system

Abstract

Provide a system. A means for providing a user interface for inputting a task; A means for analyzing the input task using natural language processing technology; Based on the analyzed tasks, a means for recommending appropriate personnel based on the user's skill set, workload, and past performance data; a means for automatically generating specific task instructions for the recommended personnel; A means of identifying and providing the resources needed to perform the task; A means to track task progress in real time and provide a dashboard to support communication between stakeholders; A system including:

Description

[Technical Field]

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

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

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

[0004] In modern workplaces, excessive task pressure and uneven distribution of work are often problems. This causes stress for many employees and reduces productivity, while delegating tasks to staff with the appropriate skills is insufficient. Furthermore, task progress is unclear, and lack of communication can cause friction in interpersonal relationships. Therefore, there is a need for a system that can solve these problems and enable users to work in a more efficient and healthy work environment. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following distinctive means. First, a means for providing a user interface for inputting tasks is provided. Next, a means for analyzing the inputted tasks using natural language processing technology is provided, and a means for recommending an appropriate person to perform the task based on the analysis results, taking into account the user's skill set, workload, and past performance data is provided. Furthermore, a means for automatically generating specific task instructions for the recommended person to perform the task is provided, and a means for identifying and providing the resources necessary to perform the task is provided. Finally, a means for tracking the progress of tasks in real time and providing a dashboard that supports communication between the parties involved is provided. This enables efficient and transparent work execution without the user feeling excessive pressure.

[0006] A "user interface" is the means by which a user inputs information into a system and receives responses from the system.

[0007] "Natural language processing technology" is a computer technology for analyzing, understanding, and generating text data based on natural language.

[0008] "Analyzing" refers to breaking down input information, understanding its content and structure, and applying appropriate processing.

[0009] A "skill set" refers to the collection of skills and knowledge possessed by a particular user.

[0010] "Workload" refers to the amount and weight of work that a user is currently working on.

[0011] "Performance data" refers to data relating to the results and evaluations of a user's past work performance.

[0012] "Associate" refers to a person who is responsible for carrying out a particular task.

[0013] "Recommend" refers to presenting the best options based on specific criteria.

[0014] "Task instructions" are instructions that show specific steps or actions to complete a specific task.

[0015] "Auto-generated" means that a machine or algorithm produces specific information or results without human intervention.

[0016] "Resources" refers to available resources such as tools, data, and information needed to complete a particular task.

[0017] "Identifying" means finding and indicating what you need from among many options.

[0018] "Progress" refers to the degree of progress toward completing a particular task or project.

[0019] "Real-time" refers to the acquisition, processing, and display of information almost simultaneously with events occurring in reality.

[0020] A "dashboard" is an interface that integrates multiple pieces of information and displays them on a single screen, allowing users to grasp the situation at a glance.

[0021] "Supporting communication" refers to helping users share information and communicate with each other smoothly and efficiently. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0023] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0024] First, the terms used in the following description will be explained.

[0025] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0026] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0027] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0028] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0029] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0033] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0034] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0035] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0036] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0037] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0040] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0041] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0042] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0043] The system according to the present invention aims to reduce the excessive pressure of tasks in the workplace and to support efficient and transparent business execution. Hereinafter, an embodiment of the present invention will be described in detail.

[0044] Overall system configuration

[0045] The system mainly consists of the following components:

[0046] 1. User Interface

[0047] 2. Natural Language Processing Engine

[0048] 3. User Profile Database

[0049] 4. Task Recommendation Engine

[0050] 5. Task Instruction Generation Engine

[0051] 6. Resource Management System

[0052] 7. Work progress management dashboard

[0053] System processing flow

[0054] Task Input

[0055] A user inputs a task into the system via a terminal. For example, a specific task such as "conduct market research for a new product" is input. The terminal accepts this input and sends it to the server.

[0056] Task Analysis

[0057] The server analyzes the received task using a natural language processing engine. This analysis extracts keywords and context (e.g., "new product" or "market research") from the task content. The server then queries a related database to retrieve similar tasks and reference materials.

[0058] Recommendation from a representative

[0059] The server refers to a user profile database and selects the most suitable person based on each user's skill set, workload, and past performance data. For example, users with extensive market research experience are given priority in the recommendation. This recommendation information is sent to the terminal.

[0060] Auto-generation of task instructions

[0061] The server automatically generates specific task instructions based on the task content and related goals, such as "First, research competitive products, then analyze market trends." These instructions are sent to the device for review by the user.

[0062] Provision of necessary resources

[0063] The server identifies the resources needed for the task (e.g., survey templates and online research tools) and provides links to them to the device, allowing users to quickly access the required resources.

[0064] Transparency in work progress and communication support

[0065] The device confirms the recommended agent and automatically generated instructions. After the agent accepts the task, their progress is tracked in real time by the server. Progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[0066] Specific examples

[0067] 1. Enter the task

[0068] The user types "I want to conduct market research on a new product" into the terminal.

[0069] The terminal sends this to the server.

[0070] 2. Task Analysis

[0071] The server analyzes the task content using natural language processing and extracts keywords such as "new product" and "market research."

[0072] The server queries the relational database to obtain similar task information and resources.

[0073] 3. Recommendation of the person in charge

[0074] The server refers to the user's skill data and recommends agent A.

[0075] The server generates the reason for recommendation and displays it on the terminal.

[0076] 4. Generate task instructions

[0077] The server generates specific task instructions (e.g., "research competing products") and sends them to the device.

[0078] 5. Providing necessary resources

[0079] The server collects links to resources necessary for market research and provides them to the terminal.

[0080] 6. Progression and communication support

[0081] The device displays the dashboard and person in charge A updates the progress.

[0082] All stakeholders can see progress in real time and provide comments and feedback as needed.

[0083] This system provides an environment in which users can carry out their work efficiently and make the most of opportunities for growth. This series of processes reduces stress for users through automation and transparency, and has the effect of improving work productivity.

[0084] The processing flow will be explained below.

[0085] Step 1:

[0086] The user inputs a task via a terminal, for example, "conduct market research for a new product."

[0087] Step 2:

[0088] The device accepts the input task and sends it to the server. The sent data includes the task content and the user's ID.

[0089] Step 3:

[0090] The server receives the task and begins analyzing it using a natural language processing engine. The server extracts keywords and context (e.g., "new product," "market research") from the task content.

[0091] Step 4:

[0092] The server queries a related database to collect similar tasks and related resources based on the extracted keywords.

[0093] Step 5:

[0094] The server checks the user profile database and analyzes each user's skill set, current workload, and past performance data.

[0095] Step 6:

[0096] The server selects the most suitable person based on the analysis data. For example, it may recommend person A, who has extensive experience in market research.

[0097] Step 7:

[0098] The server generates the reason for recommending agent A and sends this information to the terminal. The terminal displays a list of recommended agents and the reason.

[0099] Step 8:

[0100] The server automatically generates specific task instructions based on the task content, such as "First, research competitor products, then analyze market trends."

[0101] Step 9:

[0102] The server generates specific task instructions and sends them to the device, where they are displayed and viewed by the user.

[0103] Step 10:

[0104] The server identifies the resources needed to complete the task and generates links to access them, such as survey templates and online research tools.

[0105] Step 11:

[0106] The server sends these resource links to the terminal, which displays the access links and their descriptions.

[0107] Step 12:

[0108] The device confirms the recommended agent and the automatically generated instructions. When Agent A accepts the task, a confirmation is sent from the device to the server.

[0109] Step 13:

[0110] The server tracks the progress of tasks in real time and collects progress data, which is then reflected in the work progress management dashboard.

[0111] Step 14:

[0112] The device displays a progress management dashboard, allowing all stakeholders to view progress, provide comments, and provide feedback.

[0113] Step 15:

[0114] Users communicate in real time through the dashboard to provide any necessary coordination or assistance.

[0115] Example 1

[0116] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0117] In conventional task management systems, task assignment and progress tracking are performed manually, resulting in low work efficiency and a lack of transparency. It is also difficult to select the right person for the task, often resulting in delays in providing appropriate resources. Furthermore, there is a lack of communication between stakeholders, which reduces work productivity. The purpose of this invention is to solve these problems and improve work efficiency and transparency.

[0118] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0119] In this invention, the server includes a means for analyzing tasks using natural language processing technology, a means for recommending an appropriate person to perform the task based on the user's ability set, workload, and past performance data, and a means for automatically generating specific task instructions. This enables efficient analysis of tasks, appropriate recommendation of a person to perform the task, and automatic generation of specific instructions. Furthermore, by including a terminal that tracks the progress of tasks in real time and supports information exchange between related parties, and a means for identifying and providing resources required to perform the tasks, the transparency and efficiency of work are improved.

[0120] A "terminal" is an electronic device used by a user to input tasks and check instructions and progress. This includes computers and smartphones.

[0121] A "server" is a central processing unit that executes multiple means, and is a device that is responsible for analyzing tasks, recommending personnel, automatically generating task instructions, providing resources, and tracking progress.

[0122] "Natural language processing technology" is a technology for analyzing the content of a task and extracting keywords and context, and includes machine learning models and text analysis algorithms.

[0123] The "user ability set" is data relating to the job capabilities and skills of each user, and is information used for task allocation and recommendation of personnel.

[0124] "Workload" is data about the amount of tasks each user currently has and ongoing projects.

[0125] "Past achievement data" is a history of tasks and projects that the user has completed in the past, and is data related to their evaluations and achievements.

[0126] "Task instructions" are instructions that indicate the specific steps or procedures that must be performed to accomplish a particular task.

[0127] "Resources" are information or items such as materials, tools, templates, links, etc. required to perform a task.

[0128] A "dashboard" is a visual interface that displays the progress of tasks in real time and supports information exchange among stakeholders.

[0129] The present invention is a system that aims to improve the efficiency and transparency of task management in a workplace environment. This system mainly consists of the following components: a terminal, a server, a natural language processing engine, a user profile database, a task recommendation engine, a task instruction generation engine, a resource management system, and a work progress management dashboard.

[0130] System Configuration

[0131] Terminal

[0132] Users use a device (such as a PC or smartphone) to input tasks and check their progress. The device provides a user interface and sends the input tasks to the server. The device also displays the information sent from the server to the user.

[0133] server

[0134] The server serves as the central hub of the entire system and fulfills multiple roles. The specific processing performed by the server is shown below.

[0135] Natural Language Processing Engine

[0136] When a task is input, the server first analyzes the content of the task using a natural language processing engine (for example, TENSORFLOW (registered trademark) or OpenNLP). This analysis extracts key keywords and context from the task. For example, if the task "conduct market research for a new product" is input, the keywords "new product" and "market research" are extracted.

[0137] User profile database and task recommendation engine

[0138] Based on the analyzed task content, the server references a user profile database, which stores each user's ability set, workload, and past performance data. Based on this information, the server recommends the person best suited to the task. For example, a user with extensive market research experience and a light current workload may be recommended. The recommendation results are displayed on the terminal.

[0139] Task Instruction Generation Engine

[0140] The server automatically generates specific task instructions based on the acquired task content and the recommended person in charge. For example, it may generate specific steps such as "research competing products, then analyze market trends." This automatically generated instruction is sent to the terminal and can be confirmed by the user.

[0141] Resource Management System

[0142] The server identifies the resources (e.g., survey templates and online research tools) needed to complete the task and provides links to them to the device, allowing the user to quickly access the required resources. For example, specific resources such as "Market Research Template.xlsx" or "Access Link to Competitive Analysis Tool" can be included.

[0143] Business progress management dashboard

[0144] Users use a work progress management dashboard to check progress and communicate. The server tracks the progress of tasks in real time and displays it on the dashboard. After a task is accepted by a person in charge, the progress and related communications can be viewed by all parties on the dashboard. This ensures transparency of work and enables efficient information exchange.

[0145] Examples and prompts

[0146] Specific examples

[0147] Task Input

[0148] The user types "I want to conduct market research on a new product" into the terminal.

[0149] The terminal sends this to the server.

[0150] Task Analysis

[0151] The server uses a natural language processing engine to extract key keywords such as "new product" and "market research."

[0152] The server queries the relational database to obtain similar task information and resources.

[0153] Recommendation from a representative

[0154] The server refers to the user's skill data and recommends "users with extensive market research experience."

[0155] This information, along with the reason for the recommendation, is sent to the device.

[0156] Generate task instructions

[0157] The server generates specific task instructions (e.g., "research competing products") and sends them to the device.

[0158] Provision of necessary resources

[0159] The server identifies a resource such as "Market Research Template.xlsx" and provides it to the device.

[0160] Progression and communication support

[0161] The device displays progress on a dashboard, and the person in charge updates the progress as it happens.

[0162] All stakeholders can view and comment on progress and feedback in real time through a dashboard.

[0163] Prompt Sentence Examples

[0164] "I'd like to conduct market research for a new product. Please set the task to include researching competitive products and analyzing market trends."

[0165] "What are the specific steps I should take to start researching competitive products and then analyzing market trends?"

[0166] The system of the present invention provides an environment in which users can perform their work efficiently and maximize opportunities for growth. The aim is to reduce user stress through automation and transparency and improve work productivity.

[0167] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0168] Step 1:

[0169] The user inputs a task using a terminal. Specifically, the user inputs the task content (e.g., "Conduct market research for a new product") in text format through the terminal's user interface. The terminal then sends this input content to the server. The input data is the task content in natural language format and is passed to the server.

[0170] Step 2:

[0171] The server receives the task content and analyzes it using a natural language processing engine (e.g., TensorFlow or OpenNLP). Specifically, it extracts key keywords (e.g., "new product," "market research") and contextual information from the task text. The input data is the task content in text format, and the output data is the extracted keywords and contextual information.

[0172] Step 3:

[0173] The server queries the user profile database based on the extracted keywords and context information to obtain information such as past performance data, workload, and skill sets. The server analyzes this data and recommends the most suitable agent for the task. The input data are the extracted keywords and user profile information, and the output data are the recommended agent and the reason for the recommendation.

[0174] Step 4:

[0175] The server automatically generates specific task instructions for the recommended personnel. Specific steps (e.g., "Start researching competitive products, then analyze market trends") are automatically created based on predefined templates and past task instructions. The input data is the task content and information on the recommended personnel, and the output data is specific task instructions.

[0176] Step 5:

[0177] The server identifies the resources required to execute the task and provides the terminal with links and materials. Specifically, it collects research tools and templates (e.g., "Market Research Template.xlsx") and generates access links to them. The input data is the task content and resource information, and the output data is the links and materials for the required resources.

[0178] Step 6:

[0179] The user confirms the recommended agent and specific task instructions via the terminal. The agent accepts the task, and the server tracks its progress in real time. The progress is displayed on the terminal's work progress management dashboard, allowing all parties involved to check the progress and provide comments and feedback as needed. The input data is the ongoing task information, and the output data is the progress and feedback updated in real time.

[0180] Through these series of processing steps, the system can achieve efficient management and transparency of tasks, reducing the burden on users.

[0181] (Application example 1)

[0182] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0183] In modern factory operations, task allocation and progress management have become increasingly complex, making it difficult to carry out work efficiently. While there is also a need to maximize the capabilities of robots and deploy them in the right positions, current systems are unable to fully achieve this. This leads to uneven workloads within the factory, reducing the productivity of the manufacturing process.

[0184] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0185] In this invention, the server includes means for providing an operation screen for inputting tasks, means for analyzing the input tasks using natural language processing technology, means for recommending appropriate workers based on the analyzed tasks and on the user's capabilities, workload, and past execution data, means for automatically generating specific task instructions for the recommended workers, means for identifying and providing resources necessary for executing the tasks, means for tracking the progress of tasks in real time and providing a management screen that supports communication between related parties, means for considering the capabilities of robots operating in the factory when selecting and recommending workers, and means for automatically generating specific work instructions for the recommended robots. This enables efficient task allocation and progress management, thereby achieving equalization of workloads within the factory and improved productivity.

