, current workload, and job title are considered. This data is managed, for example, in an SQL database.

[0375] On the terminal side, each department's assigned personnel check and execute their tasks. Each person obtains detailed task information through their terminal and proceeds with execution. For example, if a sales department employee is assigned the task of "creating a proposal," they will use a task management app on their terminal (e.g., Trello or JIRA) to obtain detailed task information and create the proposal. The progress during this process is reported to the server in real time.

[0376] The server receives progress data reported by each team member in real time and analyzes it using progress management tools (e.g., a Grafana dashboard). Based on this analysis, delays and problems in ongoing tasks are detected early. Progress data is displayed in real time, allowing each team member and manager to check the overall progress through the dashboard.

[0377] For example, the server assigns the task "Contract Review" to the legal department. The legal department staff member checks this task on their terminal, reviews the contract, and then enters the progress into the system. The server receives this information and updates the overall task list.

[0378] This system streamlines task identification, distribution, and progress management compared to traditional manual methods. Each team member can check the progress of their tasks in real time and make necessary adjustments quickly. This significantly improves overall work efficiency.

[0379] Specific examples and prompt statements

[0380] Specific example 1:

[0381] The server receives documents from the sales department and analyzes them using a natural language processing engine to extract the important phrase "client visit." Based on this, the server generates a "client visit" task and assigns it to a sales representative. The representative checks the task details on their terminal and conducts the client visit. The progress is reported to the server in real time.

[0382] Example of a prompt:

[0383] "Please provide a detailed explanation of the server's processing procedures for analyzing sales department documents, generating tasks, and distributing them."

[0384] Specific example 2:

[0385] The server assigns the legal department a task called "contract review." The legal department staff member checks the task on their terminal, reviews the contract, and then enters the progress into the system. The server receives this information and updates the overall task list.

[0386] Example of a prompt:

[0387] "Please explain in detail the entire process from assigning tasks to the legal department to updating their progress."

[0388] These explanations will allow for a concrete understanding of each processing step, enabling the effective operation of the system.

[0389] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0390] Step 1:

[0391] Receipt of materials

[0392] The server receives sales manuals and project overview documents sent from terminals in each department.

[0393] Specific actions include each terminal uploading files to the server. For example, the sales department might send an Excel file containing details of a new project to the server.

[0394] Input: Sales manuals and project overview documents

[0395] Output: Received files

[0396] Step 2:

[0397] Analysis of the materials

[0398] The server analyzes the received data using the Google Cloud Natural Language API.

[0399] The analysis process extracts important keywords and phrases from the text. For example, the phrase "client visit" might be detected.

[0400] Input: Received file

[0401] Data processing: Text analysis and keyword extraction of documents using a natural language processing engine.

[0402] Output: Extracted keywords and phrases

[0403] Step 3:

[0404] Task generation

[0405] The server generates specific tasks based on the extracted keywords and phrases.

[0406] Tasks such as "client visit" are created in detail using custom Python scripts, etc.

[0407] Input: Extracted keywords or phrases

[0408] Data Calculation: Applying Keyword-Based Task Generation Logic

[0409] Output: Generated tasks

[0410] Step 4:

[0411] Task distribution

[0412] The server then appropriately distributes tasks to each person in charge based on the generated task list.

[0413] Tasks are distributed considering the assigned person's skill set, current workload, and job title data. For example, tasks are assigned to the appropriate person by referring to the person data stored in the SQL database.

[0414] Input: Generated tasks, assignee's skill set, current workload, job title data

[0415] Data calculation: Selecting personnel using database queries

[0416] Output: Assigned tasks

[0417] Step 5:

[0418] Task confirmation and execution

[0419] On the terminal side, the person in charge of each department checks the assigned task and retrieves detailed information.

[0420] The person in charge performs the task through their terminal. For example, a sales representative checks the task "Create a proposal" and then actually creates the proposal.

[0421] Input: Notification of assigned task

[0422] Data processing: Displaying task details

[0423] Output: Task execution status

[0424] Step 6:

[0425] Progress report

[0426] The person in charge reports the progress of the task to the server in real time via their terminal as the task progresses.

[0427] For example, after a "client visit," enter the status as "completed" in the terminal.

[0428] Input: Task progress information

[0429] Data processing: Update progress status

[0430] Output: Updated progress data

[0431] Step 7:

[0432] Progress management and display

[0433] The server receives the reported progress data in real time and analyzes and displays it using a Grafana dashboard.

[0434] This allows for early detection of delays and problems, and provides visibility into overall progress. Administrators can view detailed progress through the dashboard.

[0435] Input: Updated progress data

[0436] Data processing: Analysis of progress data and display on dashboards.

[0437] Output: Real-time progress dashboard

[0438] This system enables efficient task identification, generation, distribution, and progress management, thereby improving overall business efficiency.

[0439] (Application Example 1)

[0440] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0441] Traditional factory task management was often done manually, which was not only inefficient but also made it difficult to track work progress in real time. Furthermore, assigning appropriate tasks to each machine quickly was challenging, leading to a decline in overall production efficiency. In particular, when various work instructions existed, extracting and distributing appropriate tasks became complex, and assigning tasks while considering the skill sets and job titles of the personnel involved was an extra step.

[0442] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0443] In this invention, the server includes an analysis means, a task generation means, a task distribution means, a progress management means for receiving and analyzing task progress from each person in charge, a display means for displaying the data collected by the progress management means in real time, a task extraction means installed in a machine in the factory and equipped with a natural language processing engine for extracting work tasks from work instructions, and a task monitoring means for distributing the extracted tasks to the machine and monitoring their progress in real time. This enables efficient task extraction, appropriate task distribution, and real-time progress monitoring of work.

[0444] 1. "Analysis tools" are system components that analyze documents and data and extract important information.

[0445] 2. A "task generation means" is a system component that generates work tasks based on collected data.

[0446] 3. A "task distribution means" is a system component that appropriately assigns generated work tasks to each person or machine.

[0447] 4. A "progress management system" is a system component that receives and analyzes the work progress status from each person in charge or machine.

[0448] 5. "Display means" refers to a system component for displaying data collected by the progress management means in real time.

[0449] 6. A "task extraction means" is a system component equipped with a natural language processing engine that extracts work tasks from work instructions.

[0450] 7. A "task monitoring means" is a system component that distributes extracted tasks to each machine and monitors their progress in real time.

[0451] Modes for carrying out the invention

[0452] This invention provides a system that utilizes applications installed on machinery within a factory to achieve efficient extraction, distribution, and progress monitoring of work tasks. This system consists of three main components: a server, terminals, and users.

[0453] server

[0454] The server receives work orders sent from each department and analyzes them using a natural language processing engine. Important tasks are extracted from the analyzed data, and a detailed task list is generated based on these. The generated tasks are then appropriately distributed to each machine and person in the factory. Task distribution takes into account machine capabilities, current load levels, and the skill sets and job titles of the personnel. Progress data is received from each person and machine using a progress management system and analyzed in real time.

[0455] terminal

[0456] Terminals are assigned to machines and personnel within each factory. Personnel and machines check and execute their assigned tasks through these terminals. For example, specific tasks such as "assemble product A" or "quality inspection of product B" are assigned. Progress is reported from the terminals to the server in real time, and the server updates the task list based on this information.

[0457] User

[0458] Users (factory managers and workers) can check the overall progress in real time through the dashboard. Because progress data is displayed, delays and problems with tasks can be addressed quickly. This system significantly improves efficiency compared to traditional manual task management and allows for effective monitoring of overall work progress.

[0459] Hardware and software used

[0460] Hardware: Machinery, servers, and terminals within the factory.

[0461] software:

[0462] Spacy (natural language processing engine)

[0463] allocation_module (task allocation logic module)

[0464] task_monitor (task progress monitoring module)

[0465] Specific examples

[0466] For example, in an electronics assembly plant, if there are work instructions for "assemble product A" and "quality inspection of product B," the assembly robot will be assigned the "assembly" task, and the inspection robot will be assigned the "quality inspection" task. The progress of these tasks is reported to the server in real time and can be viewed on a dashboard.

[0467] Example of a prompt

[0468] "To efficiently carry out the assembly of product A and the quality inspection of product B within the factory, we want to assign appropriate tasks to machines and personnel. First, please create a system that extracts tasks from work instructions, then assigns those tasks to machines and personnel, and monitors progress in real time."

[0469] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0470] Processing flow of the system program that implements the application example

[0471] Step 1:

[0472] The server receives work orders sent from each department. The input is work orders sent to the server in electronic format. The server saves the received work orders. The output is the saved work order file.

[0473] Step 2:

[0474] The server analyzes saved work orders using a natural language processing engine (spacy). The input is the saved work orders. The server extracts important keywords and phrases from the work orders. Specifically, it extracts noun phrases from the document and selects those related to "work." The output is a list of the extracted keywords and phrases.

[0475] Step 3:

[0476] The server generates a task list based on extracted keywords and phrases. The input consists of keywords and phrases extracted by a natural language processing engine. The server uses this information to create specific work tasks. Specifically, it generates task objects based on the keywords. The output is the generated task list.

[0477] Step 4:

[0478] The server distributes the generated task list to the corresponding machine and person in charge at each terminal. Inputs include the generated task list and information about each machine and person in charge (skill set, current workload, job title data). The server uses this information to appropriately assign tasks. Specifically, it matches appropriate tasks with their targets based on specified conditions. The output is the task list assigned to each machine and person in charge.

[0479] Step 5:

[0480] The terminal displays tasks received from the server, and the person in charge or the machine begins working on those tasks. The input is a list of assigned tasks sent to the terminal. Specifically, the terminal receives and displays the task list. The output is the person in charge or the machine confirming the task details.

[0481] Step 6:

[0482] The server receives progress reports from terminals and updates the progress status in real time. The input is progress data sent from the terminals. The server receives this data and updates the progress status. Specifically, it records the progress data in a database and updates the overall progress list. The output is the updated progress list.

[0483] Step 7:

[0484] The server displays progress data on a dashboard in real time. The input is an updated progress list. Specifically, it graphically displays the progress list on the dashboard. The output is a dashboard where each person in charge and administrator can check the status in real time.

[0485] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0486] The system of this invention is configured to ensure efficient task identification and distribution when various departments collaborate to handle a project. The system consists of three main elements: a server, a terminal, and a user, and further incorporates an emotion engine that recognizes the user's emotions.

[0487] First, the server receives sales manuals and project summaries sent from each department's terminal and analyzes them using a natural language processing engine. The keywords and phrases extracted through the analysis are then converted into specific tasks by a task generation mechanism. If the sales manual contains a phrase such as "client visit," the server will generate a task for "client visit."

[0488] Next, the server saves the generated task list to a database and appropriately distributes tasks using a task distribution mechanism based on each person's skill set, current workload, and job title data. The distributed tasks are notified to the person's terminal. On the terminal, each person checks the assigned task and proceeds to execute it.

[0489] During a task, the user inputs the task's progress into the system via a terminal. This progress data is received by the server and analyzed using progress management tools. If delays or problems occur, the server detects them and generates an alert. Furthermore, because an emotion engine is incorporated, it analyzes the user's facial expressions and statements to collect emotional data.

[0490] The server also uses emotional data recognized by the emotion engine as an element of progress management. For example, if an employee experiencing fatigue or stress is causing delays in a task, the task is redistributed taking this emotional data into consideration. This promotes the efficient progress of tasks.

[0491] Progress and sentiment data are visualized in real time and displayed to each team member and manager via a dashboard. This allows for an at-a-glance overview of overall progress, the status of each task, and the emotional state of the team members.

[0492] For example, the server assigns the task "contract review" to the legal department. When a legal department employee reviews and completes this task on their terminal, if the emotion engine detects the employee's stress level, the server analyzes this and, if necessary, reassigns the task to another employee. This process reduces the employee's workload and ensures the smooth progress of the task.

[0493] Thus, the system of the present invention enables more efficient and flexible work execution by considering not only the task identification, distribution, and progress management when each department collaborates to handle a project, but also the emotional state of the person in charge. As a result, the overall efficiency of operations is greatly improved.