[0186] An "operation screen" is a display screen that provides an interface for a user to input a task.

[0187] "Natural language processing technology" is a technology for analyzing and understanding documents written in human language.

[0188] A "task" is an activity or task performed to achieve a specific goal.

[0189] "User" refers to the person or administrator who operates the system and inputs tasks.

[0190] "Ability" refers to the technical skills and knowledge possessed by a user or robot.

[0191] "Workload" refers to the amount of work a worker currently has and the state of their work.

[0192] "Execution data" is data that records the performance and results of tasks performed in the past.

[0193] "Worker" refers to a human or robot that performs the tasks recommended by the system.

[0194] "Task instructions" refer to instructions that show the specific steps and methods for executing a task.

[0195] "Resources" refer to things such as tools and materials needed to perform a task.

[0196] The "management screen" is an interface for tracking the progress of tasks in real time and sharing information among stakeholders.

[0197] "Communication" refers to the exchange of information or data between parties.

[0198] "Recommendation" refers to the system selecting and suggesting appropriate workers or robots.

[0199] "Factory robots" refer to mechanical devices that actually operate in a factory environment and perform specific tasks.

[0200] The system of the present invention is a program for managing tasks within a factory, and is implemented using the following hardware and software.

[0201] Program processing explanation

[0202] 1. Task Input Module:

[0203] The server provides a user interface for entering tasks. The interface runs on a tablet or personal computer and displays a form that allows users to enter tasks. The form includes input fields for task details, assignee assignments, and so on.

[0204] 2. Task Analysis Module:

[0205] The server analyzes the input task content using natural language processing technology. Specifically, it uses natural language processing engines such as spaCy and TensorFlow to extract keywords and context from the task content. Even if the task content is ambiguous, it analyzes the context and takes appropriate action.

[0206] 3. Agent Recommendation Module:

[0207] The server then refers to a user profile database based on the analyzed task information and recommends the appropriate worker. The database contains information about each user's abilities, workload, and past performance data, and the server selects the most suitable worker based on this information. Recommendations may also be made based on the capabilities of the robots operating in the factory.

[0208] 4. Task instruction generation module:

[0209] The server automatically generates specific task instructions for the recommended workers and robots. These instructions include the specific steps and necessary work processes for the task. For example, a specific instruction such as "pick out part A and perform welding" may be generated.

[0210] 5. Resource Provision Module:

[0211] The server identifies and provides the resources needed to perform a task, including links to the necessary tools and materials for quick access by users and robots.

[0212] 6. Progress Management Module:

[0213] The server monitors the progress of tasks in real time and supports communication between stakeholders through a management interface that includes a progress timeline, progress progress, and feedback functionality.

[0214] Examples and prompts

[0215] Examples:

[0216] 1. The user enters "Assemble part A" into the tablet device.

[0217] 2. The server analyzes the task content using natural language processing and extracts the keywords "Part A" and "assembly."

[0218] 3. Based on the analyzed information, the server refers to the user profile database and recommends workers and robots with extensive experience in assembling part A.

[0219] 4. The server automatically generates specific instructions, such as "pick up part A and weld it," and sends them to the recommended worker or robot.

[0220] 5. The server provides the necessary resources, such as the welding tool and the location information of part A.

[0221] 6. The administrator checks the progress on the management screen and provides feedback as needed.

[0222] Example prompt sentence:

[0223] Here's a new task: "Assemble part A." Please use a powerful natural language processing engine to analyze it and assign it to the appropriate robot. Please also automatically generate specific task instructions and required resource information.

[0224] This enables efficient task allocation and progress management, leading to equalized workloads within the factory and improved productivity.

[0225] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0226] Step 1:

[0227] The user opens an operation screen on a tablet device or personal computer for entering tasks. Here, the user enters task details, such as "Assemble part A." The input data includes the task content, the person in charge, the deadline, etc. The entered information is sent to the server via the API.

[0228] Step 2:

[0229] The server analyzes the received task content using natural language processing technology. Specifically, it uses a natural language processing engine (e.g., spaCy or TensorFlow) to extract keywords and context from the task content. At this stage, important keywords such as "Part A" and "assembly" are identified. The analysis results are used as input data to query a relational database.

[0230] Step 3:

[0231] Based on the analysis results, the server queries a relational database to collect information on similar tasks and the resources required. The database stores information on successful and unsuccessful cases of similar tasks, as well as information on the tools used. The query results are further processed and output as information on task execution.

[0232] Step 4:

[0233] Based on the analyzed task information, the server refers to a user profile database and recommends appropriate workers. The user profile database contains information on each worker's capabilities, workload, and past performance data. The capabilities of the robots operating in the factory are also taken into consideration. The selected workers and robots are output as a recommendation list.

[0234] Step 5:

[0235] The server automatically generates specific task instructions for the most suitable workers and robots based on the recommendation list. A template-based generation system is used to create instructions that indicate specific work procedures and required processes. For example, instructions such as "pick out part A and perform welding" are included. The generated task instructions are then sent to the workers and robots.

[0236] Step 6:

[0237] The server identifies and provides the resources needed to perform a task. These resources include information on the tools and materials needed. Links and location information are also provided, allowing workers and robots to quickly access them. This allows for efficient use of resources.

[0238] Step 7:

[0239] The server monitors the progress of tasks in real time and supports communication between stakeholders through a control screen that includes a progress timeline, progress progress, and feedback functions. The progress of workers and robots is updated, and stakeholders can check their respective status and provide instructions or feedback as needed.

[0240] Through this series of steps, tasks can be efficiently assigned and progress managed, resulting in equalized workloads within the factory and improved productivity.

[0241] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0242] The system according to the present invention aims to reduce the excessive pressure of tasks in the workplace and support efficient and transparent work execution. It also incorporates an emotion engine that recognizes the user's emotions and optimizes task management based on the emotions. Hereinafter, the embodiments of the present invention will be described in detail.

[0243] Overall system configuration

[0244] The system mainly consists of the following components:

[0245] 1. User Interface

[0246] 2. Natural Language Processing Engine

[0247] 3. User Profile Database

[0248] 4. Task Recommendation Engine

[0249] 5. Task Instruction Generation Engine

[0250] 6. Resource Management System

[0251] 7. Work progress management dashboard

[0252] 8. Emotion Engine

[0253] System processing flow

[0254] Task input and emotion recognition

[0255] A user inputs a task into the system via a terminal. For example, a specific task such as "conduct market research for a new product" is input. The terminal accepts this input, and at the same time, an emotion engine is activated to analyze the user's input and behavior. The emotion engine recognizes the user's current emotional state (e.g., stress, elation, etc.).

[0256] Task Analysis

[0257] The server analyzes the received task using a natural language processing engine. This analysis extracts keywords and context (e.g., "new product" or "market research") from the task content. The server then queries a related database to retrieve similar tasks and reference materials.

[0258] Recommendation from a representative

[0259] The server references the user profile database and selects the most suitable agent based on each user's skill set, workload, and past performance data. The results of the emotion engine are also reflected in this process. For example, Agent A, who has extensive experience in market research and is currently under low stress, may be recommended. This recommendation information is sent to the terminal.

[0260] Auto-generation of task instructions

[0261] The server automatically generates specific task instructions based on the task content and related goals. The instructions are adjusted to suit the user's needs, taking into account the results of the emotion engine. For example, instructions can be flexibly adjusted according to the user's emotional state, such as "First, research competing products, then analyze market trends."

[0262] Provision of necessary resources

[0263] The server identifies the resources needed for the task (e.g., survey templates and online research tools) and provides links to them to the device, allowing users to quickly access the required resources.

[0264] Transparency in work progress and communication support

[0265] The device confirms the recommended agent and automatically generated instructions. After the agent accepts the task, their progress is tracked in real time by the server. Progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[0266] Specific examples

[0267] 1. Task Input and Emotion Recognition

[0268] The user types "I want to conduct market research on a new product" into the terminal.

[0269] Along with this task, the device also analyzes the user's input and uses an emotion engine to recognize the user's emotional state.

[0270] 2. Task Analysis

[0271] The server analyzes the task content using natural language processing and extracts keywords such as "new product" and "market research."

[0272] The server queries the relational database to obtain similar task information and resources.

[0273] 3. Recommendation of the person in charge

[0274] The server refers to the user's skill data and the results of the emotion engine and recommends agent A.

[0275] The server generates the reason for recommendation and displays it on the terminal.

[0276] 4. Generate task instructions

[0277] The server generates specific task instructions (e.g., "Research competing products") and sends them to the device, reflecting the results of the emotion engine.

[0278] 5. Providing necessary resources

[0279] The server collects links to resources necessary for market research and provides them to the terminal.

[0280] 6. Progression and communication support

[0281] The device displays the dashboard and person in charge A updates the progress.

[0282] All stakeholders can see progress in real time and provide comments and feedback as needed.

[0283] This system provides an environment in which users can perform their work efficiently and make the most of opportunities for growth. In addition, incorporating an emotion engine enables flexible task management that takes into account the user's emotional state, which is expected to reduce work stress.

[0284] The processing flow will be explained below.

[0285] Step 1:

[0286] The user inputs a task via a terminal, for example, "conduct market research for a new product."

[0287] Step 2:

[0288] The device accepts the input task and sends it to the server. At the same time, the device sends the user's input and actions to the emotion engine, which analyzes the user's emotional state.

[0289] Step 3:

[0290] The emotion engine analyzes the user's input and behavioral patterns to recognize the emotions the user is currently feeling (e.g., stress, elation, etc.).

[0291] Step 4:

[0292] The server receives the task and begins analyzing it with a natural language processing engine, extracting keywords and context (e.g., "new product," "market research") from the task content.

[0293] Step 5:

[0294] The server queries a related database to collect similar tasks and related resources based on the extracted keywords.

[0295] Step 6:

[0296] The server checks the user profile database and analyzes each user's skill set, current workload, and past performance data.

[0297] Step 7:

[0298] The server selects the most suitable agent based on the analytical data and the results of the emotion engine. For example, it recommends Agent A, who has extensive experience in market research and is currently under low stress.

[0299] Step 8:

[0300] The server generates the reason for recommending agent A and sends this information to the terminal. The terminal displays a list of recommended agents and the reason.

[0301] Step 9:

[0302] The server automatically generates specific task instructions based on the task content. The instructions are adjusted to be more user-friendly, taking into account the results of the emotion engine. For example, it generates specific steps such as "First, research competing products, then analyze market trends."

[0303] Step 10:

[0304] The server generates specific task instructions and sends them to the device, where they are displayed and viewed by the user.

[0305] Step 11:

[0306] The server identifies the resources needed to complete the task and generates links to access them, such as survey templates and online research tools.

[0307] Step 12:

[0308] The server sends these resource links to the terminal, which displays the access links and their descriptions.

[0309] Step 13:

[0310] The device checks the recommended agent and automatically generated instructions. When agent A accepts the task, the status is sent from the device to the server.

[0311] Step 14:

[0312] The server tracks the progress of tasks in real time and collects progress data, which is then reflected in the work progress management dashboard.

[0313] Step 15:

[0314] The device displays a progress management dashboard, allowing all stakeholders to see the progress and provide comments and feedback.

[0315] Step 16:

[0316] Users communicate in real time through the dashboard to provide any necessary coordination or assistance.

[0317] Example 2

[0318] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0319] Conventional task management systems assign tasks without considering the user's emotional state, which increases work stress and pressure, potentially leading to reduced productivity and mental exhaustion. Furthermore, the recommendation of appropriate personnel and the generation of specific task instructions are not sufficiently automated, resulting in reduced management efficiency and difficulty in transparent work progress. There is a need to solve these problems and realize flexible task management that takes the user's emotional state into account.

[0320] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0321] In this invention, the server includes: means for providing a user interface for inputting tasks; means for analyzing the input tasks using natural language processing technology; means for recommending appropriate personnel based on the analyzed tasks and the user's skill set, workload, and past performance data; means for automatically generating specific task instructions for the recommended personnel; means for identifying and providing resources necessary to perform the tasks; means for incorporating an emotion engine that recognizes the user's emotional state and optimizes task management based thereon; and means for tracking task progress in real time and providing a dashboard that supports communication between parties involved. This enables flexible and efficient task management that takes the user's emotional state into consideration, thereby reducing work stress and improving productivity.

[0322] A "user interface" is an interface through which a user accesses a system to input tasks or obtain information.

[0323] "Natural language processing technology" is a technology for analyzing and understanding natural human language.

[0324] "User skill set" is a collective term for the skills, knowledge, and experience possessed by a particular user.

[0325] "Workload" refers to the amount and complexity of tasks currently being handled by each user.

[0326] "Past performance data" refers to data on the results and evaluations of tasks that each user has performed in the past.

[0327] "Rep recommendation" is the process of selecting the most suitable representative based on the user profile database.

[0328] "Automatic generation of task instructions" refers to automatically creating specific instructions based on task content and goals.

[0329] "Providing resources" means providing users with the tools, data, and templates necessary to complete a task.

[0330] The "emotion engine" is part of a system that recognizes the user's emotional state through analysis of their facial expressions and voice, and reflects this in task management.

[0331] A "dashboard" is an interface that displays task progress and related information in real time and supports communication between stakeholders.

[0332] This invention is a system that reduces excessive task pressure in the workplace and supports efficient and transparent work execution. In particular, it aims to reduce work stress by incorporating an emotion engine that recognizes the user's emotions and optimizes task management based on those emotions. Specific embodiments for implementing this invention are described below.

[0333] Overall system configuration

[0334] The system mainly consists of the following components:

[0335] 1. User Interface

[0336] 2. Natural Language Processing Engine (NLP Engine)

[0337] 3. User Profile Database (DB)

[0338] 4. Task Recommendation Engine

[0339] 5. Task Instruction Generation Engine

[0340] 6. Resource Management System

[0341] 7. Work progress management dashboard

[0342] 8. Emotion Engine

[0343] Hardware and software used

[0344] To realize this system, the following hardware and software are used.

[0345] Device: The device (computer, tablet, smartphone, etc.) through which the user enters the task.

[0346] Server: A device that analyzes tasks, recommends task managers, generates task instructions, tracks progress, etc. It is equipped with a high-performance CPU and memory.

[0347] Camera and microphone: Used as input devices to analyze the user's emotions.

[0348] NLP engine: Software that analyzes text. Specifically, it uses the Python library Natural Language Toolkit (NLTK) and SpaCy.

[0349] Emotion engine: Software for analyzing the user's facial expressions and voice. Specifically, it uses OpenCV, DeepFace, and the Google® Speech-to-Text API for voice recognition.

[0350] Specific operation of the system

[0351] Task input and emotion recognition

[0352] The user inputs a task into the system via a terminal. For example, the user inputs an instruction such as "conduct market research for a new product." The terminal then sends this input to the server. At the same time, the server analyzes the user's current emotional state using a camera and microphone connected to the terminal. As a result, the server recognizes information such as "the user is excited."

[0353] Task Analysis

[0354] The server analyzes the received task using a natural language processing engine. It uses NLP engines such as NLTK and SpaCy to extract keywords and context from the input text. It then queries a related database to retrieve similar tasks and reference materials. For example, keywords such as "new product" and "market research" are extracted.

[0355] Recommendation from a representative

[0356] The server refers to the user profile database and selects the most suitable agent based on each user's skill set, workload, and past performance data. This process also takes into account the results of the emotion engine. For example, it may recommend "agent A, who has extensive experience in market research and is currently under low stress." This recommendation information is sent to the terminal and can be viewed by the user.

[0357] Auto-generation of task instructions

[0358] The server automatically generates specific task instructions based on the task content and related goals. Taking into account the results of the emotion engine, the instructions are adjusted to be more user-friendly. For example, specific instructions such as "First, research competitor products, then analyze market trends" are generated. These instructions are then sent to the device.

[0359] Provision of necessary resources

[0360] The server identifies the resources needed for the task and provides links to them to the device, such as survey templates and links to online research tools, for quick access by the user.

[0361] Transparency in work progress and communication support

[0362] The device confirms the recommended agent and automatically generated instructions. After the agent accepts the task, the progress is tracked in real time by the server. The progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[0363] Specific prompt examples

[0364] "Conduct market research for new products"

[0365] "First, research competitor products, then analyze market trends."

[0366] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0367] Step 1: Enter your task

[0368] A user inputs a task into the system via a terminal. For example, the user inputs a specific task such as "conduct market research for a new product." This input is saved as text data on the terminal. The terminal then sends this input data to the server.

[0369] Input: Task input from user (text format)

[0370] Output: Task input data (sent to server)

[0371] Step 2: Recognize emotions

[0372] The device activates an emotion engine to analyze the user's input and behavior. The device collects the user's facial expressions and voice through the camera and microphone and sends the data to the emotion engine. The emotion engine uses image analysis software (OpenCV and DeepFace) and voice analysis software (Google Speech-to-Text API) to recognize the user's emotional state.

[0373] Input: User's facial expression data, voice data

[0374] Output: Emotional state (e.g., "high stress," "relaxed")

[0375] Step 3: Analyzing the task

[0376] The server analyzes the received task input data using a natural language processing engine (NLTK or SpaCy). The server performs morphological and contextual analysis to extract keywords and context from the input data. At the same time, the server queries a related database to retrieve similar tasks and reference materials.

[0377] Input: Task input data

[0378] Output: Extracted keywords (e.g., "new product," "market research"), related materials

[0379] Step 4: Recommend a Representative

[0380] The server refers to the user profile database and selects the most suitable agent based on each user's skill set, workload, and past performance data. The output information of the emotion engine is also taken into consideration, so for example, Agent A, who has extensive experience in market research and is currently under low stress, may be selected. The server generates the reason for the recommendation and sends it to the terminal.

[0381] Inputs: Skill set data, workload data, performance data, emotional state

[0382] Output: Recommender (e.g., Person A), reason for recommendation

[0383] Step 5: Auto-generate task instructions

[0384] The server automatically generates specific task instructions based on the task content and related goals. Taking into account the results of the emotion engine, the instructions are adjusted to be more user-friendly. For example, specific instructions such as "First, research competing products, then analyze market trends" are generated. These instructions are then sent to the device.

[0385] Input: Task content, goal, emotional state

[0386] Output: Specific task instructions (e.g., "Research competing products")

[0387] Step 6: Providing necessary resources

[0388] The server identifies the resources needed for the task and provides links to them to the device, such as survey templates and links to online research tools needed for market research, allowing users to quickly access them.

[0389] Input: Task details, required resource information

[0390] Output: Resource links (e.g., survey templates, online tools)

[0391] Step 7: Transparency and communication support for work progress

[0392] The device checks the recommended agent and automatically generated instructions, then begins the process of verifying whether the agent has accepted the task. After the agent accepts the task, the server tracks its progress in real time. The progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[0393] Input: Acceptance status of person in charge, task instructions

[0394] Output: Real-time progress, dashboard display

[0395] This allows users to manage tasks efficiently while taking their emotional state into account, reducing work stress and improving productivity.

[0396] (Application example 2)

[0397] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0398] Imbalances in workloads and increased work stress in factories can lead to reduced production efficiency and work errors. In particular, allocating tasks without considering the emotional state of robots and operators poses challenges in efficient work execution and in optimal production management. Furthermore, it is difficult to grasp the progress in real time, and effective communication support is lacking. Solutions to these issues are needed.

[0399] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0400] In this invention, the server includes: a means for providing a user interface for inputting tasks; a means for analyzing the input tasks using natural language processing; a means for recommending appropriate personnel based on the analyzed tasks and the user's skill set, workload, and past performance data; a means for automatically generating specific task instructions for the recommended personnel; a means for identifying and providing resources necessary to perform the tasks; a means for tracking task progress in real time and providing a dashboard to support communication between stakeholders; and a means for recognizing the emotional state of robots and optimally allocating tasks based on this. This enables even workload distribution within a factory and improves production efficiency. Furthermore, it also enables real-time progress monitoring and effective communication support.

[0401] "User interface" refers to the means and screen configuration for a user to input tasks into the system.

[0402] "Natural language processing technology" refers to the technology used to analyze the content of a task, and to extract keywords and context from the input text.

[0403] "Skill set" refers to the specific technical abilities and knowledge possessed by a user or robot.

[0404] "Workload" refers to the amount of work currently being done by a user or a robot.

[0405] "Performance Data" refers to data relating to the past work results and evaluations of a user or robot.

[0406] "Rep" refers to a person or robot that is assigned a specific task and is responsible for carrying it out.

[0407] "Task instructions" refer to instructions that explain specifically how to perform an assigned task.

[0408] "Resources" refer to the materials and tools needed to perform a task.

[0409] "Dashboard" refers to an interface for visually managing and displaying task progress and related information.

[0410] "Emotional state" refers to the current psychological state of the robot or user.

[0411] "Task recommendation engine" refers to algorithms and systems that recommend the most suitable person based on the analyzed task.

[0412] "Task allocation" refers to the process of appropriately assigning multiple tasks to each person in charge.

[0413] The present invention relates to a "factory workload management system" for resolving imbalances in workloads and increased work stress in factories. The system aims to recognize the emotional states of robots and operators and optimally allocate work tasks based on the recognition. Specific embodiments for carrying out the present invention will be described in detail below.

[0414] Overall system configuration

[0415] The system mainly consists of the following components:

[0416] 1. User interface: The means by which the user inputs the task.

[0417] 2. Natural language processing technology: A means of analyzing the content of the input task and extracting keywords and context.

[0418] 3. User profile database: A database that stores users' skill sets, workloads, and past performance data.

[0419] 4. Task recommendation engine: A means of recommending the most suitable person to handle a task based on the analyzed task.

[0420] 5. Task instruction generation engine: A means of automatically generating specific task instructions for recommended personnel.

[0421] 6. Resource Management System: A means of identifying and providing the resources needed to perform a task.

[0422] 7. Work Progress Management Dashboard: A means of tracking task progress in real time and supporting communication between stakeholders.

[0423] 8. Emotion engine: A means of recognizing the emotional state of the robot and optimally allocating tasks.

[0424] Hardware and Software Configuration

[0425] Hardware

[0426] Factory robots: Each robot is equipped with an emotion recognition sensor that can detect its emotional state in real time.

[0427] Central management server: Manages the entire system and processes data from each component.

[0428] software

[0429] Python language: A programming language for implementing task analysis and allocation algorithms.

[0430] Database management system (e.g., MySQL®): stores and manages user profile data, task data, and resource data.

[0431] Emotion recognition software: Software for analyzing the emotional state of each robot.

[0432] System processing flow

[0433] The server receives task input from a user or automated system and processes it according to the following steps:

[0434] 1. Task Input and Emotion Recognition

[0435] The terminal inputs the task, and the emotion engine recognizes the robot's emotional state.

[0436] 2. Task Analysis

[0437] The server analyzes the task content using natural language processing technology and extracts relevant keywords and context.

[0438] 3. Recommendation of the person in charge

[0439] The task recommendation engine references a user profile database and recommends the best person based on skill set, workload, performance data, and emotional state.

[0440] 4. Automatic generation of task instructions

[0441] The server generates specific task instructions and notifies the person in charge.

[0442] 5. Identifying and Providing Resources

[0443] The server identifies and provides the resources needed for the task.

[0444] 6. Progression and communication support

[0445] A progress management dashboard tracks progress in real time and supports communication between stakeholders.

[0446] Specific examples

[0447] For example, if a robot is assigned the task of "conducting market research for a new product" in a factory, the emotion engine will classify the robot's emotional state as "happy," "neutral," or "stressed," and assign the task to the robot that is most suitable for the task. This will enable the equalization of workloads and improved production efficiency.

[0448] Prompt Sentence Examples

[0449] Design a system for optimal task allocation for factory robots based on each robot's emotional state and task load. Write a program in Python to create a flow for manually assigning the following tasks. Create a program that assigns tasks to the optimal robot and displays the final task load for each robot.

[0450] In this way, by using a system based on this invention, it is possible to evenly distribute the workload within a factory and improve production efficiency. It also makes it possible to allocate tasks taking into account the emotional state of the robot, which is expected to reduce work stress.

[0451] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0452] Step 1:

[0453] The terminal inputs a task and emotion recognition by the emotion engine begins. The user inputs a task into the terminal, such as "conduct market research for a new product." While receiving the input task, the emotion engine detects the robot's emotional state using the emotion recognition sensor. The input is the task content and the robot's current emotional state, and the output is task data and emotion data for analysis.

[0454] Step 2:

[0455] The server analyzes the task content using natural language processing technology. The server extracts keywords and context from the input task content, obtaining keywords such as "market research" and "new product." The input is the task data, and the output is the analyzed keywords and context information.

[0456] Step 3:

[0457] The server refers to the user profile database and recommends the most suitable agent using the task recommendation engine. The server selects the most suitable robot by taking into account the user's skill set, workload, past performance data, and emotional state. The input is keywords, context information, and information from the user profile database, and the output is a list of recommended agents.

[0458] Step 4:

[0459] The server automatically generates specific task instructions and notifies the person in charge. For example, instructions such as "First, research competing products, then analyze market trends" are generated. The input is the recommended person in charge and the task content, and the output is specific task instructions.

[0460] Step 5:

[0461] The server identifies and provides the resources needed for the task. For example, it collects survey templates and links to online research tools and provides them to the device. The input is specific task instructions, and the output is resource links.

[0462] Step 6:

[0463] The work progress management dashboard tracks progress in real time and supports communication between stakeholders. The person in charge updates the progress of the task, and all stakeholders can see it in real time. The input is progress data from the person in charge, and the output is dashboard information updated in real time.

[0464] The above processing steps enable the even distribution of work loads within the factory, improving production efficiency. It also enables task allocation that takes into account the emotional state of the robot, reducing stress during work and tasks.

[0465] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0466] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0467] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0468] [Second embodiment]

[0469] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0470] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0471] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0472] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0473] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0474] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0475] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0476] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0477] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0478] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0479] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0480] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0481] The system according to the present invention aims to reduce the excessive pressure of tasks in the workplace and to support efficient and transparent business execution. Hereinafter, an embodiment of the present invention will be described in detail.

[0482] Overall system configuration

[0483] The system mainly consists of the following components:

[0484] 1. User Interface

[0485] 2. Natural Language Processing Engine

[0486] 3. User Profile Database

[0487] 4. Task Recommendation Engine

[0488] 5. Task Instruction Generation Engine

[0489] 6. Resource Management System

[0490] 7. Work progress management dashboard

[0491] System processing flow

[0492] Task Input

[0493] A user inputs a task into the system via a terminal. For example, a specific task such as "conduct market research for a new product" is input. The terminal accepts this input and sends it to the server.

[0494] Task Analysis

[0495] The server analyzes the received task using a natural language processing engine. This analysis extracts keywords and context (e.g., "new product" or "market research") from the task content. The server then queries a related database to retrieve similar tasks and reference materials.

[0496] Recommendation from a representative

[0497] The server refers to a user profile database and selects the most suitable person based on each user's skill set, workload, and past performance data. For example, users with extensive market research experience are given priority in the recommendation. This recommendation information is sent to the terminal.

[0498] Auto-generation of task instructions

[0499] The server automatically generates specific task instructions based on the task content and related goals, such as "First, research competitive products, then analyze market trends." These instructions are sent to the device for review by the user.

[0500] Provision of necessary resources

[0501] The server identifies the resources needed for the task (e.g., survey templates and online research tools) and provides links to them to the device, allowing users to quickly access the required resources.

[0502] Transparency in work progress and communication support

[0503] The device confirms the recommended agent and automatically generated instructions. After the agent accepts the task, their progress is tracked in real time by the server. Progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[0504] Specific examples

[0505] 1. Enter the task

[0506] The user types "I want to conduct market research on a new product" into the terminal.

[0507] The terminal sends this to the server.

[0508] 2. Task Analysis

[0509] The server analyzes the task content using natural language processing and extracts keywords such as "new product" and "market research."

[0510] The server queries the relational database to obtain similar task information and resources.

[0511] 3. Recommendation of the person in charge

[0512] The server refers to the user's skill data and recommends agent A.

[0513] The server generates the reason for recommendation and displays it on the terminal.

[0514] 4. Generate task instructions

[0515] The server generates specific task instructions (e.g., "research competing products") and sends them to the device.

[0516] 5. Providing necessary resources

[0517] The server collects links to resources necessary for market research and provides them to the terminal.

[0518] 6. Progression and communication support

[0519] The device displays the dashboard and person in charge A updates the progress.

[0520] All stakeholders can see progress in real time and provide comments and feedback as needed.

[0521] This system provides an environment in which users can carry out their work efficiently and make the most of opportunities for growth. This series of processes reduces stress for users through automation and transparency, and has the effect of improving work productivity.

[0522] The processing flow will be explained below.

[0523] Step 1:

[0524] The user inputs a task via a terminal, for example, "conduct market research for a new product."

[0525] Step 2:

[0526] The device accepts the input task and sends it to the server. The sent data includes the task content and the user's ID.

[0527] Step 3:

[0528] The server receives the task and begins analyzing it using a natural language processing engine. The server extracts keywords and context (e.g., "new product," "market research") from the task content.

[0529] Step 4:

[0530] The server queries a related database to collect similar tasks and related resources based on the extracted keywords.

[0531] Step 5:

[0532] The server checks the user profile database and analyzes each user's skill set, current workload, and past performance data.

[0533] Step 6:

[0534] The server selects the most suitable person based on the analysis data. For example, it may recommend person A, who has extensive experience in market research.

[0535] Step 7:

[0536] The server generates the reason for recommending agent A and sends this information to the terminal. The terminal displays a list of recommended agents and the reason.

[0537] Step 8:

[0538] The server automatically generates specific task instructions based on the task content, such as "First, research competitor products, then analyze market trends."

[0539] Step 9:

[0540] The server generates specific task instructions and sends them to the device, where they are displayed and viewed by the user.

[0541] Step 10:

[0542] The server identifies the resources needed to complete the task and generates links to access them, such as survey templates and online research tools.

[0543] Step 11:

[0544] The server sends these resource links to the terminal, which displays the access links and their descriptions.

[0545] Step 12:

[0546] The device confirms the recommended agent and the automatically generated instructions. When Agent A accepts the task, a confirmation is sent from the device to the server.

[0547] Step 13:

[0548] The server tracks the progress of tasks in real time and collects progress data, which is then reflected in the work progress management dashboard.

[0549] Step 14:

[0550] The device displays a progress management dashboard, allowing all stakeholders to view progress, provide comments, and provide feedback.

[0551] Step 15:

[0552] Users communicate in real time through the dashboard to provide any necessary coordination or assistance.

[0553] Example 1

[0554] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0555] In conventional task management systems, task assignment and progress tracking are performed manually, resulting in low work efficiency and a lack of transparency. It is also difficult to select the right person for the task, often resulting in delays in providing appropriate resources. Furthermore, there is a lack of communication between stakeholders, which reduces work productivity. The purpose of this invention is to solve these problems and improve work efficiency and transparency.

[0556] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0557] In this invention, the server includes a means for analyzing tasks using natural language processing technology, a means for recommending an appropriate person to perform the task based on the user's ability set, workload, and past performance data, and a means for automatically generating specific task instructions. This enables efficient analysis of tasks, appropriate recommendation of a person to perform the task, and automatic generation of specific instructions. Furthermore, by including a terminal that tracks the progress of tasks in real time and supports information exchange between related parties, and a means for identifying and providing resources required to perform the tasks, the transparency and efficiency of work are improved.