[0494] The following describes the processing flow.

[0495] Step 1:

[0496] The terminals are used by staff members in each department to upload sales manuals and project summaries to the server. The uploaded documents are in PDF or text file format.

[0497] Step 2:

[0498] The server receives the uploaded material and sends it to a natural language processing engine. This engine analyzes the material and extracts key keywords and phrases.

[0499] Step 3:

[0500] The server generates specific tasks using a task generation mechanism based on the analysis results. For example, it adds tasks such as "visit client" and "draft contract" to the list.

[0501] Step 4:

[0502] The server saves the generated task list to the database. The task list also includes a detailed description of each task and the resources required.

[0503] Step 5:

[0504] The server collects data on each user's skill set, current workload, and job title, and uses this information to appropriately distribute tasks using a task distribution mechanism. For example, difficult tasks are assigned to experienced users, while relatively easy tasks are assigned to newer users.

[0505] Step 6:

[0506] The server notifies each assignee's terminal of the assigned task. The notification includes detailed task information, deadline, and related resource information.

[0507] Step 7:

[0508] The terminal displays the tasks received by each person in charge, and the person in charge checks their own tasks. The person in charge checks the details of the task and proceeds to execute it.

[0509] Step 8:

[0510] The user (assigned person) inputs task progress and emotional state into the system via a terminal. The emotional state is analyzed by an emotion engine.

[0511] Step 9:

[0512] The server receives progress data and sentiment data and analyzes it using progress management tools. For example, it generates alerts for tasks that are behind schedule.

[0513] Step 10:

[0514] The server readjusts task distribution based on emotional data. For example, it redistributes tasks from employees who are detected as stressed or fatigued to other employees.

[0515] Step 11:

[0516] The server visualizes progress and sentiment data in real time and displays it to each team member and manager through a dashboard. The displayed information includes overall progress, individual task status, and the team member's sentiment status.

[0517] Thus, the system of the present invention efficiently identifies, distributes, manages progress, and manages the emotional state of employees when each department collaborates to handle a project. This leads to increased work efficiency and appropriate management of the workload and stress levels of employees.

[0518] (Example 2)

[0519] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0520] Traditional task management systems fail to consider the emotional state of the person in charge, in addition to managing the progress of tasks. This can lead to inadequate management of the workload and a decrease in work efficiency. Furthermore, there is a problem in that appropriate measures cannot be taken when tasks are delayed due to the stress or fatigue of the person in charge.

[0521] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0522] In this invention, the server includes analysis means, task generation means, task distribution means, progress management means, emotion recognition means, task redistribution means, and display means. This enables task management and redistribution based on the emotional state of the person in charge.

[0523] "Analysis methods" refer to the means of receiving and analyzing sales manuals and project outlines sent from each department.

[0524] A "task generation method" is a means of generating specific tasks using data collected by an analysis method.

[0525] A "task distribution method" is a means of distributing generated tasks to each person in charge.

[0526] A "progress management method" is a means of receiving and analyzing the task progress status from each person in charge.

[0527] "Emotion recognition means" refers to a method for analyzing the emotional state of the person in charge and collecting that data.

[0528] A "task redistribution method" is a means of redistributing tasks based on data collected by an emotion recognition method.

[0529] "Display means" refers to means for displaying data collected by progress management means and emotion recognition means in real time.

[0530] The system of this invention is designed to enable efficient collaboration among departments, task identification, distribution, and progress management. This system primarily consists of servers, terminals, and users, and further incorporates an emotion engine to recognize user emotions. The following describes each element of the system and the program's processing.

[0531] server

[0532] The server receives sales manuals and project summaries sent from each department and analyzes them using a natural language processing engine (e.g., AWS Comprehend or Google Cloud Natural Language). The analyzed data is then converted into specific tasks by a task generation system. For example, if the phrase "client visit" is included, the server generates it as a task for "client visit".

[0533] The generated tasks are stored in a database and distributed using a task distribution system based on each assignee's skill set, current workload, and job title data. Assigned tasks are then notified to the assignee's terminal. While a task is in progress, the server receives progress data and analyzes it using a progress management system. If delays or problems occur, an alert is generated.

[0534] Furthermore, the system uses an emotion engine to analyze the user's emotional state (e.g., fatigue and stress) and collects data using emotion recognition tools. Based on this data, tasks are redistributed to reduce the workload on team members and promote efficient task progress. Progress and emotion data are visualized in real time and displayed through a dashboard.

[0535] terminal

[0536] The terminals used by staff in each department receive task notifications sent from the server and display the task list. Staff members use their terminals to check their assigned tasks and enter their completion status. The terminals can send task progress data and staff member sentiment data to the server.

[0537] User

[0538] Users operate the system and send sales manuals and project summaries to the server via their terminals. The assigned personnel check their tasks and update their progress as needed. Furthermore, an emotion engine analyzes the user's emotional state and redistributes tasks as necessary.

[0539] Example of a prompt

[0540] "Send the sales manual and project summary to the server for analysis and generate a new task."

[0541] "Redistribute tasks based on the progress and emotional data of the assigned personnel, and help resolve delays and problems."

[0542] The above is a specific example of the system's operation. The system of the present invention is configured to enable efficient collaboration among departments and significantly improve the efficiency of operations.

[0543] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0544] Program processing flow

[0545] Step 1: Sending Data

[0546] Users use terminals in their respective departments to send sales manuals and project summaries to the server. Input is in PDF or document format, and output is the server saving the received files. Specifically, the sales department uploads the latest customer list and visit plan to the server in PDF format.

[0547] Step 2: Analysis of the month

[0548] The server analyzes the received data using a natural language processing engine (e.g., AWS Comprehend or Google Cloud Natural Language). The input is the stored data, and the output is the extracted keywords and phrases from the analysis. For example, it can extract phrases such as "customer visit" and "presentation material creation" from a customer list document.

[0549] Step 3: Task Generation

[0550] The server generates specific tasks using a task generation mechanism based on the analysis results. The input is the analyzed keywords and phrases, and the output is the generated tasks. Specifically, from the keyword "customer visit," tasks such as "schedule customer visit" are automatically generated.

[0551] Step 4: Task Distribution

[0552] The server saves the generated task list to a database and distributes it to each person in charge using a task distribution mechanism. The input is the generated tasks, the skill sets of the people in charge, and their job titles, and the output is the distributed tasks. The legal department is assigned the task of "contract review," and the sales department is assigned the task of "customer visit."

[0553] Step 5: Task Notification

[0554] The server notifies the assigned task on the employee's terminal. The input is the assigned task, and the output is the notification message sent to the employee's terminal. Specifically, a notification titled "New Task: Confirm Customer Visit Schedule" will appear on the terminal of the sales department employee.

[0555] Step 6: Execute the task and enter the progress.

[0556] Users check their assigned tasks on their devices and proceed with execution. Input is the task's progress, and output is the transmission of progress data to the server. For example, if an employee enters "Customer visit completed" on their device, the progress status is updated.

[0557] Step 7: Progress Management

[0558] The server receives progress data and analyzes it using progress management tools. The input is progress data, and the output is the analysis results of the progress status and any necessary alerts. If a delay is detected, the server sends a "Task Delayed" alert to the person in charge.

[0559] Step 8: Collecting and analyzing emotional data

[0560] The emotion engine analyzes the user's facial expressions and speech to collect emotional data. The input is the user's emotional state (e.g., facial expressions and voice), and the output is the analyzed emotional data. If an employee experiences stress during their work, this state is recorded in the system.

[0561] Step 9: Redistributing tasks

[0562] The server redistributes tasks as needed based on emotional data. Inputs are emotional data and progress data, and output is the redistributed tasks. If a high-stress employee is behind schedule, the task is reassigned to another employee.

[0563] Step 10: Real-time visualization

[0564] The server visualizes progress and sentiment data in real time and displays it through a dashboard. The input is the collected progress and sentiment data, and the output is the display of the visualized dashboard. Each person in charge and manager can check the "progress bar" and "stakeholder's sentiment status" in real time.

[0565] The above describes the specific actions taken at each processing step of the system.

[0566] (Application Example 2)

[0567] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0568] Current task management systems often distribute tasks based solely on the skill set and workload of the assigned person, without considering their psychological burden or emotional state. As a result, this can lead to decreased motivation and reduced work efficiency. Furthermore, real-time monitoring of progress is limited, making flexible task redistribution difficult. This invention aims to solve these problems, streamline task management within factories, and achieve flexible management that takes into account the health and well-being of the assigned person.

[0569] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0570] In this invention, the server includes an analysis means, a task generation means that generates tasks using data collected by the analysis means, a task distribution means that distributes the tasks generated by the task generation means to each person in charge, a progress management means that receives and analyzes the progress of the tasks distributed by the task distribution means, an emotion engine means that recognizes the emotional state of the user, and a display means that displays the data collected by the progress management means and the data collected by the emotion engine means in real time. This makes it possible to distribute and manage tasks while taking into account not only the skill set and workload of the person in charge, but also their psychological state.

[0571] "Analysis methods" refer to the functions and processes for collecting and analyzing various types of data.

[0572] A "task generation method" is a function that creates specific tasks based on collected and analyzed data.

[0573] A "task distribution mechanism" is a function that assigns generated tasks to the appropriate person or robot.

[0574] A "progress management system" is a function that receives and analyzes the progress status of assigned tasks.

[0575] The "emotional engine" refers to a function that recognizes the emotional state of personnel or robots and collects it as data.

[0576] "Display means" refers to a function for visually displaying progress data and sentiment data.

[0577] A "natural language processing engine" is a technology used to analyze documents and extract meaning and keywords.

[0578] A "skill set" is a collection of skills and expertise possessed by an individual or robot.

[0579] "Current workload" refers to the amount of work and tasks that the person in charge or robot is currently handling.

[0580] "Rank data" refers to information about the rank and position of the person in charge or the robot.

[0581] The system of this invention streamlines task management within a factory and enables flexible management that takes into account the health status of the person in charge. The system consists of three main elements: a server, a terminal, and a user, and further incorporates an emotion engine that recognizes the user's emotions.

[0582] First, the server receives documents and instructions from within the factory and analyzes them using a natural language processing engine (e.g., Google Cloud Natural Language API). This analysis allows the task generation system to generate specific tasks. For example, if a phrase such as "quality inspection of product A" is included, the server will generate a task for "quality inspection of product A".

[0583] Next, the server saves the generated task list to a database and appropriately distributes tasks using a task distribution mechanism based on each robot and operator's skill set, current workload, and rank data. In this process, the server assigns tasks to the robot or operator with the most available capacity. The assigned tasks are then notified to the operator's terminal.

[0584] Humans and robots perform their assigned tasks and report their progress to the server. The server analyzes the progress using progress management tools and generates alerts if delays or problems occur. Furthermore, because an emotion engine is built in, emotional data of the humans and robots is also collected. This emotional data is collected, for example, using sensors and voice analysis microphones. This makes it possible to detect psychological burden and stress levels.

[0585] The server integrates and analyzes collected progress and sentiment data, and redistributes tasks as needed. For example, if an employee is under high stress, their tasks can be reassigned to other employees. This appropriately adjusts the workload of employees and promotes the smooth progress of work.

[0586] Progress and sentiment data are visualized in real time and displayed to each team member and manager through a dashboard. This allows for an at-a-glance overview of overall progress, the status of each task, and the sentiment of the team members and robots.

[0587] Specific examples include tasks such as "quality inspection" and "equipment maintenance" in a factory. This system uses a natural language processing engine to extract these tasks and assign them to appropriate robots or personnel. An emotion engine allows for task redistribution if a person's stress level is high.

[0588] Examples of prompt statements include:

[0589] "Generate quality inspection and equipment maintenance tasks within the factory and distribute them to the robots in the most optimal way. Also, consider the stress level and progress of each robot and display this information on a dashboard. Progress data is stored in a temporary database."

[0590] These are some examples.

[0591] This will streamline task management within the factory and enable flexible management that takes into account the health status of personnel and robots. Furthermore, it will improve operational efficiency while minimizing psychological stress.