[0558] A "terminal" is an electronic device used by a user to input tasks and check instructions and progress. This includes computers and smartphones.

[0559] A "server" is a central processing unit that executes multiple means, and is a device that is responsible for analyzing tasks, recommending personnel, automatically generating task instructions, providing resources, and tracking progress.

[0560] "Natural language processing technology" is a technology for analyzing the content of a task and extracting keywords and context, and includes machine learning models and text analysis algorithms.

[0561] The "user ability set" is data relating to the job capabilities and skills of each user, and is information used for task allocation and recommendation of personnel.

[0562] "Workload" is data about the amount of tasks each user currently has and ongoing projects.

[0563] "Past achievement data" is a history of tasks and projects that the user has completed in the past, and is data related to their evaluations and achievements.

[0564] "Task instructions" are instructions that indicate the specific steps or procedures that must be performed to accomplish a particular task.

[0565] "Resources" are information or items such as materials, tools, templates, links, etc. required to perform a task.

[0566] A "dashboard" is a visual interface that displays the progress of tasks in real time and supports information exchange among stakeholders.

[0567] The present invention is a system that aims to improve the efficiency and transparency of task management in a workplace environment. This system mainly consists of the following components: a terminal, a server, a natural language processing engine, a user profile database, a task recommendation engine, a task instruction generation engine, a resource management system, and a work progress management dashboard.

[0568] System Configuration

[0569] Terminal

[0570] Users use a device (such as a PC or smartphone) to input tasks and check their progress. The device provides a user interface and sends the input tasks to the server. The device also displays the information sent from the server to the user.

[0571] server

[0572] The server serves as the central hub of the entire system and fulfills multiple roles. The specific processing performed by the server is shown below.

[0573] Natural Language Processing Engine

[0574] When a task is input, the server first analyzes the task content using a natural language processing engine (e.g., TensorFlow or OpenNLP). This analysis extracts key keywords and context from the task. For example, if the task is "conduct market research for a new product," the keywords "new product" and "market research" are extracted.

[0575] User profile database and task recommendation engine

[0576] Based on the analyzed task content, the server references a user profile database, which stores each user's ability set, workload, and past performance data. Based on this information, the server recommends the person best suited to the task. For example, a user with extensive market research experience and a light current workload may be recommended. The recommendation results are displayed on the terminal.

[0577] Task Instruction Generation Engine

[0578] The server automatically generates specific task instructions based on the acquired task content and the recommended person in charge. For example, it may generate specific steps such as "research competing products, then analyze market trends." This automatically generated instruction is sent to the terminal and can be confirmed by the user.

[0579] Resource Management System

[0580] The server identifies the resources (e.g., survey templates and online research tools) needed to complete the task and provides links to them to the device, allowing the user to quickly access the required resources. For example, specific resources such as "Market Research Template.xlsx" or "Access Link to Competitive Analysis Tool" can be included.

[0581] Business progress management dashboard

[0582] Users use a work progress management dashboard to check progress and communicate. The server tracks the progress of tasks in real time and displays it on the dashboard. After a task is accepted by a person in charge, the progress and related communications can be viewed by all parties on the dashboard. This ensures transparency of work and enables efficient information exchange.

[0583] Examples and prompts

[0584] Specific examples

[0585] Task Input

[0586] The user types "I want to conduct market research on a new product" into the terminal.

[0587] The terminal sends this to the server.

[0588] Task Analysis

[0589] The server uses a natural language processing engine to extract key keywords such as "new product" and "market research."

[0590] The server queries the relational database to obtain similar task information and resources.

[0591] Recommendation from a representative

[0592] The server refers to the user's skill data and recommends "users with extensive market research experience."

[0593] This information, along with the reason for the recommendation, is sent to the device.

[0594] Generate task instructions

[0595] The server generates specific task instructions (e.g., "research competing products") and sends them to the device.

[0596] Provision of necessary resources

[0597] The server identifies a resource such as "Market Research Template.xlsx" and provides it to the device.

[0598] Progression and communication support

[0599] The device displays progress on a dashboard, and the person in charge updates the progress as it happens.

[0600] All stakeholders can view and comment on progress and feedback in real time through a dashboard.

[0601] Prompt Sentence Examples

[0602] "I'd like to conduct market research for a new product. Please set the task to include researching competitive products and analyzing market trends."

[0603] "What are the specific steps I should take to start researching competitive products and then analyzing market trends?"

[0604] The system of the present invention provides an environment in which users can perform their work efficiently and maximize opportunities for growth. The aim is to reduce user stress through automation and transparency and improve work productivity.

[0605] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0606] Step 1:

[0607] The user inputs a task using a terminal. Specifically, the user inputs the task content (e.g., "Conduct market research for a new product") in text format through the terminal's user interface. The terminal then sends this input content to the server. The input data is the task content in natural language format and is passed to the server.

[0608] Step 2:

[0609] The server receives the task content and analyzes it using a natural language processing engine (e.g., TensorFlow or OpenNLP). Specifically, it extracts key keywords (e.g., "new product," "market research") and contextual information from the task text. The input data is the task content in text format, and the output data is the extracted keywords and contextual information.

[0610] Step 3:

[0611] The server queries the user profile database based on the extracted keywords and context information to obtain information such as past performance data, workload, and skill sets. The server analyzes this data and recommends the most suitable agent for the task. The input data are the extracted keywords and user profile information, and the output data are the recommended agent and the reason for the recommendation.

[0612] Step 4:

[0613] The server automatically generates specific task instructions for the recommended personnel. Specific steps (e.g., "Start researching competitive products, then analyze market trends") are automatically created based on predefined templates and past task instructions. The input data is the task content and information on the recommended personnel, and the output data is specific task instructions.

[0614] Step 5:

[0615] The server identifies the resources required to execute the task and provides the terminal with links and materials. Specifically, it collects research tools and templates (e.g., "Market Research Template.xlsx") and generates access links to them. The input data is the task content and resource information, and the output data is the links and materials for the required resources.

[0616] Step 6:

[0617] The user confirms the recommended agent and specific task instructions via the terminal. The agent accepts the task, and the server tracks its progress in real time. The progress is displayed on the terminal's work progress management dashboard, allowing all parties involved to check the progress and provide comments and feedback as needed. The input data is the ongoing task information, and the output data is the progress and feedback updated in real time.

[0618] Through these series of processing steps, the system can achieve efficient management and transparency of tasks, reducing the burden on users.

[0619] (Application example 1)

[0620] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0621] In modern factory operations, task allocation and progress management have become increasingly complex, making it difficult to carry out work efficiently. While there is also a need to maximize the capabilities of robots and deploy them in the right positions, current systems are unable to fully achieve this. This leads to uneven workloads within the factory, reducing the productivity of the manufacturing process.

[0622] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0623] In this invention, the server includes means for providing an operation screen for inputting tasks, means for analyzing the input tasks using natural language processing technology, means for recommending appropriate workers based on the analyzed tasks and on the user's capabilities, workload, and past execution data, means for automatically generating specific task instructions for the recommended workers, means for identifying and providing resources necessary for executing the tasks, means for tracking the progress of tasks in real time and providing a management screen that supports communication between related parties, means for considering the capabilities of robots operating in the factory when selecting and recommending workers, and means for automatically generating specific work instructions for the recommended robots. This enables efficient task allocation and progress management, thereby achieving equalization of workloads within the factory and improved productivity.

[0624] An "operation screen" is a display screen that provides an interface for a user to input a task.

[0625] "Natural language processing technology" is a technology for analyzing and understanding documents written in human language.

[0626] A "task" is an activity or task performed to achieve a specific goal.

[0627] "User" refers to the person or administrator who operates the system and inputs tasks.

[0628] "Ability" refers to the technical skills and knowledge possessed by a user or robot.

[0629] "Workload" refers to the amount of work a worker currently has and the state of their work.

[0630] "Execution data" is data that records the performance and results of tasks performed in the past.

[0631] "Worker" refers to a human or robot that performs the tasks recommended by the system.

[0632] "Task instructions" refer to instructions that show the specific steps and methods for executing a task.

[0633] "Resources" refer to things such as tools and materials needed to perform a task.

[0634] The "management screen" is an interface for tracking the progress of tasks in real time and sharing information among stakeholders.

[0635] "Communication" refers to the exchange of information or data between parties.

[0636] "Recommendation" refers to the system selecting and suggesting appropriate workers or robots.

[0637] "Factory robots" refer to mechanical devices that actually operate in a factory environment and perform specific tasks.

[0638] The system of the present invention is a program for managing tasks within a factory, and is implemented using the following hardware and software.

[0639] Program processing explanation

[0640] 1. Task Input Module:

[0641] The server provides a user interface for entering tasks. The interface runs on a tablet or personal computer and displays a form that allows users to enter tasks. The form includes input fields for task details, assignee assignments, and so on.

[0642] 2. Task Analysis Module:

[0643] The server analyzes the input task content using natural language processing technology. Specifically, it uses natural language processing engines such as spaCy and TensorFlow to extract keywords and context from the task content. Even if the task content is ambiguous, it analyzes the context and takes appropriate action.

[0644] 3. Agent Recommendation Module:

[0645] The server then refers to a user profile database based on the analyzed task information and recommends the appropriate worker. The database contains information about each user's abilities, workload, and past performance data, and the server selects the most suitable worker based on this information. Recommendations may also be made based on the capabilities of the robots operating in the factory.

[0646] 4. Task instruction generation module:

[0647] The server automatically generates specific task instructions for the recommended workers and robots. These instructions include the specific steps and necessary work processes for the task. For example, a specific instruction such as "pick out part A and perform welding" may be generated.

[0648] 5. Resource Provision Module:

[0649] The server identifies and provides the resources needed to perform a task, including links to the necessary tools and materials for quick access by users and robots.

[0650] 6. Progress Management Module:

[0651] The server monitors the progress of tasks in real time and supports communication between stakeholders through a management interface that includes a progress timeline, progress progress, and feedback functionality.

[0652] Examples and prompts

[0653] Examples:

[0654] 1. The user enters "Assemble part A" into the tablet device.

[0655] 2. The server analyzes the task content using natural language processing and extracts the keywords "Part A" and "assembly."

[0656] 3. Based on the analyzed information, the server refers to the user profile database and recommends workers and robots with extensive experience in assembling part A.

[0657] 4. The server automatically generates specific instructions, such as "pick up part A and weld it," and sends them to the recommended worker or robot.

[0658] 5. The server provides the necessary resources, such as the welding tool and the location information of part A.

[0659] 6. The administrator checks the progress on the management screen and provides feedback as needed.

[0660] Example prompt sentence:

[0661] Here's a new task: "Assemble part A." Please use a powerful natural language processing engine to analyze it and assign it to the appropriate robot. Please also automatically generate specific task instructions and required resource information.

[0662] This enables efficient task allocation and progress management, leading to equalized workloads within the factory and improved productivity.

[0663] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0664] Step 1:

[0665] The user opens an operation screen on a tablet device or personal computer for entering tasks. Here, the user enters task details, such as "Assemble part A." The input data includes the task content, the person in charge, the deadline, etc. The entered information is sent to the server via the API.

[0666] Step 2:

[0667] The server analyzes the received task content using natural language processing technology. Specifically, it uses a natural language processing engine (e.g., spaCy or TensorFlow) to extract keywords and context from the task content. At this stage, important keywords such as "Part A" and "assembly" are identified. The analysis results are used as input data to query a relational database.

[0668] Step 3:

[0669] Based on the analysis results, the server queries a relational database to collect information on similar tasks and the resources required. The database stores information on successful and unsuccessful cases of similar tasks, as well as information on the tools used. The query results are further processed and output as information on task execution.

[0670] Step 4:

[0671] Based on the analyzed task information, the server refers to a user profile database and recommends appropriate workers. The user profile database contains information on each worker's capabilities, workload, and past performance data. The capabilities of the robots operating in the factory are also taken into consideration. The selected workers and robots are output as a recommendation list.

[0672] Step 5:

[0673] The server automatically generates specific task instructions for the most suitable workers and robots based on the recommendation list. A template-based generation system is used to create instructions that indicate specific work procedures and required processes. For example, instructions such as "pick out part A and perform welding" are included. The generated task instructions are then sent to the workers and robots.

[0674] Step 6:

[0675] The server identifies and provides the resources needed to perform a task. These resources include information on the tools and materials needed. Links and location information are also provided, allowing workers and robots to quickly access them. This allows for efficient use of resources.

[0676] Step 7:

[0677] The server monitors the progress of tasks in real time and supports communication between stakeholders through a control screen that includes a progress timeline, progress progress, and feedback functions. The progress of workers and robots is updated, and stakeholders can check their respective status and provide instructions or feedback as needed.

[0678] Through this series of steps, tasks can be efficiently assigned and progress managed, resulting in equalized workloads within the factory and improved productivity.

[0679] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0680] The system according to the present invention aims to reduce the excessive pressure of tasks in the workplace and support efficient and transparent work execution. It also incorporates an emotion engine that recognizes the user's emotions and optimizes task management based on the emotions. Hereinafter, the embodiments of the present invention will be described in detail.

[0681] Overall system configuration

[0682] The system mainly consists of the following components:

[0683] 1. User Interface

[0684] 2. Natural Language Processing Engine

[0685] 3. User Profile Database

[0686] 4. Task Recommendation Engine

[0687] 5. Task Instruction Generation Engine

[0688] 6. Resource Management System

[0689] 7. Work progress management dashboard

[0690] 8. Emotion Engine

[0691] System processing flow

[0692] Task input and emotion recognition

[0693] A user inputs a task into the system via a terminal. For example, a specific task such as "conduct market research for a new product" is input. The terminal accepts this input, and at the same time, an emotion engine is activated to analyze the user's input and behavior. The emotion engine recognizes the user's current emotional state (e.g., stress, elation, etc.).

[0694] Task Analysis

[0695] The server analyzes the received task using a natural language processing engine. This analysis extracts keywords and context (e.g., "new product" or "market research") from the task content. The server then queries a related database to retrieve similar tasks and reference materials.

[0696] Recommendation from a representative

[0697] The server references the user profile database and selects the most suitable agent based on each user's skill set, workload, and past performance data. The results of the emotion engine are also reflected in this process. For example, Agent A, who has extensive experience in market research and is currently under low stress, may be recommended. This recommendation information is sent to the terminal.

[0698] Auto-generation of task instructions

[0699] The server automatically generates specific task instructions based on the task content and related goals. The instructions are adjusted to suit the user's needs, taking into account the results of the emotion engine. For example, instructions can be flexibly adjusted according to the user's emotional state, such as "First, research competing products, then analyze market trends."

[0700] Provision of necessary resources

[0701] The server identifies the resources needed for the task (e.g., survey templates and online research tools) and provides links to them to the device, allowing users to quickly access the required resources.

[0702] Transparency in work progress and communication support

[0703] The device confirms the recommended agent and automatically generated instructions. After the agent accepts the task, their progress is tracked in real time by the server. Progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[0704] Specific examples

[0705] 1. Task Input and Emotion Recognition

[0706] The user types "I want to conduct market research on a new product" into the terminal.

[0707] Along with this task, the device also analyzes the user's input and uses an emotion engine to recognize the user's emotional state.

[0708] 2. Task Analysis

[0709] The server analyzes the task content using natural language processing and extracts keywords such as "new product" and "market research."

[0710] The server queries the relational database to obtain similar task information and resources.

[0711] 3. Recommendation of the person in charge

[0712] The server refers to the user's skill data and the results of the emotion engine and recommends agent A.

[0713] The server generates the reason for recommendation and displays it on the terminal.

[0714] 4. Generate task instructions

[0715] The server generates specific task instructions (e.g., "Research competing products") and sends them to the device, reflecting the results of the emotion engine.