[0592] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0593] Step 1:

[0594] The server receives documents and instructions from within the factory. The received data is parsed by a natural language processing engine (e.g., Google Cloud Natural Language API). The input is documents and instructions from within the factory, and the output is keywords and phrases that indicate extracted tasks. To execute this, the server analyzes the text data and identifies the necessary tasks.

[0595] Step 2:

[0596] The server generates specific tasks based on keywords and phrases extracted by the natural language processing engine. The task generation mechanism fulfills this role. The input is the keywords and phrases extracted in the previous step, and the output is a list of specific tasks. The server creates each task based on the text analysis results.

[0597] Step 3:

[0598] The server saves the generated task list to the database. The input is the task list, and the output is the task list stored in the database. The server performs database operations to record the task list.

[0599] Step 4:

[0600] The server distributes tasks generated using a task distribution mechanism to individual personnel and robots. The distribution criteria are the skill sets, current workload, and rank data of the personnel and robots. The input is a task list and information on each personnel and robot, and the output is a list of tasks distributed to the personnel and robots. The server analyzes the status of each personnel and robot to perform optimal distribution.

[0601] Step 5:

[0602] The terminal notifies the assigned personnel or robots of the assigned tasks and initiates their execution. The input is the assigned task list, and the output is the task information notified on the terminal. The terminal notifies the personnel or robots of the tasks and monitors their execution status.

[0603] Step 6:

[0604] Human resources or robots perform tasks and report their progress to the server via terminals. The input is progress data, and the output is the progress data sent to the server. Human resources or robots complete tasks and report their progress.

[0605] Step 7:

[0606] The server receives and analyzes progress data using a progress management system. The input is progress data, and the output is the analyzed progress data and alert information. The server evaluates the status of ongoing tasks and generates alerts as needed.

[0607] Step 8:

[0608] The emotion engine recognizes the emotional state of the person in charge or the robot and collects data. The input is emotional data (e.g., from sensors or voice analysis), and the output is emotional data sent to the server. The emotion engine analyzes the psychological state of the person in charge or the robot.

[0609] Step 9:

[0610] The server integrates progress and sentiment data and redistributes tasks as needed. Inputs are progress and sentiment data, and output is a redistributed task list. Based on this data, the server readjusts the load balancing.

[0611] Step 10:

[0612] Using a display mechanism, progress data and sentiment data are shown on a dashboard in real time. The input is integrated progress data and sentiment data, and the output is the information displayed on the dashboard. The server makes this information visually accessible to monitors and administrators.

[0613] Through these steps, the system can efficiently and flexibly manage tasks within the factory, while also appropriately managing the psychological burden on personnel and robots.

[0614] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0615] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0616] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0617] [Third Embodiment]

[0618] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0619] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0620] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0621] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0622] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0623] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0624] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0625] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0626] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0627] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0628] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0629] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0630] The system of this invention is configured to enable efficient task identification and distribution when various departments collaborate to handle a project. The system consists of three main elements: a server, terminals, and users.

[0631] First, the server receives sales manuals and project summaries sent from each department's terminal. These documents are analyzed using a natural language processing engine to extract important keywords and phrases. For example, if the sales manual contains the phrase "client visit," the server uses this information to generate a task for "client visit."

[0632] Next, the server manages the generated tasks. Based on the preceding information, a specific task list is generated by the task generation mechanism. The server then appropriately distributes tasks to each person in charge based on this list. When distributing tasks, factors such as the person in charge's skill set, current workload, and job title are taken into consideration.

[0633] On the terminal, each department's assigned personnel check and execute their tasks. For example, if the sales department is assigned the task of "creating a proposal," the person in charge will obtain detailed task information through the terminal and create the proposal. The progress of this process is reported from the terminal to the server in real time.

[0634] The server receives progress data from each team member and analyzes it using progress management tools. Based on this analysis, delays and problems in ongoing tasks are detected early. Furthermore, progress data is displayed in real time, allowing team members and managers to check the overall progress through a dashboard.

[0635] For example, the server assigns the task "Contract Review" to the legal department. The legal department staff member checks this task on their terminal, reviews the contract, and then enters the progress into the system. The server receives this information and updates the overall task list.

[0636] This system streamlines task identification, distribution, and progress management compared to traditional manual methods. Each team member can check the progress of their tasks in real time and make necessary adjustments quickly. This significantly improves overall work efficiency.

[0637] In general, the system of the present invention provides a powerful tool for effectively and efficiently managing tasks when various departments collaborate to handle a project.

[0638] The following describes the processing flow.

[0639] Step 1:

[0640] The terminals are used by staff members in each department to upload sales manuals and project summaries to the server. The uploaded documents are in PDF or text file format.

[0641] Step 2:

[0642] The server receives the uploaded material and sends it to a natural language processing engine. This engine analyzes the material and extracts key keywords and phrases.

[0643] Step 3:

[0644] The server generates specific tasks using a task generation mechanism based on the analysis results. The generated tasks include information on the necessary resources and the departments involved.

[0645] Step 4:

[0646] The server saves the generated task list to a database. The saved task list is then used in subsequent processing.

[0647] Step 5:

[0648] The server collects and analyzes information such as each user's skill set, current workload, and job title. Based on this information, it appropriately distributes tasks using a task distribution mechanism.

[0649] Step 6:

[0650] The server notifies each assigned person's terminal of the assigned task. The notification includes detailed information about the task.

[0651] Step 7:

[0652] The terminal displays the tasks received by each person in charge. The person in charge checks their tasks and proceeds to execute them.

[0653] Step 8:

[0654] Users (assigned personnel) input task progress into the system via their terminals. This information is updated in real time.

[0655] Step 9:

[0656] The server receives progress data and analyzes ongoing tasks using progress management tools. It generates alerts if delays or problems occur.

[0657] Step 10:

[0658] The server visualizes progress data and displays it in real time to each person in charge and administrator through a dashboard. The display includes overall progress and the status of individual tasks.

[0659] In this way, the system of the present invention efficiently identifies, distributes, and manages the progress of tasks when each department collaborates to handle a project. This leads to increased efficiency in operations.

[0660] (Example 1)

[0661] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0662] Traditional manual task management methods presented problems when multiple departments collaborated on a project, such as the inefficient identification, distribution, and progress management of tasks. Furthermore, it was difficult to appropriately distribute tasks considering each person's workload and skill set, often resulting in decreased overall work efficiency. To address this, a more effective and efficient task management system is needed.

[0663] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0664] In this invention, the server includes means for receiving and analyzing data, task generation means for extracting keywords from the analyzed data and generating tasks, task distribution means for distributing tasks to assigned personnel using the generated task list, means for receiving the progress of tasks performed by each assigned personnel, progress management means, and display means. This enables efficient task identification, distribution, and progress management, and allows for appropriate task distribution that takes into account the workload and skill sets of each assigned personnel.

[0665] The "means for receiving and analyzing documents" refer to the methods for receiving documents such as sales manuals and project summaries sent from terminals in each department onto a server, and then analyzing these documents using a natural language processing engine.

[0666] A "task generation method" is a means of extracting important keywords and phrases from analyzed data and generating specific tasks based on them.

[0667] A "task distribution method" is a means of appropriately distributing tasks to assigned personnel based on a generated task list, taking into account the assigned personnel's skill set, current workload, and job title data.

[0668] "Means for receiving progress reports" refers to the means by which each person in charge reports the progress of their tasks from their terminal to the server in real time.

[0669] A "progress management method" is a means of analyzing received progress data to detect the progress and delays of tasks at an early stage.

[0670] A "display method" refers to a means of visualizing data analyzed by progress management methods in real time, allowing each person in charge and manager to check the overall progress status through a dashboard or similar means.

[0671] This invention is a system for efficiently identifying and distributing tasks when various departments collaborate to handle a project. This system consists of three main elements: a server, terminals, and users.

[0672] First, the server receives sales manuals and project summaries sent from each department's terminal. These documents are analyzed using a natural language processing engine such as the Google Cloud Natural Language API, and important keywords and phrases are extracted. For example, if the sales manual contains the phrase "client visit," the server will use this information to generate a task for "client visit."

[0673] Next, the server manages the generated tasks. Task generation is achieved using custom Python scripts or the Task Management API to create a detailed task list based on the aforementioned analysis results. The server then appropriately distributes tasks to each assignee based on this list. When distributing tasks, factors such as the assignee's skill set, current workload, and job title are considered. This data is managed, for example, in an SQL database.

[0674] On the terminal side, each department's assigned personnel check and execute their tasks. Each person obtains detailed task information through their terminal and proceeds with execution. For example, if a sales department employee is assigned the task of "creating a proposal," they will use a task management app on their terminal (e.g., Trello or JIRA) to obtain detailed task information and create the proposal. The progress during this process is reported to the server in real time.

[0675] The server receives progress data reported by each team member in real time and analyzes it using progress management tools (e.g., a Grafana dashboard). Based on this analysis, delays and problems in ongoing tasks are detected early. Progress data is displayed in real time, allowing each team member and manager to check the overall progress through the dashboard.

[0676] For example, the server assigns the task "Contract Review" to the legal department. The legal department staff member checks this task on their terminal, reviews the contract, and then enters the progress into the system. The server receives this information and updates the overall task list.

[0677] This system streamlines task identification, distribution, and progress management compared to traditional manual methods. Each team member can check the progress of their tasks in real time and make necessary adjustments quickly. This significantly improves overall work efficiency.

[0678] Specific examples and prompt statements

[0679] Specific example 1:

[0680] The server receives documents from the sales department and analyzes them using a natural language processing engine to extract the important phrase "client visit." Based on this, the server generates a "client visit" task and assigns it to a sales representative. The representative checks the task details on their terminal and conducts the client visit. The progress is reported to the server in real time.

[0681] Example of a prompt:

[0682] "Please provide a detailed explanation of the server's processing procedures for analyzing sales department documents, generating tasks, and distributing them."

[0683] Specific example 2:

[0684] The server assigns the legal department a task called "contract review." The legal department staff member checks the task on their terminal, reviews the contract, and then enters the progress into the system. The server receives this information and updates the overall task list.

[0685] Example of a prompt:

[0686] "Please explain in detail the entire process from assigning tasks to the legal department to updating their progress."

[0687] These explanations will allow for a concrete understanding of each processing step, enabling the effective operation of the system.

[0688] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0689] Step 1:

[0690] Receipt of materials

[0691] The server receives sales manuals and project overview documents sent from terminals in each department.

[0692] Specific actions include each terminal uploading files to the server. For example, the sales department might send an Excel file containing details of a new project to the server.

[0693] Input: Sales manuals and project overview documents

[0694] Output: Received files

[0695] Step 2:

[0696] Analysis of the materials

[0697] The server analyzes the received data using the Google Cloud Natural Language API.

[0698] The analysis process extracts important keywords and phrases from the text. For example, the phrase "client visit" might be detected.

[0699] Input: Received file

[0700] Data processing: Text analysis and keyword extraction of documents using a natural language processing engine.

[0701] Output: Extracted keywords and phrases

[0702] Step 3:

[0703] Task generation

[0704] The server generates specific tasks based on the extracted keywords and phrases.

[0705] Tasks such as "client visit" are created in detail using custom Python scripts, etc.

[0706] Input: Extracted keywords or phrases

[0707] Data Calculation: Applying Keyword-Based Task Generation Logic

[0708] Output: Generated tasks

[0709] Step 4:

[0710] Task distribution

[0711] The server then appropriately distributes tasks to each person in charge based on the generated task list.

[0712] Tasks are distributed considering the assigned person's skill set, current workload, and job title data. For example, tasks are assigned to the appropriate person by referring to the person data stored in the SQL database.

[0713] Input: Generated tasks, assignee's skill set, current workload, job title data

[0714] Data calculation: Selecting personnel using database queries

[0715] Output: Assigned tasks

[0716] Step 5:

[0717] Task confirmation and execution

[0718] On the terminal side, the person in charge of each department checks the assigned task and retrieves detailed information.

[0719] The person in charge performs the task through their terminal. For example, a sales representative checks the task "Create a proposal" and then actually creates the proposal.

[0720] Input: Notification of assigned task

[0721] Data processing: Displaying task details

[0722] Output: Task execution status

[0723] Step 6:

[0724] Progress report

[0725] The person in charge reports the progress of the task to the server in real time via their terminal as the task progresses.

[0726] For example, after a "client visit," enter the status as "completed" in the terminal.

[0727] Input: Task progress information

[0728] Data processing: Update progress status

[0729] Output: Updated progress data

[0730] Step 7:

[0731] Progress management and display

[0732] The server receives the reported progress data in real time and analyzes and displays it using a Grafana dashboard.

[0733] This allows for early detection of delays and problems, and provides visibility into overall progress. Administrators can view detailed progress through the dashboard.

[0734] Input: Updated progress data

[0735] Data processing: Analysis of progress data and display on dashboards.

[0736] Output: Real-time progress dashboard

[0737] This system enables efficient task identification, generation, distribution, and progress management, thereby improving overall business efficiency.

[0738] (Application Example 1)

[0739] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0740] Traditional factory task management was often done manually, which was not only inefficient but also made it difficult to track work progress in real time. Furthermore, assigning appropriate tasks to each machine quickly was challenging, leading to a decline in overall production efficiency. In particular, when various work instructions existed, extracting and distributing appropriate tasks became complex, and assigning tasks while considering the skill sets and job titles of the personnel involved was an extra step.

[0741] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0742] In this invention, the server includes an analysis means, a task generation means, a task distribution means, a progress management means for receiving and analyzing task progress from each person in charge, a display means for displaying the data collected by the progress management means in real time, a task extraction means installed in a machine in the factory and equipped with a natural language processing engine for extracting work tasks from work instructions, and a task monitoring means for distributing the extracted tasks to the machine and monitoring their progress in real time. This enables efficient task extraction, appropriate task distribution, and real-time progress monitoring of work.

[0743] 1. "Analysis tools" are system components that analyze documents and data and extract important information.

[0744] 2. A "task generation means" is a system component that generates work tasks based on collected data.

[0745] 3. A "task distribution means" is a system component that appropriately assigns generated work tasks to each person or machine.

[0746] 4. A "progress management system" is a system component that receives and analyzes the work progress status from each person in charge or machine.

[0747] 5. "Display means" refers to a system component for displaying data collected by the progress management means in real time.

[0748] 6. A "task extraction means" is a system component equipped with a natural language processing engine that extracts work tasks from work instructions.

[0749] 7. A "task monitoring means" is a system component that distributes extracted tasks to each machine and monitors their progress in real time.

[0750] Modes for carrying out the invention

[0751] This invention provides a system that utilizes applications installed on machinery within a factory to achieve efficient extraction, distribution, and progress monitoring of work tasks. This system consists of three main components: a server, terminals, and users.

[0752] server

[0753] The server receives work orders sent from each department and analyzes them using a natural language processing engine. Important tasks are extracted from the analyzed data, and a detailed task list is generated based on these. The generated tasks are then appropriately distributed to each machine and person in the factory. Task distribution takes into account machine capabilities, current load levels, and the skill sets and job titles of the personnel. Progress data is received from each person and machine using a progress management system and analyzed in real time.

[0754] terminal

[0755] Terminals are assigned to machines and personnel within each factory. Personnel and machines check and execute their assigned tasks through these terminals. For example, specific tasks such as "assemble product A" or "quality inspection of product B" are assigned. Progress is reported from the terminals to the server in real time, and the server updates the task list based on this information.

[0756] User

[0757] Users (factory managers and workers) can check the overall progress in real time through the dashboard. Because progress data is displayed, delays and problems with tasks can be addressed quickly. This system significantly improves efficiency compared to traditional manual task management and allows for effective monitoring of overall work progress.

[0758] Hardware and software used

[0759] Hardware: Machinery, servers, and terminals within the factory.

[0760] software:

[0761] Spacy (natural language processing engine)

[0762] allocation_module (task allocation logic module)

[0763] task_monitor (task progress monitoring module)

[0764] Specific examples

[0765] For example, in an electronics assembly plant, if there are work instructions for "assemble product A" and "quality inspection of product B," the assembly robot will be assigned the "assembly" task, and the inspection robot will be assigned the "quality inspection" task. The progress of these tasks is reported to the server in real time and can be viewed on a dashboard.

[0766] Example of a prompt

[0767] "To efficiently carry out the assembly of product A and the quality inspection of product B within the factory, we want to assign appropriate tasks to machines and personnel. First, please create a system that extracts tasks from work instructions, then assigns those tasks to machines and personnel, and monitors progress in real time."

[0768] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0769] Processing flow of the system program that implements the application example

[0770] Step 1:

[0771] The server receives work orders sent from each department. The input is work orders sent to the server in electronic format. The server saves the received work orders. The output is the saved work order file.

[0772] Step 2:

[0773] The server analyzes saved work orders using a natural language processing engine (spacy). The input is the saved work orders. The server extracts important keywords and phrases from the work orders. Specifically, it extracts noun phrases from the document and selects those related to "work." The output is a list of the extracted keywords and phrases.

[0774] Step 3:

[0775] The server generates a task list based on extracted keywords and phrases. The input consists of keywords and phrases extracted by a natural language processing engine. The server uses this information to create specific work tasks. Specifically, it generates task objects based on the keywords. The output is the generated task list.

[0776] Step 4:

[0777] The server distributes the generated task list to the corresponding machine and person in charge at each terminal. Inputs include the generated task list and information about each machine and person in charge (skill set, current workload, job title data). The server uses this information to appropriately assign tasks. Specifically, it matches appropriate tasks with their targets based on specified conditions. The output is the task list assigned to each machine and person in charge.

[0778] Step 5:

[0779] The terminal displays tasks received from the server, and the person in charge or the machine begins working on those tasks. The input is a list of assigned tasks sent to the terminal. Specifically, the terminal receives and displays the task list. The output is the person in charge or the machine confirming the task details.

[0780] Step 6:

[0781] The server receives progress reports from terminals and updates the progress status in real time. The input is progress data sent from the terminals. The server receives this data and updates the progress status. Specifically, it records the progress data in a database and updates the overall progress list. The output is the updated progress list.

[0782] Step 7:

[0783] The server displays progress data on a dashboard in real time. The input is an updated progress list. Specifically, it graphically displays the progress list on the dashboard. The output is a dashboard where each person in charge and administrator can check the status in real time.

[0784] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0785] The system of this invention is configured to ensure efficient task identification and distribution when various departments collaborate to handle a project. The system consists of three main elements: a server, a terminal, and a user, and further incorporates an emotion engine that recognizes the user's emotions.

[0786] First, the server receives sales manuals and project summaries sent from each department's terminal and analyzes them using a natural language processing engine. The keywords and phrases extracted through the analysis are then converted into specific tasks by a task generation mechanism. If the sales manual contains a phrase such as "client visit," the server will generate a task for "client visit."

[0787] Next, the server saves the generated task list to a database and appropriately distributes tasks using a task distribution mechanism based on each person's skill set, current workload, and job title data. The distributed tasks are notified to the person's terminal. On the terminal, each person checks the assigned task and proceeds to execute it.

[0788] During a task, the user inputs the task's progress into the system via a terminal. This progress data is received by the server and analyzed using progress management tools. If delays or problems occur, the server detects them and generates an alert. Furthermore, because an emotion engine is incorporated, it analyzes the user's facial expressions and statements to collect emotional data.

[0789] The server also uses emotional data recognized by the emotion engine as an element of progress management. For example, if an employee experiencing fatigue or stress is causing delays in a task, the task is redistributed taking this emotional data into consideration. This promotes the efficient progress of tasks.

[0790] Progress and sentiment data are visualized in real time and displayed to each team member and manager via a dashboard. This allows for an at-a-glance overview of overall progress, the status of each task, and the emotional state of the team members.

[0791] For example, the server assigns the task "contract review" to the legal department. When a legal department employee reviews and completes this task on their terminal, if the emotion engine detects the employee's stress level, the server analyzes this and, if necessary, reassigns the task to another employee. This process reduces the employee's workload and ensures the smooth progress of the task.

[0792] Thus, the system of the present invention enables more efficient and flexible work execution by considering not only the task identification, distribution, and progress management when each department collaborates to handle a project, but also the emotional state of the person in charge. As a result, the overall efficiency of operations is greatly improved.

[0793] The following describes the processing flow.

[0794] Step 1:

[0795] The terminals are used by staff members in each department to upload sales manuals and project summaries to the server. The uploaded documents are in PDF or text file format.

[0796] Step 2:

[0797] The server receives the uploaded material and sends it to a natural language processing engine. This engine analyzes the material and extracts key keywords and phrases.

[0798] Step 3:

[0799] The server generates specific tasks using a task generation mechanism based on the analysis results. For example, it adds tasks such as "visit client" and "draft contract" to the list.

[0800] Step 4:

[0801] The server saves the generated task list to the database. The task list also includes a detailed description of each task and the resources required.

[0802] Step 5:

[0803] The server collects data on each user's skill set, current workload, and job title, and uses this information to appropriately distribute tasks using a task distribution mechanism. For example, difficult tasks are assigned to experienced users, while relatively easy tasks are assigned to newer users.

[0804] Step 6:

[0805] The server notifies each assignee's terminal of the assigned task. The notification includes detailed task information, deadline, and related resource information.

[0806] Step 7:

[0807] The terminal displays the tasks received by each person in charge, and the person in charge checks their own tasks. The person in charge checks the details of the task and proceeds to execute it.

[0808] Step 8:

[0809] The user (assigned person) inputs task progress and emotional state into the system via a terminal. The emotional state is analyzed by an emotion engine.

[0810] Step 9:

[0811] The server receives progress data and sentiment data and analyzes it using progress management tools. For example, it generates alerts for tasks that are behind schedule.

[0812] Step 10:

[0813] The server readjusts task distribution based on emotional data. For example, it redistributes tasks from employees who are detected as stressed or fatigued to other employees.

[0814] Step 11:

[0815] The server visualizes progress and sentiment data in real time and displays it to each team member and manager through a dashboard. The displayed information includes overall progress, individual task status, and the team member's sentiment status.

[0816] Thus, the system of the present invention efficiently identifies, distributes, manages progress, and manages the emotional state of employees when each department collaborates to handle a project. This leads to increased work efficiency and appropriate management of the workload and stress levels of employees.

[0817] (Example 2)

[0818] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0819] Traditional task management systems fail to consider the emotional state of the person in charge, in addition to managing the progress of tasks. This can lead to inadequate management of the workload and a decrease in work efficiency. Furthermore, there is a problem in that appropriate measures cannot be taken when tasks are delayed due to the stress or fatigue of the person in charge.

[0820] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0821] In this invention, the server includes analysis means, task generation means, task distribution means, progress management means, emotion recognition means, task redistribution means, and display means. This enables task management and redistribution based on the emotional state of the person in charge.

[0822] "Analysis methods" refer to the means of receiving and analyzing sales manuals and project outlines sent from each department.

[0823] A "task generation method" is a means of generating specific tasks using data collected by an analysis method.

[0824] A "task distribution method" is a means of distributing generated tasks to each person in charge.

[0825] A "progress management method" is a means of receiving and analyzing the task progress status from each person in charge.

[0826] "Emotion recognition means" refers to a method for analyzing the emotional state of the person in charge and collecting that data.

[0827] A "task redistribution method" is a means of redistributing tasks based on data collected by an emotion recognition method.

[0828] "Display means" refers to means for displaying data collected by progress management means and emotion recognition means in real time.

[0829] The system of this invention is designed to enable efficient collaboration among departments, task identification, distribution, and progress management. This system primarily consists of servers, terminals, and users, and further incorporates an emotion engine to recognize user emotions. The following describes each element of the system and the program's processing.

[0830] server

[0831] The server receives sales manuals and project summaries sent from each department and analyzes them using a natural language processing engine (e.g., AWS Comprehend or Google Cloud Natural Language). The analyzed data is then converted into specific tasks by a task generation system. For example, if the phrase "client visit" is included, the server generates it as a task for "client visit".