[0716] 5. Providing necessary resources

[0717] The server collects links to resources necessary for market research and provides them to the terminal.

[0718] 6. Progression and communication support

[0719] The device displays the dashboard and person in charge A updates the progress.

[0720] All stakeholders can see progress in real time and provide comments and feedback as needed.

[0721] This system provides an environment in which users can perform their work efficiently and make the most of opportunities for growth. In addition, incorporating an emotion engine enables flexible task management that takes into account the user's emotional state, which is expected to reduce work stress.

[0722] The processing flow will be explained below.

[0723] Step 1:

[0724] The user inputs a task via a terminal, for example, "conduct market research for a new product."

[0725] Step 2:

[0726] The device accepts the input task and sends it to the server. At the same time, the device sends the user's input and actions to the emotion engine, which analyzes the user's emotional state.

[0727] Step 3:

[0728] The emotion engine analyzes the user's input and behavioral patterns to recognize the emotions the user is currently feeling (e.g., stress, elation, etc.).

[0729] Step 4:

[0730] The server receives the task and begins analyzing it with a natural language processing engine, extracting keywords and context (e.g., "new product," "market research") from the task content.

[0731] Step 5:

[0732] The server queries a related database to collect similar tasks and related resources based on the extracted keywords.

[0733] Step 6:

[0734] The server checks the user profile database and analyzes each user's skill set, current workload, and past performance data.

[0735] Step 7:

[0736] The server selects the most suitable agent based on the analytical data and the results of the emotion engine. For example, it recommends Agent A, who has extensive experience in market research and is currently under low stress.

[0737] Step 8:

[0738] The server generates the reason for recommending agent A and sends this information to the terminal. The terminal displays a list of recommended agents and the reason.

[0739] Step 9:

[0740] The server automatically generates specific task instructions based on the task content. The instructions are adjusted to be more user-friendly, taking into account the results of the emotion engine. For example, it generates specific steps such as "First, research competing products, then analyze market trends."

[0741] Step 10:

[0742] The server generates specific task instructions and sends them to the device, where they are displayed and viewed by the user.

[0743] Step 11:

[0744] The server identifies the resources needed to complete the task and generates links to access them, such as survey templates and online research tools.

[0745] Step 12:

[0746] The server sends these resource links to the terminal, which displays the access links and their descriptions.

[0747] Step 13:

[0748] The device checks the recommended agent and automatically generated instructions. When agent A accepts the task, the status is sent from the device to the server.

[0749] Step 14:

[0750] The server tracks the progress of tasks in real time and collects progress data, which is then reflected in the work progress management dashboard.

[0751] Step 15:

[0752] The device displays a progress management dashboard, allowing all stakeholders to see the progress and provide comments and feedback.

[0753] Step 16:

[0754] Users communicate in real time through the dashboard to provide any necessary coordination or assistance.

[0755] Example 2

[0756] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0757] Conventional task management systems assign tasks without considering the user's emotional state, which increases work stress and pressure, potentially leading to reduced productivity and mental exhaustion. Furthermore, the recommendation of appropriate personnel and the generation of specific task instructions are not sufficiently automated, resulting in reduced management efficiency and difficulty in transparent work progress. There is a need to solve these problems and realize flexible task management that takes the user's emotional state into account.

[0758] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0759] In this invention, the server includes: means for providing a user interface for inputting tasks; means for analyzing the input tasks using natural language processing technology; means for recommending appropriate personnel based on the analyzed tasks and the user's skill set, workload, and past performance data; means for automatically generating specific task instructions for the recommended personnel; means for identifying and providing resources necessary to perform the tasks; means for incorporating an emotion engine that recognizes the user's emotional state and optimizes task management based thereon; and means for tracking task progress in real time and providing a dashboard that supports communication between parties involved. This enables flexible and efficient task management that takes the user's emotional state into consideration, thereby reducing work stress and improving productivity.

[0760] A "user interface" is an interface through which a user accesses a system to input tasks or obtain information.

[0761] "Natural language processing technology" is a technology for analyzing and understanding natural human language.

[0762] "User skill set" is a collective term for the skills, knowledge, and experience possessed by a particular user.

[0763] "Workload" refers to the amount and complexity of tasks currently being handled by each user.

[0764] "Past performance data" refers to data on the results and evaluations of tasks that each user has performed in the past.

[0765] "Rep recommendation" is the process of selecting the most suitable representative based on the user profile database.

[0766] "Automatic generation of task instructions" refers to automatically creating specific instructions based on task content and goals.

[0767] "Providing resources" means providing users with the tools, data, and templates necessary to complete a task.

[0768] The "emotion engine" is part of a system that recognizes the user's emotional state through analysis of their facial expressions and voice, and reflects this in task management.

[0769] A "dashboard" is an interface that displays task progress and related information in real time and supports communication between stakeholders.

[0770] This invention is a system that reduces excessive task pressure in the workplace and supports efficient and transparent work execution. In particular, it aims to reduce work stress by incorporating an emotion engine that recognizes the user's emotions and optimizes task management based on those emotions. Specific embodiments for implementing this invention are described below.

[0771] Overall system configuration

[0772] The system mainly consists of the following components:

[0773] 1. User Interface

[0774] 2. Natural Language Processing Engine (NLP Engine)

[0775] 3. User Profile Database (DB)

[0776] 4. Task Recommendation Engine

[0777] 5. Task Instruction Generation Engine

[0778] 6. Resource Management System

[0779] 7. Work progress management dashboard

[0780] 8. Emotion Engine

[0781] Hardware and software used

[0782] To realize this system, the following hardware and software are used.

[0783] Device: The device (computer, tablet, smartphone, etc.) through which the user enters the task.

[0784] Server: A device that analyzes tasks, recommends task managers, generates task instructions, tracks progress, etc. It is equipped with a high-performance CPU and memory.

[0785] Camera and microphone: Used as input devices to analyze the user's emotions.

[0786] NLP engine: Software that analyzes text. Specifically, it uses the Python library Natural Language Toolkit (NLTK) and SpaCy.

[0787] Emotion engine: Software for analyzing the user's facial expressions and voice. Specifically, it uses OpenCV, DeepFace, and the Google Speech-to-Text API for voice recognition.

[0788] Specific operation of the system

[0789] Task input and emotion recognition

[0790] The user inputs a task into the system via a terminal. For example, the user inputs an instruction such as "conduct market research for a new product." The terminal then sends this input to the server. At the same time, the server analyzes the user's current emotional state using a camera and microphone connected to the terminal. As a result, the server recognizes information such as "the user is excited."

[0791] Task Analysis

[0792] The server analyzes the received task using a natural language processing engine. It uses NLP engines such as NLTK and SpaCy to extract keywords and context from the input text. It then queries a related database to retrieve similar tasks and reference materials. For example, keywords such as "new product" and "market research" are extracted.

[0793] Recommendation from a representative

[0794] The server refers to the user profile database and selects the most suitable agent based on each user's skill set, workload, and past performance data. This process also takes into account the results of the emotion engine. For example, it may recommend "agent A, who has extensive experience in market research and is currently under low stress." This recommendation information is sent to the terminal and can be viewed by the user.

[0795] Auto-generation of task instructions

[0796] The server automatically generates specific task instructions based on the task content and related goals. Taking into account the results of the emotion engine, the instructions are adjusted to be more user-friendly. For example, specific instructions such as "First, research competitor products, then analyze market trends" are generated. These instructions are then sent to the device.

[0797] Provision of necessary resources

[0798] The server identifies the resources needed for the task and provides links to them to the device, such as survey templates and links to online research tools, for quick access by the user.

[0799] Transparency in work progress and communication support

[0800] The device confirms the recommended agent and automatically generated instructions. After the agent accepts the task, the progress is tracked in real time by the server. The progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[0801] Specific prompt examples

[0802] "Conduct market research for new products"

[0803] "First, research competitor products, then analyze market trends."

[0804] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0805] Step 1: Enter your task

[0806] A user inputs a task into the system via a terminal. For example, the user inputs a specific task such as "conduct market research for a new product." This input is saved as text data on the terminal. The terminal then sends this input data to the server.

[0807] Input: Task input from user (text format)

[0808] Output: Task input data (sent to server)

[0809] Step 2: Recognize emotions

[0810] The device activates an emotion engine to analyze the user's input and behavior. The device collects the user's facial expressions and voice through the camera and microphone and sends the data to the emotion engine. The emotion engine uses image analysis software (OpenCV and DeepFace) and voice analysis software (Google Speech-to-Text API) to recognize the user's emotional state.

[0811] Input: User's facial expression data, voice data

[0812] Output: Emotional state (e.g., "high stress," "relaxed")

[0813] Step 3: Analyzing the task

[0814] The server analyzes the received task input data using a natural language processing engine (NLTK or SpaCy). The server performs morphological and contextual analysis to extract keywords and context from the input data. At the same time, the server queries a related database to retrieve similar tasks and reference materials.

[0815] Input: Task input data

[0816] Output: Extracted keywords (e.g., "new product," "market research"), related materials

[0817] Step 4: Recommend a Representative

[0818] The server refers to the user profile database and selects the most suitable agent based on each user's skill set, workload, and past performance data. The output information of the emotion engine is also taken into consideration, so for example, Agent A, who has extensive experience in market research and is currently under low stress, may be selected. The server generates the reason for the recommendation and sends it to the terminal.

[0819] Inputs: Skill set data, workload data, performance data, emotional state

[0820] Output: Recommender (e.g., Person A), reason for recommendation

[0821] Step 5: Auto-generate task instructions

[0822] The server automatically generates specific task instructions based on the task content and related goals. Taking into account the results of the emotion engine, the instructions are adjusted to be more user-friendly. For example, specific instructions such as "First, research competing products, then analyze market trends" are generated. These instructions are then sent to the device.

[0823] Input: Task content, goal, emotional state

[0824] Output: Specific task instructions (e.g., "Research competing products")

[0825] Step 6: Providing necessary resources

[0826] The server identifies the resources needed for the task and provides links to them to the device, such as survey templates and links to online research tools needed for market research, allowing users to quickly access them.

[0827] Input: Task details, required resource information

[0828] Output: Resource links (e.g., survey templates, online tools)

[0829] Step 7: Transparency and communication support for work progress

[0830] The device checks the recommended agent and automatically generated instructions, then begins the process of verifying whether the agent has accepted the task. After the agent accepts the task, the server tracks its progress in real time. The progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[0831] Input: Acceptance status of person in charge, task instructions

[0832] Output: Real-time progress, dashboard display

[0833] This allows users to manage tasks efficiently while taking their emotional state into account, reducing work stress and improving productivity.

[0834] (Application example 2)

[0835] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0836] Imbalances in workloads and increased work stress in factories can lead to reduced production efficiency and work errors. In particular, allocating tasks without considering the emotional state of robots and operators poses challenges in efficient work execution and in optimal production management. Furthermore, it is difficult to grasp the progress in real time, and effective communication support is lacking. Solutions to these issues are needed.

[0837] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0838] In this invention, the server includes: a means for providing a user interface for inputting tasks; a means for analyzing the input tasks using natural language processing; a means for recommending appropriate personnel based on the analyzed tasks and the user's skill set, workload, and past performance data; a means for automatically generating specific task instructions for the recommended personnel; a means for identifying and providing resources necessary to perform the tasks; a means for tracking task progress in real time and providing a dashboard to support communication between stakeholders; and a means for recognizing the emotional state of robots and optimally allocating tasks based on this. This enables even workload distribution within a factory and improves production efficiency. Furthermore, it also enables real-time progress monitoring and effective communication support.

[0839] "User interface" refers to the means and screen configuration for a user to input tasks into the system.

[0840] "Natural language processing technology" refers to the technology used to analyze the content of a task, and to extract keywords and context from the input text.

[0841] "Skill set" refers to the specific technical abilities and knowledge possessed by a user or robot.

[0842] "Workload" refers to the amount of work currently being done by a user or a robot.

[0843] "Performance Data" refers to data relating to the past work results and evaluations of a user or robot.

[0844] "Rep" refers to a person or robot that is assigned a specific task and is responsible for carrying it out.

[0845] "Task instructions" refer to instructions that explain specifically how to perform an assigned task.

[0846] "Resources" refer to the materials and tools needed to perform a task.

[0847] "Dashboard" refers to an interface for visually managing and displaying task progress and related information.

[0848] "Emotional state" refers to the current psychological state of the robot or user.

[0849] "Task recommendation engine" refers to algorithms and systems that recommend the most suitable person based on the analyzed task.

[0850] "Task allocation" refers to the process of appropriately assigning multiple tasks to each person in charge.

[0851] The present invention relates to a "factory workload management system" for resolving imbalances in workloads and increased work stress in factories. The system aims to recognize the emotional states of robots and operators and optimally allocate work tasks based on the recognition. Specific embodiments for carrying out the present invention will be described in detail below.

[0852] Overall system configuration

[0853] The system mainly consists of the following components:

[0854] 1. User interface: The means by which the user inputs the task.

[0855] 2. Natural language processing technology: A means of analyzing the content of the input task and extracting keywords and context.

[0856] 3. User profile database: A database that stores users' skill sets, workloads, and past performance data.

[0857] 4. Task recommendation engine: A means of recommending the most suitable person to handle a task based on the analyzed task.

[0858] 5. Task instruction generation engine: A means of automatically generating specific task instructions for recommended personnel.

[0859] 6. Resource Management System: A means of identifying and providing the resources needed to perform a task.

[0860] 7. Work Progress Management Dashboard: A means of tracking task progress in real time and supporting communication between stakeholders.

[0861] 8. Emotion engine: A means of recognizing the emotional state of the robot and optimally allocating tasks.

[0862] Hardware and Software Configuration

[0863] Hardware

[0864] Factory robots: Each robot is equipped with an emotion recognition sensor that can detect its emotional state in real time.

[0865] Central management server: Manages the entire system and processes data from each component.

[0866] software

[0867] Python language: A programming language for implementing task analysis and allocation algorithms.

[0868] Database management system (e.g., MySQL): stores and manages user profile data, task data, and resource data.

[0869] Emotion recognition software: Software for analyzing the emotional state of each robot.

[0870] System processing flow

[0871] The server receives task input from a user or automated system and processes it according to the following steps:

[0872] 1. Task Input and Emotion Recognition

[0873] The terminal inputs the task, and the emotion engine recognizes the robot's emotional state.

[0874] 2. Task Analysis

[0875] The server analyzes the task content using natural language processing technology and extracts relevant keywords and context.

[0876] 3. Recommendation of the person in charge

[0877] The task recommendation engine references a user profile database and recommends the best person based on skill set, workload, performance data, and emotional state.

[0878] 4. Automatic generation of task instructions

[0879] The server generates specific task instructions and notifies the person in charge.

[0880] 5. Identifying and Providing Resources

[0881] The server identifies and provides the resources needed for the task.

[0882] 6. Progression and communication support

[0883] A progress management dashboard tracks progress in real time and supports communication between stakeholders.

[0884] Specific examples

[0885] For example, if a robot is assigned the task of "conducting market research for a new product" in a factory, the emotion engine will classify the robot's emotional state as "happy," "neutral," or "stressed," and assign the task to the robot that is most suitable for the task. This will enable the equalization of workloads and improved production efficiency.

[0886] Prompt Sentence Examples

[0887] Design a system for optimal task allocation for factory robots based on each robot's emotional state and task load. Write a program in Python to create a flow for manually assigning the following tasks. Create a program that assigns tasks to the optimal robot and displays the final task load for each robot.

[0888] In this way, by using a system based on this invention, it is possible to evenly distribute the workload within a factory and improve production efficiency. It also makes it possible to allocate tasks taking into account the emotional state of the robot, which is expected to reduce work stress.

[0889] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0890] Step 1:

[0891] The terminal inputs a task and emotion recognition by the emotion engine begins. The user inputs a task into the terminal, such as "conduct market research for a new product." While receiving the input task, the emotion engine detects the robot's emotional state using the emotion recognition sensor. The input is the task content and the robot's current emotional state, and the output is task data and emotion data for analysis.

[0892] Step 2:

[0893] The server analyzes the task content using natural language processing technology. The server extracts keywords and context from the input task content, obtaining keywords such as "market research" and "new product." The input is the task data, and the output is the analyzed keywords and context information.

[0894] Step 3:

[0895] The server refers to the user profile database and recommends the most suitable agent using the task recommendation engine. The server selects the most suitable robot by taking into account the user's skill set, workload, past performance data, and emotional state. The input is keywords, context information, and information from the user profile database, and the output is a list of recommended agents.

[0896] Step 4:

[0897] The server automatically generates specific task instructions and notifies the person in charge. For example, instructions such as "First, research competing products, then analyze market trends" are generated. The input is the recommended person in charge and the task content, and the output is specific task instructions.

[0898] Step 5:

[0899] The server identifies and provides the resources needed for the task. For example, it collects survey templates and links to online research tools and provides them to the device. The input is specific task instructions, and the output is resource links.

[0900] Step 6:

[0901] The work progress management dashboard tracks progress in real time and supports communication between stakeholders. The person in charge updates the progress of the task, and all stakeholders can see it in real time. The input is progress data from the person in charge, and the output is dashboard information updated in real time.

[0902] The above processing steps enable the even distribution of work loads within the factory, improving production efficiency. It also enables task allocation that takes into account the emotional state of the robot, reducing stress during work and tasks.

[0903] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0904] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0905] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0906] [Third embodiment]

[0907] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0908] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0909] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0910] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0911] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0912] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0913] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0914] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0915] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0916] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0917] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0918] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0919] The system according to the present invention aims to reduce the excessive pressure of tasks in the workplace and to support efficient and transparent business execution. Hereinafter, an embodiment of the present invention will be described in detail.

[0920] Overall system configuration

[0921] The system mainly consists of the following components:

[0922] 1. User Interface

[0923] 2. Natural Language Processing Engine

[0924] 3. User Profile Database

[0925] 4. Task Recommendation Engine

[0926] 5. Task Instruction Generation Engine

[0927] 6. Resource Management System

[0928] 7. Work progress management dashboard

[0929] System processing flow

[0930] Task Input

[0931] A user inputs a task into the system via a terminal. For example, a specific task such as "conduct market research for a new product" is input. The terminal accepts this input and sends it to the server.

[0932] Task Analysis

[0933] The server analyzes the received task using a natural language processing engine. This analysis extracts keywords and context (e.g., "new product" or "market research") from the task content. The server then queries a related database to retrieve similar tasks and reference materials.

[0934] Recommendation from a representative

[0935] The server refers to a user profile database and selects the most suitable person based on each user's skill set, workload, and past performance data. For example, users with extensive market research experience are given priority in the recommendation. This recommendation information is sent to the terminal.

[0936] Auto-generation of task instructions

[0937] The server automatically generates specific task instructions based on the task content and related goals, such as "First, research competitive products, then analyze market trends." These instructions are sent to the device for review by the user.

[0938] Provision of necessary resources

[0939] The server identifies the resources needed for the task (e.g., survey templates and online research tools) and provides links to them to the device, allowing users to quickly access the required resources.

[0940] Transparency in work progress and communication support

[0941] The device confirms the recommended agent and automatically generated instructions. After the agent accepts the task, their progress is tracked in real time by the server. Progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[0942] Specific examples

[0943] 1. Enter the task

[0944] The user types "I want to conduct market research on a new product" into the terminal.

[0945] The terminal sends this to the server.

[0946] 2. Task Analysis

[0947] The server analyzes the task content using natural language processing and extracts keywords such as "new product" and "market research."

[0948] The server queries the relational database to obtain similar task information and resources.

[0949] 3. Recommendation of the person in charge

[0950] The server refers to the user's skill data and recommends agent A.

[0951] The server generates the reason for recommendation and displays it on the terminal.

[0952] 4. Generate task instructions

[0953] The server generates specific task instructions (e.g., "research competing products") and sends them to the device.

[0954] 5. Providing necessary resources

[0955] The server collects links to resources necessary for market research and provides them to the terminal.

[0956] 6. Progression and communication support

[0957] The device displays the dashboard and person in charge A updates the progress.

[0958] All stakeholders can see progress in real time and provide comments and feedback as needed.

[0959] This system provides an environment in which users can carry out their work efficiently and make the most of opportunities for growth. This series of processes reduces stress for users through automation and transparency, and has the effect of improving work productivity.

[0960] The processing flow will be explained below.

[0961] Step 1:

[0962] The user inputs a task via a terminal, for example, "conduct market research for a new product."

[0963] Step 2:

[0964] The device accepts the input task and sends it to the server. The sent data includes the task content and the user's ID.

[0965] Step 3:

[0966] The server receives the task and begins analyzing it using a natural language processing engine. The server extracts keywords and context (e.g., "new product," "market research") from the task content.

[0967] Step 4:

[0968] The server queries a related database to collect similar tasks and related resources based on the extracted keywords.

[0969] Step 5:

[0970] The server checks the user profile database and analyzes each user's skill set, current workload, and past performance data.

[0971] Step 6:

[0972] The server selects the most suitable person based on the analysis data. For example, it may recommend person A, who has extensive experience in market research.

[0973] Step 7:

[0974] The server generates the reason for recommending agent A and sends this information to the terminal. The terminal displays a list of recommended agents and the reason.

[0975] Step 8:

[0976] The server automatically generates specific task instructions based on the task content, such as "First, research competitor products, then analyze market trends."

[0977] Step 9:

[0978] The server generates specific task instructions and sends them to the device, where they are displayed and viewed by the user.

[0979] Step 10:

[0980] The server identifies the resources needed to complete the task and generates links to access them, such as survey templates and online research tools.

[0981] Step 11:

[0982] The server sends these resource links to the terminal, which displays the access links and their descriptions.

[0983] Step 12:

[0984] The device confirms the recommended agent and the automatically generated instructions. When Agent A accepts the task, a confirmation is sent from the device to the server.

[0985] Step 13:

[0986] The server tracks the progress of tasks in real time and collects progress data, which is then reflected in the work progress management dashboard.

[0987] Step 14:

[0988] The device displays a progress management dashboard, allowing all stakeholders to view progress, provide comments, and provide feedback.

[0989] Step 15:

[0990] Users communicate in real time through the dashboard to provide any necessary coordination or assistance.

[0991] Example 1

[0992] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0993] In conventional task management systems, task assignment and progress tracking are performed manually, resulting in low work efficiency and a lack of transparency. It is also difficult to select the right person for the task, often resulting in delays in providing appropriate resources. Furthermore, there is a lack of communication between stakeholders, which reduces work productivity. The purpose of this invention is to solve these problems and improve work efficiency and transparency.

[0994] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0995] In this invention, the server includes a means for analyzing tasks using natural language processing technology, a means for recommending an appropriate person to perform the task based on the user's ability set, workload, and past performance data, and a means for automatically generating specific task instructions. This enables efficient analysis of tasks, appropriate recommendation of a person to perform the task, and automatic generation of specific instructions. Furthermore, by including a terminal that tracks the progress of tasks in real time and supports information exchange between related parties, and a means for identifying and providing resources required to perform the tasks, the transparency and efficiency of work are improved.

[0996] A "terminal" is an electronic device used by a user to input tasks and check instructions and progress. This includes computers and smartphones.

[0997] A "server" is a central processing unit that executes multiple means, and is a device that is responsible for analyzing tasks, recommending personnel, automatically generating task instructions, providing resources, and tracking progress.

[0998] "Natural language processing technology" is a technology for analyzing the content of a task and extracting keywords and context, and includes machine learning models and text analysis algorithms.

[0999] The "user ability set" is data relating to the job capabilities and skills of each user, and is information used for task allocation and recommendation of personnel.

[1000] "Workload" is data about the amount of tasks each user currently has and ongoing projects.

[1001] "Past achievement data" is a history of tasks and projects that the user has completed in the past, and is data related to their evaluations and achievements.

[1002] "Task instructions" are instructions that indicate the specific steps or procedures that must be performed to accomplish a particular task.

[1003] "Resources" are information or items such as materials, tools, templates, links, etc. required to perform a task.

[1004] A "dashboard" is a visual interface that displays the progress of tasks in real time and supports information exchange among stakeholders.

[1005] The present invention is a system that aims to improve the efficiency and transparency of task management in a workplace environment. This system mainly consists of the following components: a terminal, a server, a natural language processing engine, a user profile database, a task recommendation engine, a task instruction generation engine, a resource management system, and a work progress management dashboard.

[1006] System Configuration

[1007] Terminal

[1008] Users use a device (such as a PC or smartphone) to input tasks and check their progress. The device provides a user interface and sends the input tasks to the server. The device also displays the information sent from the server to the user.

[1009] server

[1010] The server serves as the central hub of the entire system and fulfills multiple roles. The specific processing performed by the server is shown below.

[1011] Natural Language Processing Engine

[1012] When a task is input, the server first analyzes the task content using a natural language processing engine (e.g., TensorFlow or OpenNLP). This analysis extracts key keywords and context from the task. For example, if the task is "conduct market research for a new product," the keywords "new product" and "market research" are extracted.

[1013] User profile database and task recommendation engine

[1014] Based on the analyzed task content, the server references a user profile database, which stores each user's ability set, workload, and past performance data. Based on this information, the server recommends the person best suited to the task. For example, a user with extensive market research experience and a light current workload may be recommended. The recommendation results are displayed on the terminal.

[1015] Task Instruction Generation Engine

[1016] The server automatically generates specific task instructions based on the acquired task content and the recommended person in charge. For example, it may generate specific steps such as "research competing products, then analyze market trends." This automatically generated instruction is sent to the terminal and can be confirmed by the user.

[1017] Resource Management System

[1018] The server identifies the resources (e.g., survey templates and online research tools) needed to complete the task and provides links to them to the device, allowing the user to quickly access the required resources. For example, specific resources such as "Market Research Template.xlsx" or "Access Link to Competitive Analysis Tool" can be included.

[1019] Business progress management dashboard

[1020] Users use a work progress management dashboard to check progress and communicate. The server tracks the progress of tasks in real time and displays it on the dashboard. After a task is accepted by a person in charge, the progress and related communications can be viewed by all parties on the dashboard. This ensures transparency of work and enables efficient information exchange.

[1021] Examples and prompts

[1022] Specific examples

[1023] Task Input

[1024] The user types "I want to conduct market research on a new product" into the terminal.

[1025] The terminal sends this to the server.

[1026] Task Analysis

[1027] The server uses a natural language processing engine to extract key keywords such as "new product" and "market research."

[1028] The server queries the relational database to obtain similar task information and resources.

[1029] Recommendation from a representative

[1030] The server refers to the user's skill data and recommends "users with extensive market research experience."

[1031] This information, along with the reason for the recommendation, is sent to the device.

[1032] Generate task instructions

[1033] The server generates specific task instructions (e.g., "research competing products") and sends them to the device.

[1034] Provision of necessary resources

[1035] The server identifies a resource such as "Market Research Template.xlsx" and provides it to the device.

[1036] Progression and communication support

[1037] The device displays progress on a dashboard, and the person in charge updates the progress as it happens.

[1038] All stakeholders can view and comment on progress and feedback in real time through a dashboard.

[1039] Prompt Sentence Examples

[1040] "I'd like to conduct market research for a new product. Please set the task to include researching competitive products and analyzing market trends."

[1041] "What are the specific steps I should take to start researching competitive products and then analyzing market trends?"

[1042] The system of the present invention provides an environment in which users can perform their work efficiently and maximize opportunities for growth. The aim is to reduce user stress through automation and transparency and improve work productivity.

[1043] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1044] Step 1:

[1045] The user inputs a task using a terminal. Specifically, the user inputs the task content (e.g., "Conduct market research for a new product") in text format through the terminal's user interface. The terminal then sends this input content to the server. The input data is the task content in natural language format and is passed to the server.

[1046] Step 2:

[1047] The server receives the task content and analyzes it using a natural language processing engine (e.g., TensorFlow or OpenNLP). Specifically, it extracts key keywords (e.g., "new product," "market research") and contextual information from the task text. The input data is the task content in text format, and the output data is the extracted keywords and contextual information.

[1048] Step 3:

[1049] The server queries the user profile database based on the extracted keywords and context information to obtain information such as past performance data, workload, and skill sets. The server analyzes this data and recommends the most suitable agent for the task. The input data are the extracted keywords and user profile information, and the output data are the recommended agent and the reason for the recommendation.

[1050] Step 4:

[1051] The server automatically generates specific task instructions for the recommended personnel. Specific steps (e.g., "Start researching competitive products, then analyze market trends") are automatically created based on predefined templates and past task instructions. The input data is the task content and information on the recommended personnel, and the output data is specific task instructions.

[1052] Step 5:

[1053] The server identifies the resources required to execute the task and provides the terminal with links and materials. Specifically, it collects research tools and templates (e.g., "Market Research Template.xlsx") and generates access links to them. The input data is the task content and resource information, and the output data is the links and materials for the required resources.

[1054] Step 6:

[1055] The user confirms the recommended agent and specific task instructions via the terminal. The agent accepts the task, and the server tracks its progress in real time. The progress is displayed on the terminal's work progress management dashboard, allowing all parties involved to check the progress and provide comments and feedback as needed. The input data is the ongoing task information, and the output data is the progress and feedback updated in real time.

[1056] Through these series of processing steps, the system can achieve efficient management and transparency of tasks, reducing the burden on users.

[1057] (Application example 1)

[1058] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1059] In modern factory operations, task allocation and progress management have become increasingly complex, making it difficult to carry out work efficiently. While there is also a need to maximize the capabilities of robots and deploy them in the right positions, current systems are unable to fully achieve this. This leads to uneven workloads within the factory, reducing the productivity of the manufacturing process.

[1060] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1061] In this invention, the server includes means for providing an operation screen for inputting tasks, means for analyzing the input tasks using natural language processing technology, means for recommending appropriate workers based on the analyzed tasks and on the user's capabilities, workload, and past execution data, means for automatically generating specific task instructions for the recommended workers, means for identifying and providing resources necessary for executing the tasks, means for tracking the progress of tasks in real time and providing a management screen that supports communication between related parties, means for considering the capabilities of robots operating in the factory when selecting and recommending workers, and means for automatically generating specific work instructions for the recommended robots. This enables efficient task allocation and progress management, thereby achieving equalization of workloads within the factory and improved productivity.

[1062] An "operation screen" is a display screen that provides an interface for a user to input a task.

[1063] "Natural language processing technology" is a technology for analyzing and understanding documents written in human language.

[1064] A "task" is an activity or task performed to achieve a specific goal.

[1065] "User" refers to the person or administrator who operates the system and inputs tasks.

[1066] "Ability" refers to the technical skills and knowledge possessed by a user or robot.

[1067] "Workload" refers to the amount of work a worker currently has and the state of their work.

[1068] "Execution data" is data that records the performance and results of tasks performed in the past.

[1069] "Worker" refers to a human or robot that performs the tasks recommended by the system.

[1070] "Task instructions" refer to instructions that show the specific steps and methods for executing a task.

[1071] "Resources" refer to things such as tools and materials needed to perform a task.

[1072] The "management screen" is an interface for tracking the progress of tasks in real time and sharing information among stakeholders.

[1073] "Communication" refers to the exchange of information or data between parties.

[1074] "Recommendation" refers to the system selecting and suggesting appropriate workers or robots.

[1075] "Factory robots" refer to mechanical devices that actually operate in a factory environment and perform specific tasks.

[1076] The system of the present invention is a program for managing tasks within a factory, and is implemented using the following hardware and software.