[0832] The generated tasks are stored in a database and distributed using a task distribution system based on each assignee's skill set, current workload, and job title data. Assigned tasks are then notified to the assignee's terminal. While a task is in progress, the server receives progress data and analyzes it using a progress management system. If delays or problems occur, an alert is generated.

[0833] Furthermore, the system uses an emotion engine to analyze the user's emotional state (e.g., fatigue and stress) and collects data using emotion recognition tools. Based on this data, tasks are redistributed to reduce the workload on team members and promote efficient task progress. Progress and emotion data are visualized in real time and displayed through a dashboard.

[0834] terminal

[0835] The terminals used by staff in each department receive task notifications sent from the server and display the task list. Staff members use their terminals to check their assigned tasks and enter their completion status. The terminals can send task progress data and staff member sentiment data to the server.

[0836] User

[0837] Users operate the system and send sales manuals and project summaries to the server via their terminals. The assigned personnel check their tasks and update their progress as needed. Furthermore, an emotion engine analyzes the user's emotional state and redistributes tasks as necessary.

[0838] Example of a prompt

[0839] "Send the sales manual and project summary to the server for analysis and generate a new task."

[0840] "Redistribute tasks based on the progress and emotional data of the assigned personnel, and help resolve delays and problems."

[0841] The above is a specific example of the system's operation. The system of the present invention is configured to enable efficient collaboration among departments and significantly improve the efficiency of operations.

[0842] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0843] Program processing flow

[0844] Step 1: Sending Data

[0845] Users use terminals in their respective departments to send sales manuals and project summaries to the server. Input is in PDF or document format, and output is the server saving the received files. Specifically, the sales department uploads the latest customer list and visit plan to the server in PDF format.

[0846] Step 2: Analysis of the month

[0847] The server analyzes the received data using a natural language processing engine (e.g., AWS Comprehend or Google Cloud Natural Language). The input is the stored data, and the output is the extracted keywords and phrases from the analysis. For example, it can extract phrases such as "customer visit" and "presentation material creation" from a customer list document.

[0848] Step 3: Task Generation

[0849] The server generates specific tasks using a task generation mechanism based on the analysis results. The input is the analyzed keywords and phrases, and the output is the generated tasks. Specifically, from the keyword "customer visit," tasks such as "schedule customer visit" are automatically generated.

[0850] Step 4: Task Distribution

[0851] The server saves the generated task list to a database and distributes it to each person in charge using a task distribution mechanism. The input is the generated tasks, the skill sets of the people in charge, and their job titles, and the output is the distributed tasks. The legal department is assigned the task of "contract review," and the sales department is assigned the task of "customer visit."

[0852] Step 5: Task Notification

[0853] The server notifies the assigned task on the employee's terminal. The input is the assigned task, and the output is the notification message sent to the employee's terminal. Specifically, a notification titled "New Task: Confirm Customer Visit Schedule" will appear on the terminal of the sales department employee.

[0854] Step 6: Execute the task and enter the progress.

[0855] Users check their assigned tasks on their devices and proceed with execution. Input is the task's progress, and output is the transmission of progress data to the server. For example, if an employee enters "Customer visit completed" on their device, the progress status is updated.

[0856] Step 7: Progress Management

[0857] The server receives progress data and analyzes it using progress management tools. The input is progress data, and the output is the analysis results of the progress status and any necessary alerts. If a delay is detected, the server sends a "Task Delayed" alert to the person in charge.

[0858] Step 8: Collecting and analyzing emotional data

[0859] The emotion engine analyzes the user's facial expressions and speech to collect emotional data. The input is the user's emotional state (e.g., facial expressions and voice), and the output is the analyzed emotional data. If an employee experiences stress during their work, this state is recorded in the system.

[0860] Step 9: Redistributing tasks

[0861] The server redistributes tasks as needed based on emotional data. Inputs are emotional data and progress data, and output is the redistributed tasks. If a high-stress employee is behind schedule, the task is reassigned to another employee.

[0862] Step 10: Real-time visualization

[0863] The server visualizes progress and sentiment data in real time and displays it through a dashboard. The input is the collected progress and sentiment data, and the output is the display of the visualized dashboard. Each person in charge and manager can check the "progress bar" and "stakeholder's sentiment status" in real time.

[0864] The above describes the specific actions taken at each processing step of the system.

[0865] (Application Example 2)

[0866] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0867] Current task management systems often distribute tasks based solely on the skill set and workload of the assigned person, without considering their psychological burden or emotional state. As a result, this can lead to decreased motivation and reduced work efficiency. Furthermore, real-time monitoring of progress is limited, making flexible task redistribution difficult. This invention aims to solve these problems, streamline task management within factories, and achieve flexible management that takes into account the health and well-being of the assigned person.

[0868] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0869] In this invention, the server includes an analysis means, a task generation means that generates tasks using data collected by the analysis means, a task distribution means that distributes the tasks generated by the task generation means to each person in charge, a progress management means that receives and analyzes the progress of the tasks distributed by the task distribution means, an emotion engine means that recognizes the emotional state of the user, and a display means that displays the data collected by the progress management means and the data collected by the emotion engine means in real time. This makes it possible to distribute and manage tasks while taking into account not only the skill set and workload of the person in charge, but also their psychological state.

[0870] "Analysis methods" refer to the functions and processes for collecting and analyzing various types of data.

[0871] A "task generation method" is a function that creates specific tasks based on collected and analyzed data.

[0872] A "task distribution mechanism" is a function that assigns generated tasks to the appropriate person or robot.

[0873] A "progress management system" is a function that receives and analyzes the progress status of assigned tasks.

[0874] The "emotional engine" refers to a function that recognizes the emotional state of personnel or robots and collects it as data.

[0875] "Display means" refers to a function for visually displaying progress data and sentiment data.

[0876] A "natural language processing engine" is a technology used to analyze documents and extract meaning and keywords.

[0877] A "skill set" is a collection of skills and expertise possessed by an individual or robot.

[0878] "Current workload" refers to the amount of work and tasks that the person in charge or robot is currently handling.

[0879] "Rank data" refers to information about the rank and position of the person in charge or the robot.

[0880] The system of this invention streamlines task management within a factory and enables flexible management that takes into account the health status of the person in charge. The system consists of three main elements: a server, a terminal, and a user, and further incorporates an emotion engine that recognizes the user's emotions.

[0881] First, the server receives documents and instructions from within the factory and analyzes them using a natural language processing engine (e.g., Google Cloud Natural Language API). This analysis allows the task generation system to generate specific tasks. For example, if a phrase such as "quality inspection of product A" is included, the server will generate a task for "quality inspection of product A".

[0882] Next, the server saves the generated task list to a database and appropriately distributes tasks using a task distribution mechanism based on each robot and operator's skill set, current workload, and rank data. In this process, the server assigns tasks to the robot or operator with the most available capacity. The assigned tasks are then notified to the operator's terminal.

[0883] Humans and robots perform their assigned tasks and report their progress to the server. The server analyzes the progress using progress management tools and generates alerts if delays or problems occur. Furthermore, because an emotion engine is built in, emotional data of the humans and robots is also collected. This emotional data is collected, for example, using sensors and voice analysis microphones. This makes it possible to detect psychological burden and stress levels.

[0884] The server integrates and analyzes collected progress and sentiment data, and redistributes tasks as needed. For example, if an employee is under high stress, their tasks can be reassigned to other employees. This appropriately adjusts the workload of employees and promotes the smooth progress of work.

[0885] Progress and sentiment data are visualized in real time and displayed to each team member and manager through a dashboard. This allows for an at-a-glance overview of overall progress, the status of each task, and the sentiment of the team members and robots.

[0886] Specific examples include tasks such as "quality inspection" and "equipment maintenance" in a factory. This system uses a natural language processing engine to extract these tasks and assign them to appropriate robots or personnel. An emotion engine allows for task redistribution if a person's stress level is high.

[0887] Examples of prompt statements include:

[0888] "Generate quality inspection and equipment maintenance tasks within the factory and distribute them to the robots in the most optimal way. Also, consider the stress level and progress of each robot and display this information on a dashboard. Progress data is stored in a temporary database."

[0889] These are some examples.

[0890] This will streamline task management within the factory and enable flexible management that takes into account the health status of personnel and robots. Furthermore, it will improve operational efficiency while minimizing psychological stress.

[0891] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0892] Step 1:

[0893] The server receives documents and instructions from within the factory. The received data is parsed by a natural language processing engine (e.g., Google Cloud Natural Language API). The input is documents and instructions from within the factory, and the output is keywords and phrases that indicate extracted tasks. To execute this, the server analyzes the text data and identifies the necessary tasks.

[0894] Step 2:

[0895] The server generates specific tasks based on keywords and phrases extracted by the natural language processing engine. The task generation mechanism fulfills this role. The input is the keywords and phrases extracted in the previous step, and the output is a list of specific tasks. The server creates each task based on the text analysis results.

[0896] Step 3:

[0897] The server saves the generated task list to the database. The input is the task list, and the output is the task list stored in the database. The server performs database operations to record the task list.

[0898] Step 4:

[0899] The server distributes tasks generated using a task distribution mechanism to individual personnel and robots. The distribution criteria are the skill sets, current workload, and rank data of the personnel and robots. The input is a task list and information on each personnel and robot, and the output is a list of tasks distributed to the personnel and robots. The server analyzes the status of each personnel and robot to perform optimal distribution.

[0900] Step 5:

[0901] The terminal notifies the assigned personnel or robots of the assigned tasks and initiates their execution. The input is the assigned task list, and the output is the task information notified on the terminal. The terminal notifies the personnel or robots of the tasks and monitors their execution status.

[0902] Step 6:

[0903] Human resources or robots perform tasks and report their progress to the server via terminals. The input is progress data, and the output is the progress data sent to the server. Human resources or robots complete tasks and report their progress.

[0904] Step 7:

[0905] The server receives and analyzes progress data using a progress management system. The input is progress data, and the output is the analyzed progress data and alert information. The server evaluates the status of ongoing tasks and generates alerts as needed.

[0906] Step 8:

[0907] The emotion engine recognizes the emotional state of the person in charge or the robot and collects data. The input is emotional data (e.g., from sensors or voice analysis), and the output is emotional data sent to the server. The emotion engine analyzes the psychological state of the person in charge or the robot.

[0908] Step 9:

[0909] The server integrates progress and sentiment data and redistributes tasks as needed. Inputs are progress and sentiment data, and output is a redistributed task list. Based on this data, the server readjusts the load balancing.

[0910] Step 10:

[0911] Using a display mechanism, progress data and sentiment data are shown on a dashboard in real time. The input is integrated progress data and sentiment data, and the output is the information displayed on the dashboard. The server makes this information visually accessible to monitors and administrators.

[0912] Through these steps, the system can efficiently and flexibly manage tasks within the factory, while also appropriately managing the psychological burden on personnel and robots.

[0913] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0914] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0915] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0916] [Fourth Embodiment]

[0917] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0918] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0919] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0920] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0921] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0922] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0923] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0924] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0925] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0926] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0927] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0928] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0929] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0930] The system of this invention is configured to enable efficient task identification and distribution when various departments collaborate to handle a project. The system consists of three main elements: a server, terminals, and users.

[0931] First, the server receives sales manuals and project summaries sent from each department's terminal. These documents are analyzed using a natural language processing engine to extract important keywords and phrases. For example, if the sales manual contains the phrase "client visit," the server uses this information to generate a task for "client visit."

[0932] Next, the server manages the generated tasks. Based on the preceding information, a specific task list is generated by the task generation mechanism. The server then appropriately distributes tasks to each person in charge based on this list. When distributing tasks, factors such as the person in charge's skill set, current workload, and job title are taken into consideration.

[0933] On the terminal, each department's assigned personnel check and execute their tasks. For example, if the sales department is assigned the task of "creating a proposal," the person in charge will obtain detailed task information through the terminal and create the proposal. The progress of this process is reported from the terminal to the server in real time.

[0934] The server receives progress data from each team member and analyzes it using progress management tools. Based on this analysis, delays and problems in ongoing tasks are detected early. Furthermore, progress data is displayed in real time, allowing team members and managers to check the overall progress through a dashboard.