[1077] Program processing explanation

[1078] 1. Task Input Module:

[1079] The server provides a user interface for entering tasks. The interface runs on a tablet or personal computer and displays a form that allows users to enter tasks. The form includes input fields for task details, assignee assignments, and so on.

[1080] 2. Task Analysis Module:

[1081] The server analyzes the input task content using natural language processing technology. Specifically, it uses natural language processing engines such as spaCy and TensorFlow to extract keywords and context from the task content. Even if the task content is ambiguous, it analyzes the context and takes appropriate action.

[1082] 3. Agent Recommendation Module:

[1083] The server then refers to a user profile database based on the analyzed task information and recommends the appropriate worker. The database contains information about each user's abilities, workload, and past performance data, and the server selects the most suitable worker based on this information. Recommendations may also be made based on the capabilities of the robots operating in the factory.

[1084] 4. Task instruction generation module:

[1085] The server automatically generates specific task instructions for the recommended workers and robots. These instructions include the specific steps and necessary work processes for the task. For example, a specific instruction such as "pick out part A and perform welding" may be generated.

[1086] 5. Resource Provision Module:

[1087] The server identifies and provides the resources needed to perform a task, including links to the necessary tools and materials for quick access by users and robots.

[1088] 6. Progress Management Module:

[1089] The server monitors the progress of tasks in real time and supports communication between stakeholders through a management interface that includes a progress timeline, progress progress, and feedback functionality.

[1090] Examples and prompts

[1091] Examples:

[1092] 1. The user enters "Assemble part A" into the tablet device.

[1093] 2. The server analyzes the task content using natural language processing and extracts the keywords "Part A" and "assembly."

[1094] 3. Based on the analyzed information, the server refers to the user profile database and recommends workers and robots with extensive experience in assembling part A.

[1095] 4. The server automatically generates specific instructions, such as "pick up part A and weld it," and sends them to the recommended worker or robot.

[1096] 5. The server provides the necessary resources, such as the welding tool and the location information of part A.

[1097] 6. The administrator checks the progress on the management screen and provides feedback as needed.

[1098] Example prompt sentence:

[1099] Here's a new task: "Assemble part A." Please use a powerful natural language processing engine to analyze it and assign it to the appropriate robot. Please also automatically generate specific task instructions and required resource information.

[1100] This enables efficient task allocation and progress management, leading to equalized workloads within the factory and improved productivity.

[1101] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1102] Step 1:

[1103] The user opens an operation screen on a tablet device or personal computer for entering tasks. Here, the user enters task details, such as "Assemble part A." The input data includes the task content, the person in charge, the deadline, etc. The entered information is sent to the server via the API.

[1104] Step 2:

[1105] The server analyzes the received task content using natural language processing technology. Specifically, it uses a natural language processing engine (e.g., spaCy or TensorFlow) to extract keywords and context from the task content. At this stage, important keywords such as "Part A" and "assembly" are identified. The analysis results are used as input data to query a relational database.

[1106] Step 3:

[1107] Based on the analysis results, the server queries a relational database to collect information on similar tasks and the resources required. The database stores information on successful and unsuccessful cases of similar tasks, as well as information on the tools used. The query results are further processed and output as information on task execution.

[1108] Step 4:

[1109] Based on the analyzed task information, the server refers to a user profile database and recommends appropriate workers. The user profile database contains information on each worker's capabilities, workload, and past performance data. The capabilities of the robots operating in the factory are also taken into consideration. The selected workers and robots are output as a recommendation list.

[1110] Step 5:

[1111] The server automatically generates specific task instructions for the most suitable workers and robots based on the recommendation list. A template-based generation system is used to create instructions that indicate specific work procedures and required processes. For example, instructions such as "pick out part A and perform welding" are included. The generated task instructions are then sent to the workers and robots.

[1112] Step 6:

[1113] The server identifies and provides the resources needed to perform a task. These resources include information on the tools and materials needed. Links and location information are also provided, allowing workers and robots to quickly access them. This allows for efficient use of resources.

[1114] Step 7:

[1115] The server monitors the progress of tasks in real time and supports communication between stakeholders through a control screen that includes a progress timeline, progress progress, and feedback functions. The progress of workers and robots is updated, and stakeholders can check their respective status and provide instructions or feedback as needed.

[1116] Through this series of steps, tasks can be efficiently assigned and progress managed, resulting in equalized workloads within the factory and improved productivity.

[1117] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1118] The system according to the present invention aims to reduce the excessive pressure of tasks in the workplace and support efficient and transparent work execution. It also incorporates an emotion engine that recognizes the user's emotions and optimizes task management based on the emotions. Hereinafter, the embodiments of the present invention will be described in detail.

[1119] Overall system configuration

[1120] The system mainly consists of the following components:

[1121] 1. User Interface

[1122] 2. Natural Language Processing Engine

[1123] 3. User Profile Database

[1124] 4. Task Recommendation Engine

[1125] 5. Task Instruction Generation Engine

[1126] 6. Resource Management System

[1127] 7. Work progress management dashboard

[1128] 8. Emotion Engine

[1129] System processing flow

[1130] Task input and emotion recognition

[1131] A user inputs a task into the system via a terminal. For example, a specific task such as "conduct market research for a new product" is input. The terminal accepts this input, and at the same time, an emotion engine is activated to analyze the user's input and behavior. The emotion engine recognizes the user's current emotional state (e.g., stress, elation, etc.).

[1132] Task Analysis

[1133] The server analyzes the received task using a natural language processing engine. This analysis extracts keywords and context (e.g., "new product" or "market research") from the task content. The server then queries a related database to retrieve similar tasks and reference materials.

[1134] Recommendation from a representative

[1135] The server references the user profile database and selects the most suitable agent based on each user's skill set, workload, and past performance data. The results of the emotion engine are also reflected in this process. For example, Agent A, who has extensive experience in market research and is currently under low stress, may be recommended. This recommendation information is sent to the terminal.

[1136] Auto-generation of task instructions

[1137] The server automatically generates specific task instructions based on the task content and related goals. The instructions are adjusted to suit the user's needs, taking into account the results of the emotion engine. For example, instructions can be flexibly adjusted according to the user's emotional state, such as "First, research competing products, then analyze market trends."

[1138] Provision of necessary resources

[1139] The server identifies the resources needed for the task (e.g., survey templates and online research tools) and provides links to them to the device, allowing users to quickly access the required resources.

[1140] Transparency in work progress and communication support

[1141] The device confirms the recommended agent and automatically generated instructions. After the agent accepts the task, their progress is tracked in real time by the server. Progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[1142] Specific examples

[1143] 1. Task Input and Emotion Recognition

[1144] The user types "I want to conduct market research on a new product" into the terminal.

[1145] Along with this task, the device also analyzes the user's input and uses an emotion engine to recognize the user's emotional state.

[1146] 2. Task Analysis

[1147] The server analyzes the task content using natural language processing and extracts keywords such as "new product" and "market research."

[1148] The server queries the relational database to obtain similar task information and resources.

[1149] 3. Recommendation of the person in charge

[1150] The server refers to the user's skill data and the results of the emotion engine and recommends agent A.

[1151] The server generates the reason for recommendation and displays it on the terminal.

[1152] 4. Generate task instructions

[1153] The server generates specific task instructions (e.g., "Research competing products") and sends them to the device, reflecting the results of the emotion engine.

[1154] 5. Providing necessary resources

[1155] The server collects links to resources necessary for market research and provides them to the terminal.

[1156] 6. Progression and communication support

[1157] The device displays the dashboard and person in charge A updates the progress.

[1158] All stakeholders can see progress in real time and provide comments and feedback as needed.

[1159] This system provides an environment in which users can perform their work efficiently and make the most of opportunities for growth. In addition, incorporating an emotion engine enables flexible task management that takes into account the user's emotional state, which is expected to reduce work stress.

[1160] The processing flow will be explained below.

[1161] Step 1:

[1162] The user inputs a task via a terminal, for example, "conduct market research for a new product."

[1163] Step 2:

[1164] The device accepts the input task and sends it to the server. At the same time, the device sends the user's input and actions to the emotion engine, which analyzes the user's emotional state.

[1165] Step 3:

[1166] The emotion engine analyzes the user's input and behavioral patterns to recognize the emotions the user is currently feeling (e.g., stress, elation, etc.).

[1167] Step 4:

[1168] The server receives the task and begins analyzing it with a natural language processing engine, extracting keywords and context (e.g., "new product," "market research") from the task content.

[1169] Step 5:

[1170] The server queries a related database to collect similar tasks and related resources based on the extracted keywords.

[1171] Step 6:

[1172] The server checks the user profile database and analyzes each user's skill set, current workload, and past performance data.

[1173] Step 7:

[1174] The server selects the most suitable agent based on the analytical data and the results of the emotion engine. For example, it recommends Agent A, who has extensive experience in market research and is currently under low stress.

[1175] Step 8:

[1176] The server generates the reason for recommending agent A and sends this information to the terminal. The terminal displays a list of recommended agents and the reason.

[1177] Step 9:

[1178] The server automatically generates specific task instructions based on the task content. The instructions are adjusted to be more user-friendly, taking into account the results of the emotion engine. For example, it generates specific steps such as "First, research competing products, then analyze market trends."

[1179] Step 10:

[1180] The server generates specific task instructions and sends them to the device, where they are displayed and viewed by the user.

[1181] Step 11:

[1182] The server identifies the resources needed to complete the task and generates links to access them, such as survey templates and online research tools.

[1183] Step 12:

[1184] The server sends these resource links to the terminal, which displays the access links and their descriptions.

[1185] Step 13:

[1186] The device checks the recommended agent and automatically generated instructions. When agent A accepts the task, the status is sent from the device to the server.

[1187] Step 14:

[1188] The server tracks the progress of tasks in real time and collects progress data, which is then reflected in the work progress management dashboard.

[1189] Step 15:

[1190] The device displays a progress management dashboard, allowing all stakeholders to see the progress and provide comments and feedback.

[1191] Step 16:

[1192] Users communicate in real time through the dashboard to provide any necessary coordination or assistance.

[1193] Example 2

[1194] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1195] Conventional task management systems assign tasks without considering the user's emotional state, which increases work stress and pressure, potentially leading to reduced productivity and mental exhaustion. Furthermore, the recommendation of appropriate personnel and the generation of specific task instructions are not sufficiently automated, resulting in reduced management efficiency and difficulty in transparent work progress. There is a need to solve these problems and realize flexible task management that takes the user's emotional state into account.

[1196] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1197] In this invention, the server includes: means for providing a user interface for inputting tasks; means for analyzing the input tasks using natural language processing technology; means for recommending appropriate personnel based on the analyzed tasks and the user's skill set, workload, and past performance data; means for automatically generating specific task instructions for the recommended personnel; means for identifying and providing resources necessary to perform the tasks; means for incorporating an emotion engine that recognizes the user's emotional state and optimizes task management based thereon; and means for tracking task progress in real time and providing a dashboard that supports communication between parties involved. This enables flexible and efficient task management that takes the user's emotional state into consideration, thereby reducing work stress and improving productivity.

[1198] A "user interface" is an interface through which a user accesses a system to input tasks or obtain information.

[1199] "Natural language processing technology" is a technology for analyzing and understanding natural human language.

[1200] "User skill set" is a collective term for the skills, knowledge, and experience possessed by a particular user.

[1201] "Workload" refers to the amount and complexity of tasks currently being handled by each user.

[1202] "Past performance data" refers to data on the results and evaluations of tasks that each user has performed in the past.

[1203] "Rep recommendation" is the process of selecting the most suitable representative based on the user profile database.

[1204] "Automatic generation of task instructions" refers to automatically creating specific instructions based on task content and goals.

[1205] "Providing resources" means providing users with the tools, data, and templates necessary to complete a task.

[1206] The "emotion engine" is part of a system that recognizes the user's emotional state through analysis of their facial expressions and voice, and reflects this in task management.

[1207] A "dashboard" is an interface that displays task progress and related information in real time and supports communication between stakeholders.

[1208] This invention is a system that reduces excessive task pressure in the workplace and supports efficient and transparent work execution. In particular, it aims to reduce work stress by incorporating an emotion engine that recognizes the user's emotions and optimizes task management based on those emotions. Specific embodiments for implementing this invention are described below.

[1209] Overall system configuration

[1210] The system mainly consists of the following components:

[1211] 1. User Interface

[1212] 2. Natural Language Processing Engine (NLP Engine)

[1213] 3. User Profile Database (DB)

[1214] 4. Task Recommendation Engine

[1215] 5. Task Instruction Generation Engine

[1216] 6. Resource Management System

[1217] 7. Work progress management dashboard

[1218] 8. Emotion Engine

[1219] Hardware and software used

[1220] To realize this system, the following hardware and software are used.

[1221] Device: The device (computer, tablet, smartphone, etc.) through which the user enters the task.

[1222] Server: A device that analyzes tasks, recommends task managers, generates task instructions, tracks progress, etc. It is equipped with a high-performance CPU and memory.

[1223] Camera and microphone: Used as input devices to analyze the user's emotions.

[1224] NLP engine: Software that analyzes text. Specifically, it uses the Python library Natural Language Toolkit (NLTK) and SpaCy.

[1225] Emotion engine: Software for analyzing the user's facial expressions and voice. Specifically, it uses OpenCV, DeepFace, and the Google Speech-to-Text API for voice recognition.

[1226] Specific operation of the system

[1227] Task input and emotion recognition

[1228] The user inputs a task into the system via a terminal. For example, the user inputs an instruction such as "conduct market research for a new product." The terminal then sends this input to the server. At the same time, the server analyzes the user's current emotional state using a camera and microphone connected to the terminal. As a result, the server recognizes information such as "the user is excited."

[1229] Task Analysis

[1230] The server analyzes the received task using a natural language processing engine. It uses NLP engines such as NLTK and SpaCy to extract keywords and context from the input text. It then queries a related database to retrieve similar tasks and reference materials. For example, keywords such as "new product" and "market research" are extracted.

[1231] Recommendation from a representative

[1232] The server refers to the user profile database and selects the most suitable agent based on each user's skill set, workload, and past performance data. This process also takes into account the results of the emotion engine. For example, it may recommend "agent A, who has extensive experience in market research and is currently under low stress." This recommendation information is sent to the terminal and can be viewed by the user.

[1233] Auto-generation of task instructions

[1234] The server automatically generates specific task instructions based on the task content and related goals. Taking into account the results of the emotion engine, the instructions are adjusted to be more user-friendly. For example, specific instructions such as "First, research competitor products, then analyze market trends" are generated. These instructions are then sent to the device.

[1235] Provision of necessary resources

[1236] The server identifies the resources needed for the task and provides links to them to the device, such as survey templates and links to online research tools, for quick access by the user.

[1237] Transparency in work progress and communication support

[1238] The device confirms the recommended agent and automatically generated instructions. After the agent accepts the task, the progress is tracked in real time by the server. The progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[1239] Specific prompt examples

[1240] "Conduct market research for new products"

[1241] "First, research competitor products, then analyze market trends."

[1242] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1243] Step 1: Enter your task

[1244] A user inputs a task into the system via a terminal. For example, the user inputs a specific task such as "conduct market research for a new product." This input is saved as text data on the terminal. The terminal then sends this input data to the server.

[1245] Input: Task input from user (text format)

[1246] Output: Task input data (sent to server)

[1247] Step 2: Recognize emotions

[1248] The device activates an emotion engine to analyze the user's input and behavior. The device collects the user's facial expressions and voice through the camera and microphone and sends the data to the emotion engine. The emotion engine uses image analysis software (OpenCV and DeepFace) and voice analysis software (Google Speech-to-Text API) to recognize the user's emotional state.

[1249] Input: User's facial expression data, voice data

[1250] Output: Emotional state (e.g., "high stress," "relaxed")

[1251] Step 3: Analyzing the task

[1252] The server analyzes the received task input data using a natural language processing engine (NLTK or SpaCy). The server performs morphological and contextual analysis to extract keywords and context from the input data. At the same time, the server queries a related database to retrieve similar tasks and reference materials.