[0935] For example, the server assigns the task "Contract Review" to the legal department. The legal department staff member checks this task on their terminal, reviews the contract, and then enters the progress into the system. The server receives this information and updates the overall task list.

[0936] This system streamlines task identification, distribution, and progress management compared to traditional manual methods. Each team member can check the progress of their tasks in real time and make necessary adjustments quickly. This significantly improves overall work efficiency.

[0937] In general, the system of the present invention provides a powerful tool for effectively and efficiently managing tasks when various departments collaborate to handle a project.

[0938] The following describes the processing flow.

[0939] Step 1:

[0940] The terminals are used by staff members in each department to upload sales manuals and project summaries to the server. The uploaded documents are in PDF or text file format.

[0941] Step 2:

[0942] The server receives the uploaded material and sends it to a natural language processing engine. This engine analyzes the material and extracts key keywords and phrases.

[0943] Step 3:

[0944] The server generates specific tasks using a task generation mechanism based on the analysis results. The generated tasks include information on the necessary resources and the departments involved.

[0945] Step 4:

[0946] The server saves the generated task list to a database. The saved task list is then used in subsequent processing.

[0947] Step 5:

[0948] The server collects and analyzes information such as each user's skill set, current workload, and job title. Based on this information, it appropriately distributes tasks using a task distribution mechanism.

[0949] Step 6:

[0950] The server notifies each assigned person's terminal of the assigned task. The notification includes detailed information about the task.

[0951] Step 7:

[0952] The terminal displays the tasks received by each person in charge. The person in charge checks their tasks and proceeds to execute them.

[0953] Step 8:

[0954] Users (assigned personnel) input task progress into the system via their terminals. This information is updated in real time.

[0955] Step 9:

[0956] The server receives progress data and analyzes ongoing tasks using progress management tools. It generates alerts if delays or problems occur.

[0957] Step 10:

[0958] The server visualizes progress data and displays it in real time to each person in charge and administrator through a dashboard. The display includes overall progress and the status of individual tasks.

[0959] In this way, the system of the present invention efficiently identifies, distributes, and manages the progress of tasks when each department collaborates to handle a project. This leads to increased efficiency in operations.

[0960] (Example 1)

[0961] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0962] Traditional manual task management methods presented problems when multiple departments collaborated on a project, such as the inefficient identification, distribution, and progress management of tasks. Furthermore, it was difficult to appropriately distribute tasks considering each person's workload and skill set, often resulting in decreased overall work efficiency. To address this, a more effective and efficient task management system is needed.

[0963] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0964] In this invention, the server includes means for receiving and analyzing data, task generation means for extracting keywords from the analyzed data and generating tasks, task distribution means for distributing tasks to assigned personnel using the generated task list, means for receiving the progress of tasks performed by each assigned personnel, progress management means, and display means. This enables efficient task identification, distribution, and progress management, and allows for appropriate task distribution that takes into account the workload and skill sets of each assigned personnel.

[0965] The "means for receiving and analyzing documents" refer to the methods for receiving documents such as sales manuals and project summaries sent from terminals in each department onto a server, and then analyzing these documents using a natural language processing engine.

[0966] A "task generation method" is a means of extracting important keywords and phrases from analyzed data and generating specific tasks based on them.

[0967] A "task distribution method" is a means of appropriately distributing tasks to assigned personnel based on a generated task list, taking into account the assigned personnel's skill set, current workload, and job title data.

[0968] "Means for receiving progress reports" refers to the means by which each person in charge reports the progress of their tasks from their terminal to the server in real time.

[0969] A "progress management method" is a means of analyzing received progress data to detect the progress and delays of tasks at an early stage.

[0970] A "display method" refers to a means of visualizing data analyzed by progress management methods in real time, allowing each person in charge and manager to check the overall progress status through a dashboard or similar means.

[0971] This invention is a system for efficiently identifying and distributing tasks when various departments collaborate to handle a project. This system consists of three main elements: a server, terminals, and users.

[0972] First, the server receives sales manuals and project summaries sent from each department's terminal. These documents are analyzed using a natural language processing engine such as the Google Cloud Natural Language API, and important keywords and phrases are extracted. For example, if the sales manual contains the phrase "client visit," the server will use this information to generate a task for "client visit."

[0973] Next, the server manages the generated tasks. Task generation is achieved using custom Python scripts or the Task Management API to create a detailed task list based on the aforementioned analysis results. The server then appropriately distributes tasks to each assignee based on this list. When distributing tasks, factors such as the assignee's skill set, current workload, and job title are considered. This data is managed, for example, in an SQL database.

[0974] On the terminal side, each department's assigned personnel check and execute their tasks. Each person obtains detailed task information through their terminal and proceeds with execution. For example, if a sales department employee is assigned the task of "creating a proposal," they will use a task management app on their terminal (e.g., Trello or JIRA) to obtain detailed task information and create the proposal. The progress during this process is reported to the server in real time.

[0975] The server receives progress data reported by each team member in real time and analyzes it using progress management tools (e.g., a Grafana dashboard). Based on this analysis, delays and problems in ongoing tasks are detected early. Progress data is displayed in real time, allowing each team member and manager to check the overall progress through the dashboard.

[0976] For example, the server assigns the task "Contract Review" to the legal department. The legal department staff member checks this task on their terminal, reviews the contract, and then enters the progress into the system. The server receives this information and updates the overall task list.

[0977] This system streamlines task identification, distribution, and progress management compared to traditional manual methods. Each team member can check the progress of their tasks in real time and make necessary adjustments quickly. This significantly improves overall work efficiency.

[0978] Specific examples and prompt statements

[0979] Specific example 1:

[0980] The server receives documents from the sales department and analyzes them using a natural language processing engine to extract the important phrase "client visit." Based on this, the server generates a "client visit" task and assigns it to a sales representative. The representative checks the task details on their terminal and conducts the client visit. The progress is reported to the server in real time.

[0981] Example of a prompt:

[0982] "Please provide a detailed explanation of the server's processing procedures for analyzing sales department documents, generating tasks, and distributing them."

[0983] Specific example 2:

[0984] The server assigns the legal department a task called "contract review." The legal department staff member checks the task on their terminal, reviews the contract, and then enters the progress into the system. The server receives this information and updates the overall task list.

[0985] Example of a prompt:

[0986] "Please explain in detail the entire process from assigning tasks to the legal department to updating their progress."

[0987] These explanations will allow for a concrete understanding of each processing step, enabling the effective operation of the system.

[0988] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0989] Step 1:

[0990] Receipt of materials

[0991] The server receives sales manuals and project overview documents sent from terminals in each department.

[0992] Specific actions include each terminal uploading files to the server. For example, the sales department might send an Excel file containing details of a new project to the server.

[0993] Input: Sales manuals and project overview documents

[0994] Output: Received files

[0995] Step 2:

[0996] Analysis of the materials

[0997] The server analyzes the received data using the Google Cloud Natural Language API.

[0998] The analysis process extracts important keywords and phrases from the text. For example, the phrase "client visit" might be detected.

[0999] Input: Received file

[1000] Data processing: Text analysis and keyword extraction of documents using a natural language processing engine.

[1001] Output: Extracted keywords and phrases

[1002] Step 3:

[1003] Task generation

[1004] The server generates specific tasks based on the extracted keywords and phrases.

[1005] Tasks such as "client visit" are created in detail using custom Python scripts, etc.

[1006] Input: Extracted keywords or phrases

[1007] Data Calculation: Applying Keyword-Based Task Generation Logic

[1008] Output: Generated tasks

[1009] Step 4:

[1010] Task distribution

[1011] The server then appropriately distributes tasks to each person in charge based on the generated task list.

[1012] Tasks are distributed considering the assigned person's skill set, current workload, and job title data. For example, tasks are assigned to the appropriate person by referring to the person data stored in the SQL database.

[1013] Input: Generated tasks, assignee's skill set, current workload, job title data

[1014] Data calculation: Selecting personnel using database queries

[1015] Output: Assigned tasks

[1016] Step 5:

[1017] Task confirmation and execution

[1018] On the terminal side, the person in charge of each department checks the assigned task and retrieves detailed information.

[1019] The person in charge performs the task through their terminal. For example, a sales representative checks the task "Create a proposal" and then actually creates the proposal.

[1020] Input: Notification of assigned task

[1021] Data processing: Displaying task details

[1022] Output: Task execution status

[1023] Step 6:

[1024] Progress report

[1025] The person in charge reports the progress of the task to the server in real time via their terminal as the task progresses.

[1026] For example, after a "client visit," enter the status as "completed" in the terminal.

[1027] Input: Task progress information

[1028] Data processing: Update progress status

[1029] Output: Updated progress data

[1030] Step 7:

[1031] Progress management and display

[1032] The server receives the reported progress data in real time and analyzes and displays it using a Grafana dashboard.

[1033] This allows for early detection of delays and problems, and provides visibility into overall progress. Administrators can view detailed progress through the dashboard.

[1034] Input: Updated progress data

[1035] Data processing: Analysis of progress data and display on dashboards.

[1036] Output: Real-time progress dashboard

[1037] This system enables efficient task identification, generation, distribution, and progress management, thereby improving overall business efficiency.

[1038] (Application Example 1)

[1039] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1040] Traditional factory task management was often done manually, which was not only inefficient but also made it difficult to track work progress in real time. Furthermore, assigning appropriate tasks to each machine quickly was challenging, leading to a decline in overall production efficiency. In particular, when various work instructions existed, extracting and distributing appropriate tasks became complex, and assigning tasks while considering the skill sets and job titles of the personnel involved was an extra step.

[1041] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1042] In this invention, the server includes an analysis means, a task generation means, a task distribution means, a progress management means for receiving and analyzing task progress from each person in charge, a display means for displaying the data collected by the progress management means in real time, a task extraction means installed in a machine in the factory and equipped with a natural language processing engine for extracting work tasks from work instructions, and a task monitoring means for distributing the extracted tasks to the machine and monitoring their progress in real time. This enables efficient task extraction, appropriate task distribution, and real-time progress monitoring of work.

[1043] 1. "Analysis tools" are system components that analyze documents and data and extract important information.

[1044] 2. A "task generation means" is a system component that generates work tasks based on collected data.

[1045] 3. A "task distribution means" is a system component that appropriately assigns generated work tasks to each person or machine.

[1046] 4. A "progress management system" is a system component that receives and analyzes the work progress status from each person in charge or machine.

[1047] 5. "Display means" refers to a system component for displaying data collected by the progress management means in real time.

[1048] 6. A "task extraction means" is a system component equipped with a natural language processing engine that extracts work tasks from work instructions.

[1049] 7. A "task monitoring means" is a system component that distributes extracted tasks to each machine and monitors their progress in real time.

[1050] Modes for carrying out the invention

[1051] This invention provides a system that utilizes applications installed on machinery within a factory to achieve efficient extraction, distribution, and progress monitoring of work tasks. This system consists of three main components: a server, terminals, and users.

[1052] server

[1053] The server receives work orders sent from each department and analyzes them using a natural language processing engine. Important tasks are extracted from the analyzed data, and a detailed task list is generated based on these. The generated tasks are then appropriately distributed to each machine and person in the factory. Task distribution takes into account machine capabilities, current load levels, and the skill sets and job titles of the personnel. Progress data is received from each person and machine using a progress management system and analyzed in real time.

[1054] terminal

[1055] Terminals are assigned to machines and personnel within each factory. Personnel and machines check and execute their assigned tasks through these terminals. For example, specific tasks such as "assemble product A" or "quality inspection of product B" are assigned. Progress is reported from the terminals to the server in real time, and the server updates the task list based on this information.

[1056] User

[1057] Users (factory managers and workers) can check the overall progress in real time through the dashboard. Because progress data is displayed, delays and problems with tasks can be addressed quickly. This system significantly improves efficiency compared to traditional manual task management and allows for effective monitoring of overall work progress.

[1058] Hardware and software used

[1059] Hardware: Machinery, servers, and terminals within the factory.

[1060] software:

[1061] Spacy (natural language processing engine)

[1062] allocation_module (task allocation logic module)

[1063] task_monitor (task progress monitoring module)

[1064] Specific examples

[1065] For example, in an electronics assembly plant, if there are work instructions for "assemble product A" and "quality inspection of product B," the assembly robot will be assigned the "assembly" task, and the inspection robot will be assigned the "quality inspection" task. The progress of these tasks is reported to the server in real time and can be viewed on a dashboard.

[1066] Example of a prompt

[1067] "To efficiently carry out the assembly of product A and the quality inspection of product B within the factory, we want to assign appropriate tasks to machines and personnel. First, please create a system that extracts tasks from work instructions, then assigns those tasks to machines and personnel, and monitors progress in real time."

[1068] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1069] Processing flow of the system program that implements the application example

[1070] Step 1:

[1071] The server receives work orders sent from each department. The input is work orders sent to the server in electronic format. The server saves the received work orders. The output is the saved work order file.

[1072] Step 2:

[1073] The server analyzes saved work orders using a natural language processing engine (spacy). The input is the saved work orders. The server extracts important keywords and phrases from the work orders. Specifically, it extracts noun phrases from the document and selects those related to "work." The output is a list of the extracted keywords and phrases.

[1074] Step 3:

[1075] The server generates a task list based on extracted keywords and phrases. The input consists of keywords and phrases extracted by a natural language processing engine. The server uses this information to create specific work tasks. Specifically, it generates task objects based on the keywords. The output is the generated task list.

[1076] Step 4:

[1077] The server distributes the generated task list to the corresponding machine and person in charge at each terminal. Inputs include the generated task list and information about each machine and person in charge (skill set, current workload, job title data). The server uses this information to appropriately assign tasks. Specifically, it matches appropriate tasks with their targets based on specified conditions. The output is the task list assigned to each machine and person in charge.

[1078] Step 5:

[1079] The terminal displays tasks received from the server, and the person in charge or the machine begins working on those tasks. The input is a list of assigned tasks sent to the terminal. Specifically, the terminal receives and displays the task list. The output is the person in charge or the machine confirming the task details.

[1080] Step 6:

[1081] The server receives progress reports from terminals and updates the progress status in real time. The input is progress data sent from the terminals. The server receives this data and updates the progress status. Specifically, it records the progress data in a database and updates the overall progress list. The output is the updated progress list.

[1082] Step 7:

[1083] The server displays progress data on a dashboard in real time. The input is an updated progress list. Specifically, it graphically displays the progress list on the dashboard. The output is a dashboard where each person in charge and administrator can check the status in real time.

[1084] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1085] The system of this invention is configured to ensure efficient task identification and distribution when various departments collaborate to handle a project. The system consists of three main elements: a server, a terminal, and a user, and further incorporates an emotion engine that recognizes the user's emotions.

[1086] First, the server receives sales manuals and project summaries sent from each department's terminal and analyzes them using a natural language processing engine. The keywords and phrases extracted through the analysis are then converted into specific tasks by a task generation mechanism. If the sales manual contains a phrase such as "client visit," the server will generate a task for "client visit."

[1087] Next, the server saves the generated task list to a database and appropriately distributes tasks using a task distribution mechanism based on each person's skill set, current workload, and job title data. The distributed tasks are notified to the person's terminal. On the terminal, each person checks the assigned task and proceeds to execute it.

[1088] During a task, the user inputs the task's progress into the system via a terminal. This progress data is received by the server and analyzed using progress management tools. If delays or problems occur, the server detects them and generates an alert. Furthermore, because an emotion engine is incorporated, it analyzes the user's facial expressions and statements to collect emotional data.

[1089] The server also uses emotional data recognized by the emotion engine as an element of progress management. For example, if an employee experiencing fatigue or stress is causing delays in a task, the task is redistributed taking this emotional data into consideration. This promotes the efficient progress of tasks.

[1090] Progress and sentiment data are visualized in real time and displayed to each team member and manager via a dashboard. This allows for an at-a-glance overview of overall progress, the status of each task, and the emotional state of the team members.

[1091] For example, the server assigns the task "contract review" to the legal department. When a legal department employee reviews and completes this task on their terminal, if the emotion engine detects the employee's stress level, the server analyzes this and, if necessary, reassigns the task to another employee. This process reduces the employee's workload and ensures the smooth progress of the task.

[1092] Thus, the system of the present invention enables more efficient and flexible work execution by considering not only the task identification, distribution, and progress management when each department collaborates to handle a project, but also the emotional state of the person in charge. As a result, the overall efficiency of operations is greatly improved.

[1093] The following describes the processing flow.

[1094] Step 1:

[1095] The terminals are used by staff members in each department to upload sales manuals and project summaries to the server. The uploaded documents are in PDF or text file format.

[1096] Step 2:

[1097] The server receives the uploaded material and sends it to a natural language processing engine. This engine analyzes the material and extracts key keywords and phrases.

[1098] Step 3:

[1099] The server generates specific tasks using a task generation mechanism based on the analysis results. For example, it adds tasks such as "visit client" and "draft contract" to the list.

[1100] Step 4:

[1101] The server saves the generated task list to the database. The task list also includes a detailed description of each task and the resources required.

[1102] Step 5:

[1103] The server collects data on each user's skill set, current workload, and job title, and uses this information to appropriately distribute tasks using a task distribution mechanism. For example, difficult tasks are assigned to experienced users, while relatively easy tasks are assigned to newer users.

[1104] Step 6:

[1105] The server notifies each assignee's terminal of the assigned task. The notification includes detailed task information, deadline, and related resource information.

[1106] Step 7:

[1107] The terminal displays the tasks received by each person in charge, and the person in charge checks their own tasks. The person in charge checks the details of the task and proceeds to execute it.

[1108] Step 8:

[1109] The user (assigned person) inputs task progress and emotional state into the system via a terminal. The emotional state is analyzed by an emotion engine.

[1110] Step 9:

[1111] The server receives progress data and sentiment data and analyzes it using progress management tools. For example, it generates alerts for tasks that are behind schedule.

[1112] Step 10:

[1113] The server readjusts task distribution based on emotional data. For example, it redistributes tasks from employees who are detected as stressed or fatigued to other employees.

[1114] Step 11:

[1115] The server visualizes progress and sentiment data in real time and displays it to each team member and manager through a dashboard. The displayed information includes overall progress, individual task status, and the team member's sentiment status.

[1116] Thus, the system of the present invention efficiently identifies, distributes, manages progress, and manages the emotional state of employees when each department collaborates to handle a project. This leads to increased work efficiency and appropriate management of the workload and stress levels of employees.

[1117] (Example 2)

[1118] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1119] Traditional task management systems fail to consider the emotional state of the person in charge, in addition to managing the progress of tasks. This can lead to inadequate management of the workload and a decrease in work efficiency. Furthermore, there is a problem in that appropriate measures cannot be taken when tasks are delayed due to the stress or fatigue of the person in charge.

[1120] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1121] In this invention, the server includes analysis means, task generation means, task distribution means, progress management means, emotion recognition means, task redistribution means, and display means. This enables task management and redistribution based on the emotional state of the person in charge.

[1122] "Analysis methods" refer to the means of receiving and analyzing sales manuals and project outlines sent from each department.

[1123] A "task generation method" is a means of generating specific tasks using data collected by an analysis method.

[1124] A "task distribution method" is a means of distributing generated tasks to each person in charge.

[1125] A "progress management method" is a means of receiving and analyzing the task progress status from each person in charge.

[1126] "Emotion recognition means" refers to a method for analyzing the emotional state of the person in charge and collecting that data.

[1127] A "task redistribution method" is a means of redistributing tasks based on data collected by an emotion recognition method.

[1128] "Display means" refers to means for displaying data collected by progress management means and emotion recognition means in real time.

[1129] The system of this invention is designed to enable efficient collaboration among departments, task identification, distribution, and progress management. This system primarily consists of servers, terminals, and users, and further incorporates an emotion engine to recognize user emotions. The following describes each element of the system and the program's processing.

[1130] server

[1131] The server receives sales manuals and project summaries sent from each department and analyzes them using a natural language processing engine (e.g., AWS Comprehend or Google Cloud Natural Language). The analyzed data is then converted into specific tasks by a task generation system. For example, if the phrase "client visit" is included, the server generates it as a task for "client visit".

[1132] The generated tasks are stored in a database and distributed using a task distribution system based on each assignee's skill set, current workload, and job title data. Assigned tasks are then notified to the assignee's terminal. While a task is in progress, the server receives progress data and analyzes it using a progress management system. If delays or problems occur, an alert is generated.

[1133] Furthermore, the system uses an emotion engine to analyze the user's emotional state (e.g., fatigue and stress) and collects data using emotion recognition tools. Based on this data, tasks are redistributed to reduce the workload on team members and promote efficient task progress. Progress and emotion data are visualized in real time and displayed through a dashboard.

[1134] terminal

[1135] The terminals used by staff in each department receive task notifications sent from the server and display the task list. Staff members use their terminals to check their assigned tasks and enter their completion status. The terminals can send task progress data and staff member sentiment data to the server.

[1136] User

[1137] Users operate the system and send sales manuals and project summaries to the server via their terminals. The assigned personnel check their tasks and update their progress as needed. Furthermore, an emotion engine analyzes the user's emotional state and redistributes tasks as necessary.

[1138] Example of a prompt

[1139] "Send the sales manual and project summary to the server for analysis and generate a new task."

[1140] "Redistribute tasks based on the progress and emotional data of the assigned personnel, and help resolve delays and problems."

[1141] The above is a specific example of the system's operation. The system of the present invention is configured to enable efficient collaboration among departments and significantly improve the efficiency of operations.

[1142] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1143] Program processing flow

[1144] Step 1: Sending Data

[1145] Users use terminals in their respective departments to send sales manuals and project summaries to the server. Input is in PDF or document format, and output is the server saving the received files. Specifically, the sales department uploads the latest customer list and visit plan to the server in PDF format.

[1146] Step 2: Analysis of the month

[1147] The server analyzes the received data using a natural language processing engine (e.g., AWS Comprehend or Google Cloud Natural Language). The input is the stored data, and the output is the extracted keywords and phrases from the analysis. For example, it can extract phrases such as "customer visit" and "presentation material creation" from a customer list document.

[1148] Step 3: Task Generation

[1149] The server generates specific tasks using a task generation mechanism based on the analysis results. The input is the analyzed keywords and phrases, and the output is the generated tasks. Specifically, from the keyword "customer visit," tasks such as "schedule customer visit" are automatically generated.

[1150] Step 4: Task Distribution

[1151] The server saves the generated task list to a database and distributes it to each person in charge using a task distribution mechanism. The input is the generated tasks, the skill sets of the people in charge, and their job titles, and the output is the distributed tasks. The legal department is assigned the task of "contract review," and the sales department is assigned the task of "customer visit."

[1152] Step 5: Task Notification

[1153] The server notifies the assigned task on the employee's terminal. The input is the assigned task, and the output is the notification message sent to the employee's terminal. Specifically, a notification titled "New Task: Confirm Customer Visit Schedule" will appear on the terminal of the sales department employee.

[1154] Step 6: Execute the task and enter the progress.

[1155] Users check their assigned tasks on their devices and proceed with execution. Input is the task's progress, and output is the transmission of progress data to the server. For example, if an employee enters "Customer visit completed" on their device, the progress status is updated.

[1156] Step 7: Progress Management

[1157] The server receives progress data and analyzes it using progress management tools. The input is progress data, and the output is the analysis results of the progress status and any necessary alerts. If a delay is detected, the server sends a "Task Delayed" alert to the person in charge.

[1158] Step 8: Collecting and analyzing emotional data

[1159] The emotion engine analyzes the user's facial expressions and speech to collect emotional data. The input is the user's emotional state (e.g., facial expressions and voice), and the output is the analyzed emotional data. If an employee experiences stress during their work, this state is recorded in the system.

[1160] Step 9: Redistributing tasks

[1161] The server redistributes tasks as needed based on emotional data. Inputs are emotional data and progress data, and output is the redistributed tasks. If a high-stress employee is behind schedule, the task is reassigned to another employee.

[1162] Step 10: Real-time visualization

[1163] The server visualizes progress and sentiment data in real time and displays it through a dashboard. The input is the collected progress and sentiment data, and the output is the display of the visualized dashboard. Each person in charge and manager can check the "progress bar" and "stakeholder's sentiment status" in real time.

[1164] The above describes the specific actions taken at each processing step of the system.

[1165] (Application Example 2)

[1166] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1167] Current task management systems often distribute tasks based solely on the skill set and workload of the assigned person, without considering their psychological burden or emotional state. As a result, this can lead to decreased motivation and reduced work efficiency. Furthermore, real-time monitoring of progress is limited, making flexible task redistribution difficult. This invention aims to solve these problems, streamline task management within factories, and achieve flexible management that takes into account the health and well-being of the assigned person.

[1168] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1169] In this invention, the server includes an analysis means, a task generation means that generates tasks using data collected by the analysis means, a task distribution means that distributes the tasks generated by the task generation means to each person in charge, a progress management means that receives and analyzes the progress of the tasks distributed by the task distribution means, an emotion engine means that recognizes the emotional state of the user, and a display means that displays the data collected by the progress management means and the data collected by the emotion engine means in real time. This makes it possible to distribute and manage tasks while taking into account not only the skill set and workload of the person in charge, but also their psychological state.

[1170] "Analysis methods" refer to the functions and processes for collecting and analyzing various types of data.

[1171] A "task generation method" is a function that creates specific tasks based on collected and analyzed data.

[1172] A "task distribution mechanism" is a function that assigns generated tasks to the appropriate person or robot.

[1173] A "progress management system" is a function that receives and analyzes the progress status of assigned tasks.

[1174] The "emotional engine" refers to a function that recognizes the emotional state of personnel or robots and collects it as data.

[1175] "Display means" refers to a function for visually displaying progress data and sentiment data.

[1176] A "natural language processing engine" is a technology used to analyze documents and extract meaning and keywords.

[1177] A "skill set" is a collection of skills and expertise possessed by an individual or robot.

[1178] "Current workload" refers to the amount of work and tasks that the person in charge or robot is currently handling.

[1179] "Rank data" refers to information about the rank and position of the person in charge or the robot.

[1180] The system of this invention streamlines task management within a factory and enables flexible management that takes into account the health status of the person in charge. The system consists of three main elements: a server, a terminal, and a user, and further incorporates an emotion engine that recognizes the user's emotions.

[1181] First, the server receives documents and instructions from within the factory and analyzes them using a natural language processing engine (e.g., Google Cloud Natural Language API). This analysis allows the task generation system to generate specific tasks. For example, if a phrase such as "quality inspection of product A" is included, the server will generate a task for "quality inspection of product A".

[1182] Next, the server saves the generated task list to a database and appropriately distributes tasks using a task distribution mechanism based on each robot and operator's skill set, current workload, and rank data. In this process, the server assigns tasks to the robot or operator with the most available capacity. The assigned tasks are then notified to the operator's terminal.

[1183] Humans and robots perform their assigned tasks and report their progress to the server. The server analyzes the progress using progress management tools and generates alerts if delays or problems occur. Furthermore, because an emotion engine is built in, emotional data of the humans and robots is also collected. This emotional data is collected, for example, using sensors and voice analysis microphones. This makes it possible to detect psychological burden and stress levels.

[1184] The server integrates and analyzes collected progress and sentiment data, and redistributes tasks as needed. For example, if an employee is under high stress, their tasks can be reassigned to other employees. This appropriately adjusts the workload of employees and promotes the smooth progress of work.

[1185] Progress and sentiment data are visualized in real time and displayed to each team member and manager through a dashboard. This allows for an at-a-glance overview of overall progress, the status of each task, and the sentiment of the team members and robots.

[1186] Specific examples include tasks such as "quality inspection" and "equipment maintenance" in a factory. This system uses a natural language processing engine to extract these tasks and assign them to appropriate robots or personnel. An emotion engine allows for task redistribution if a person's stress level is high.

[1187] Examples of prompt statements include:

[1188] "Generate quality inspection and equipment maintenance tasks within the factory and distribute them to the robots in the most optimal way. Also, consider the stress level and progress of each robot and display this information on a dashboard. Progress data is stored in a temporary database."

[1189] These are some examples.

[1190] This will streamline task management within the factory and enable flexible management that takes into account the health status of personnel and robots. Furthermore, it will improve operational efficiency while minimizing psychological stress.

[1191] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1192] Step 1:

[1193] The server receives documents and instructions from within the factory. The received data is parsed by a natural language processing engine (e.g., Google Cloud Natural Language API). The input is documents and instructions from within the factory, and the output is keywords and phrases that indicate extracted tasks. To execute this, the server analyzes the text data and identifies the necessary tasks.

[1194] Step 2:

[1195] The server generates specific tasks based on keywords and phrases extracted by the natural language processing engine. The task generation mechanism fulfills this role. The input is the keywords and phrases extracted in the previous step, and the output is a list of specific tasks. The server creates each task based on the text analysis results.

[1196] Step 3:

[1197] The server saves the generated task list to the database. The input is the task list, and the output is the task list stored in the database. The server performs database operations to record the task list.

[1198] Step 4:

[1199] The server distributes tasks generated using a task distribution mechanism to individual personnel and robots. The distribution criteria are the skill sets, current workload, and rank data of the personnel and robots. The input is a task list and information on each personnel and robot, and the output is a list of tasks distributed to the personnel and robots. The server analyzes the status of each personnel and robot to perform optimal distribution.

[1200] Step 5:

[1201] The terminal notifies the assigned personnel or robots of the assigned tasks and initiates their execution. The input is the assigned task list, and the output is the task information notified on the terminal. The terminal notifies the personnel or robots of the tasks and monitors their execution status.

[1202] Step 6:

[1203] Human resources or robots perform tasks and report their progress to the server via terminals. The input is progress data, and the output is the progress data sent to the server. Human resources or robots complete tasks and report their progress.

[1204] Step 7:

[1205] The server receives and analyzes progress data using a progress management system. The input is progress data, and the output is the analyzed progress data and alert information. The server evaluates the status of ongoing tasks and generates alerts as needed.

[1206] Step 8:

[1207] The emotion engine recognizes the emotional state of the person in charge or the robot and collects data. The input is emotional data (e.g., from sensors or voice analysis), and the output is emotional data sent to the server. The emotion engine analyzes the psychological state of the person in charge or the robot.

[1208] Step 9:

[1209] The server integrates progress and sentiment data and redistributes tasks as needed. Inputs are progress and sentiment data, and output is a redistributed task list. Based on this data, the server readjusts the load balancing.

[1210] Step 10:

[1211] Using a display mechanism, progress data and sentiment data are shown on a dashboard in real time. The input is integrated progress data and sentiment data, and the output is the information displayed on the dashboard. The server makes this information visually accessible to monitors and administrators.

[1212] Through these steps, the system can efficiently and flexibly manage tasks within the factory, while also appropriately managing the psychological burden on personnel and robots.

[1213] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1214] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1215] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1216] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1217] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1218] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1219] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1220] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1221] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1222] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1223] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1224] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1225] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1226] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1227] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1228] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1229] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1230] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1231] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1232] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1233] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1234] The following is further disclosed regarding the embodiments described above.

[1235] (Claim 1)

[1236] Analytical methods,

[1237] A task generation means that generates tasks using the data collected by the analysis means,

[1238] A task distribution means for distributing tasks generated by the task generation means to each person in charge,

[1239] A progress management means that receives and analyzes the task progress status from each of the aforementioned persons in charge,

[1240] A display means that displays the data collected by the progress management means in real time,

[1241] A system that includes this.

[1242] (Claim 2)

[1243] The system according to claim 1, characterized in that the analysis means analyzes a document using a natural language processing engine.

[1244] (Claim 3)

[1245] The system according to claim 1, wherein the task distribution means distributes tasks taking into account the skill set, current workload, and job title data of the person in charge.

[1246] "Example 1"

[1247] (Claim 1)

[1248] A means of receiving and analyzing data,

[1249] A task generation means that extracts keywords from the analyzed data and generates tasks,

[1250] A task distribution means that distributes tasks to assigned personnel using the task list generated by the task generation means,

[1251] A means of receiving the progress status of tasks performed by each person in charge,

[1252] A progress management means for analyzing the progress status,

[1253] A display means that displays the data analyzed by the progress management means in real time,

[1254] A system that includes this.

[1255] (Claim 2)

[1256] The system according to claim 1, characterized in that the analysis means analyzes the data using a natural language processing engine.

[1257] (Claim 3)

[1258] The system according to claim 1, wherein the task distribution means distributes tasks taking into account the skill set, current workload, and job title data of the person in charge.

[1259] "Application Example 1"

[1260] (Claim 1)

[1261] Analytical methods,

[1262] A task generation means that generates tasks using the data collected by the analysis means,

[1263] A task distribution means for distributing tasks generated by the task generation means to each person in charge,

[1264] A progress management means that receives and analyzes the task progress status from each of the aforementioned persons in charge,

[1265] A display means that displays the data collected by the progress management means in real time,

[1266] A task extraction means, which is installed on machinery within a factory and is equipped with a natural language processing engine that extracts work tasks from work instructions,

[1267] A task monitoring system that distributes extracted tasks to machines and monitors their progress in real time,

[1268] A system that includes this.

[1269] (Claim 2)

[1270] The system according to claim 1, characterized in that the analysis means analyzes a document using a natural language processing engine.

[1271] (Claim 3)

[1272] The system according to claim 1, wherein the task distribution means distributes tasks taking into account the skill set, current workload, and job title data of the person in charge.

[1273] "Example 2 of combining an emotion engine"

[1274] (Claim 1)

[1275] Analytical methods,

[1276] A task generation means that generates tasks using the data collected by the analysis means,

[1277] A task distribution means for distributing tasks generated by the task generation means to each person in charge,

[1278] A progress management means that receives and analyzes the task progress status from each of the aforementioned persons in charge,

[1279] An emotion recognition method that analyzes the emotional state of the person in charge and collects that data,

[1280] A task redistribution means that redistributes tasks based on the data collected by the emotion recognition means,

[1281] A display means that displays the data collected by the progress management means and emotion recognition means in real time,

[1282] A system that includes this.

[1283] (Claim 2)

[1284] The system according to claim 1, characterized in that the analysis means analyzes a document using a natural language processing engine.

[1285] (Claim 3)

[1286] The system according to claim 1, wherein the task distribution means distributes tasks taking into account the skill set, current workload, and job title data of the person in charge.

[1287] "Application example 2 when combining with an emotional engine"

[1288] (Claim 1)

[1289] Analytical methods,

[1290] A task generation means that generates tasks using the data collected by the analysis means,

[1291] A task distribution means for distributing tasks generated by the task generation means to each person in charge,

[1292] A progress management means that receives and analyzes the progress status of tasks distributed by the task distribution means,

[1293] An emotion engine means for recognizing the user's emotional state,

[1294] A display means that displays in real time the data collected by the progress management means and the data collected by the emotion engine means,

[1295] A system that includes this.

[1296] (Claim 2)

[1297] The system according to claim 1, characterized in that the analysis means analyzes a document using a natural language processing engine.

[1298] (Claim 3)

[1299] The system according to claim 1, wherein the task distribution means distributes tasks taking into account the skillset of the person in charge, the current workload, and rank data. [Explanation of Symbols]

[1300] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Analytical methods, A task generation means that generates tasks using the data collected by the analysis means, A task distribution means for distributing tasks generated by the task generation means to each person in charge, A progress management means that receives and analyzes the task progress status from each of the aforementioned persons in charge, A display means that displays the data collected by the progress management means in real time, A system that includes this.

2. The system according to claim 1, characterized in that the analysis means analyzes a document using a natural language processing engine.

3. The system according to claim 1, characterized in that the task distribution means distributes tasks taking into account the skill set, current workload, and job title data of the person in charge.

Images