[1253] Input: Task input data

[1254] Output: Extracted keywords (e.g., "new product," "market research"), related materials

[1255] Step 4: Recommend a Representative

[1256] The server refers to the user profile database and selects the most suitable agent based on each user's skill set, workload, and past performance data. The output information of the emotion engine is also taken into consideration, so for example, Agent A, who has extensive experience in market research and is currently under low stress, may be selected. The server generates the reason for the recommendation and sends it to the terminal.

[1257] Inputs: Skill set data, workload data, performance data, emotional state

[1258] Output: Recommender (e.g., Person A), reason for recommendation

[1259] Step 5: Auto-generate task instructions

[1260] The server automatically generates specific task instructions based on the task content and related goals. Taking into account the results of the emotion engine, the instructions are adjusted to be more user-friendly. For example, specific instructions such as "First, research competing products, then analyze market trends" are generated. These instructions are then sent to the device.

[1261] Input: Task content, goal, emotional state

[1262] Output: Specific task instructions (e.g., "Research competing products")

[1263] Step 6: Providing necessary resources

[1264] The server identifies the resources needed for the task and provides links to them to the device, such as survey templates and links to online research tools needed for market research, allowing users to quickly access them.

[1265] Input: Task details, required resource information

[1266] Output: Resource links (e.g., survey templates, online tools)

[1267] Step 7: Transparency and communication support for work progress

[1268] The device checks the recommended agent and automatically generated instructions, then begins the process of verifying whether the agent has accepted the task. After the agent accepts the task, the server tracks its progress in real time. The progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[1269] Input: Acceptance status of person in charge, task instructions

[1270] Output: Real-time progress, dashboard display

[1271] This allows users to manage tasks efficiently while taking their emotional state into account, reducing work stress and improving productivity.

[1272] (Application example 2)

[1273] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1274] Imbalances in workloads and increased work stress in factories can lead to reduced production efficiency and work errors. In particular, allocating tasks without considering the emotional state of robots and operators poses challenges in efficient work execution and in optimal production management. Furthermore, it is difficult to grasp the progress in real time, and effective communication support is lacking. Solutions to these issues are needed.

[1275] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1276] In this invention, the server includes: a means for providing a user interface for inputting tasks; a means for analyzing the input tasks using natural language processing; a means for recommending appropriate personnel based on the analyzed tasks and the user's skill set, workload, and past performance data; a means for automatically generating specific task instructions for the recommended personnel; a means for identifying and providing resources necessary to perform the tasks; a means for tracking task progress in real time and providing a dashboard to support communication between stakeholders; and a means for recognizing the emotional state of robots and optimally allocating tasks based on this. This enables even workload distribution within a factory and improves production efficiency. Furthermore, it also enables real-time progress monitoring and effective communication support.

[1277] "User interface" refers to the means and screen configuration for a user to input tasks into the system.

[1278] "Natural language processing technology" refers to the technology used to analyze the content of a task, and to extract keywords and context from the input text.

[1279] "Skill set" refers to the specific technical abilities and knowledge possessed by a user or robot.

[1280] "Workload" refers to the amount of work currently being done by a user or a robot.

[1281] "Performance Data" refers to data relating to the past work results and evaluations of a user or robot.

[1282] "Rep" refers to a person or robot that is assigned a specific task and is responsible for carrying it out.

[1283] "Task instructions" refer to instructions that explain specifically how to perform an assigned task.

[1284] "Resources" refer to the materials and tools needed to perform a task.

[1285] "Dashboard" refers to an interface for visually managing and displaying task progress and related information.

[1286] "Emotional state" refers to the current psychological state of the robot or user.

[1287] "Task recommendation engine" refers to algorithms and systems that recommend the most suitable person based on the analyzed task.

[1288] "Task allocation" refers to the process of appropriately assigning multiple tasks to each person in charge.

[1289] The present invention relates to a "factory workload management system" for resolving imbalances in workloads and increased work stress in factories. The system aims to recognize the emotional states of robots and operators and optimally allocate work tasks based on the recognition. Specific embodiments for carrying out the present invention will be described in detail below.

[1290] Overall system configuration

[1291] The system mainly consists of the following components:

[1292] 1. User interface: The means by which the user inputs the task.

[1293] 2. Natural language processing technology: A means of analyzing the content of the input task and extracting keywords and context.

[1294] 3. User profile database: A database that stores users' skill sets, workloads, and past performance data.

[1295] 4. Task recommendation engine: A means of recommending the most suitable person to handle a task based on the analyzed task.

[1296] 5. Task instruction generation engine: A means of automatically generating specific task instructions for recommended personnel.

[1297] 6. Resource Management System: A means of identifying and providing the resources needed to perform a task.

[1298] 7. Work Progress Management Dashboard: A means of tracking task progress in real time and supporting communication between stakeholders.

[1299] 8. Emotion engine: A means of recognizing the emotional state of the robot and optimally allocating tasks.

[1300] Hardware and Software Configuration

[1301] Hardware

[1302] Factory robots: Each robot is equipped with an emotion recognition sensor that can detect its emotional state in real time.

[1303] Central management server: Manages the entire system and processes data from each component.

[1304] software

[1305] Python language: A programming language for implementing task analysis and allocation algorithms.

[1306] Database management system (e.g., MySQL): stores and manages user profile data, task data, and resource data.

[1307] Emotion recognition software: Software for analyzing the emotional state of each robot.

[1308] System processing flow

[1309] The server receives task input from a user or automated system and processes it according to the following steps:

[1310] 1. Task Input and Emotion Recognition

[1311] The terminal inputs the task, and the emotion engine recognizes the robot's emotional state.

[1312] 2. Task Analysis

[1313] The server analyzes the task content using natural language processing technology and extracts relevant keywords and context.

[1314] 3. Recommendation of the person in charge

[1315] The task recommendation engine references a user profile database and recommends the best person based on skill set, workload, performance data, and emotional state.

[1316] 4. Automatic generation of task instructions

[1317] The server generates specific task instructions and notifies the person in charge.

[1318] 5. Identifying and Providing Resources

[1319] The server identifies and provides the resources needed for the task.

[1320] 6. Progression and communication support

[1321] A progress management dashboard tracks progress in real time and supports communication between stakeholders.

[1322] Specific examples

[1323] For example, if a robot is assigned the task of "conducting market research for a new product" in a factory, the emotion engine will classify the robot's emotional state as "happy," "neutral," or "stressed," and assign the task to the robot that is most suitable for the task. This will enable the equalization of workloads and improved production efficiency.

[1324] Prompt Sentence Examples

[1325] Design a system for optimal task allocation for factory robots based on each robot's emotional state and task load. Write a program in Python to create a flow for manually assigning the following tasks. Create a program that assigns tasks to the optimal robot and displays the final task load for each robot.

[1326] In this way, by using a system based on this invention, it is possible to evenly distribute the workload within a factory and improve production efficiency. It also makes it possible to allocate tasks taking into account the emotional state of the robot, which is expected to reduce work stress.

[1327] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1328] Step 1:

[1329] The terminal inputs a task and emotion recognition by the emotion engine begins. The user inputs a task into the terminal, such as "conduct market research for a new product." While receiving the input task, the emotion engine detects the robot's emotional state using the emotion recognition sensor. The input is the task content and the robot's current emotional state, and the output is task data and emotion data for analysis.

[1330] Step 2:

[1331] The server analyzes the task content using natural language processing technology. The server extracts keywords and context from the input task content, obtaining keywords such as "market research" and "new product." The input is the task data, and the output is the analyzed keywords and context information.

[1332] Step 3:

[1333] The server refers to the user profile database and recommends the most suitable agent using the task recommendation engine. The server selects the most suitable robot by taking into account the user's skill set, workload, past performance data, and emotional state. The input is keywords, context information, and information from the user profile database, and the output is a list of recommended agents.

[1334] Step 4:

[1335] The server automatically generates specific task instructions and notifies the person in charge. For example, instructions such as "First, research competing products, then analyze market trends" are generated. The input is the recommended person in charge and the task content, and the output is specific task instructions.

[1336] Step 5:

[1337] The server identifies and provides the resources needed for the task. For example, it collects survey templates and links to online research tools and provides them to the device. The input is specific task instructions, and the output is resource links.

[1338] Step 6:

[1339] The work progress management dashboard tracks progress in real time and supports communication between stakeholders. The person in charge updates the progress of the task, and all stakeholders can see it in real time. The input is progress data from the person in charge, and the output is dashboard information updated in real time.

[1340] The above processing steps enable the even distribution of work loads within the factory, improving production efficiency. It also enables task allocation that takes into account the emotional state of the robot, reducing stress during work and tasks.

[1341] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1342] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1343] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1344] [Fourth embodiment]

[1345] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1346] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1347] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1348] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1349] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1350] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1351] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1352] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1353] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1354] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1355] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1356] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1357] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1358] The system according to the present invention aims to reduce the excessive pressure of tasks in the workplace and to support efficient and transparent business execution. Hereinafter, an embodiment of the present invention will be described in detail.

[1359] Overall system configuration

[1360] The system mainly consists of the following components:

[1361] 1. User Interface

[1362] 2. Natural Language Processing Engine

[1363] 3. User Profile Database

[1364] 4. Task Recommendation Engine

[1365] 5. Task Instruction Generation Engine

[1366] 6. Resource Management System

[1367] 7. Work progress management dashboard

[1368] System processing flow

[1369] Task Input

[1370] A user inputs a task into the system via a terminal. For example, a specific task such as "conduct market research for a new product" is input. The terminal accepts this input and sends it to the server.

[1371] Task Analysis

[1372] The server analyzes the received task using a natural language processing engine. This analysis extracts keywords and context (e.g., "new product" or "market research") from the task content. The server then queries a related database to retrieve similar tasks and reference materials.

[1373] Recommendation from a representative

[1374] The server refers to a user profile database and selects the most suitable person based on each user's skill set, workload, and past performance data. For example, users with extensive market research experience are given priority in the recommendation. This recommendation information is sent to the terminal.

[1375] Auto-generation of task instructions

[1376] The server automatically generates specific task instructions based on the task content and related goals, such as "First, research competitive products, then analyze market trends." These instructions are sent to the device for review by the user.

[1377] Provision of necessary resources

[1378] The server identifies the resources needed for the task (e.g., survey templates and online research tools) and provides links to them to the device, allowing users to quickly access the required resources.

[1379] Transparency in work progress and communication support

[1380] The device confirms the recommended agent and automatically generated instructions. After the agent accepts the task, their progress is tracked in real time by the server. Progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[1381] Specific examples

[1382] 1. Enter the task

[1383] The user types "I want to conduct market research on a new product" into the terminal.

[1384] The terminal sends this to the server.

[1385] 2. Task Analysis

[1386] The server analyzes the task content using natural language processing and extracts keywords such as "new product" and "market research."

[1387] The server queries the relational database to obtain similar task information and resources.

[1388] 3. Recommendation of the person in charge

[1389] The server refers to the user's skill data and recommends agent A.

[1390] The server generates the reason for recommendation and displays it on the terminal.

[1391] 4. Generate task instructions

[1392] The server generates specific task instructions (e.g., "research competing products") and sends them to the device.

[1393] 5. Providing necessary resources

[1394] The server collects links to resources necessary for market research and provides them to the terminal.

[1395] 6. Progression and communication support

[1396] The device displays the dashboard and person in charge A updates the progress.

[1397] All stakeholders can see progress in real time and provide comments and feedback as needed.

[1398] This system provides an environment in which users can carry out their work efficiently and make the most of opportunities for growth. This series of processes reduces stress for users through automation and transparency, and has the effect of improving work productivity.

[1399] The processing flow will be explained below.

[1400] Step 1:

[1401] The user inputs a task via a terminal, for example, "conduct market research for a new product."

[1402] Step 2:

[1403] The device accepts the input task and sends it to the server. The sent data includes the task content and the user's ID.

[1404] Step 3:

[1405] The server receives the task and begins analyzing it using a natural language processing engine. The server extracts keywords and context (e.g., "new product," "market research") from the task content.

[1406] Step 4:

[1407] The server queries a related database to collect similar tasks and related resources based on the extracted keywords.

[1408] Step 5:

[1409] The server checks the user profile database and analyzes each user's skill set, current workload, and past performance data.

[1410] Step 6:

[1411] The server selects the most suitable person based on the analysis data. For example, it may recommend person A, who has extensive experience in market research.

[1412] Step 7:

[1413] The server generates the reason for recommending agent A and sends this information to the terminal. The terminal displays a list of recommended agents and the reason.

[1414] Step 8:

[1415] The server automatically generates specific task instructions based on the task content, such as "First, research competitor products, then analyze market trends."

[1416] Step 9:

[1417] The server generates specific task instructions and sends them to the device, where they are displayed and viewed by the user.

[1418] Step 10:

[1419] The server identifies the resources needed to complete the task and generates links to access them, such as survey templates and online research tools.

[1420] Step 11:

[1421] The server sends these resource links to the terminal, which displays the access links and their descriptions.

[1422] Step 12:

[1423] The device confirms the recommended agent and the automatically generated instructions. When Agent A accepts the task, a confirmation is sent from the device to the server.

[1424] Step 13:

[1425] The server tracks the progress of tasks in real time and collects progress data, which is then reflected in the work progress management dashboard.

[1426] Step 14:

[1427] The device displays a progress management dashboard, allowing all stakeholders to view progress, provide comments, and provide feedback.

[1428] Step 15:

[1429] Users communicate in real time through the dashboard to provide any necessary coordination or assistance.

[1430] Example 1

[1431] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1432] In conventional task management systems, task assignment and progress tracking are performed manually, resulting in low work efficiency and a lack of transparency. It is also difficult to select the right person for the task, often resulting in delays in providing appropriate resources. Furthermore, there is a lack of communication between stakeholders, which reduces work productivity. The purpose of this invention is to solve these problems and improve work efficiency and transparency.

[1433] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1434] In this invention, the server includes a means for analyzing tasks using natural language processing technology, a means for recommending an appropriate person to perform the task based on the user's ability set, workload, and past performance data, and a means for automatically generating specific task instructions. This enables efficient analysis of tasks, appropriate recommendation of a person to perform the task, and automatic generation of specific instructions. Furthermore, by including a terminal that tracks the progress of tasks in real time and supports information exchange between related parties, and a means for identifying and providing resources required to perform the tasks, the transparency and efficiency of work are improved.

[1435] A "terminal" is an electronic device used by a user to input tasks and check instructions and progress. This includes computers and smartphones.

[1436] A "server" is a central processing unit that executes multiple means, and is a device that is responsible for analyzing tasks, recommending personnel, automatically generating task instructions, providing resources, and tracking progress.

[1437] "Natural language processing technology" is a technology for analyzing the content of a task and extracting keywords and context, and includes machine learning models and text analysis algorithms.

[1438] The "user ability set" is data relating to the job capabilities and skills of each user, and is information used for task allocation and recommendation of personnel.

[1439] "Workload" is data about the amount of tasks each user currently has and ongoing projects.

[1440] "Past achievement data" is a history of tasks and projects that the user has completed in the past, and is data related to their evaluations and achievements.

[1441] "Task instructions" are instructions that indicate the specific steps or procedures that must be performed to accomplish a particular task.

[1442] "Resources" are information or items such as materials, tools, templates, links, etc. required to perform a task.

[1443] A "dashboard" is a visual interface that displays the progress of tasks in real time and supports information exchange among stakeholders.

[1444] The present invention is a system that aims to improve the efficiency and transparency of task management in a workplace environment. This system mainly consists of the following components: a terminal, a server, a natural language processing engine, a user profile database, a task recommendation engine, a task instruction generation engine, a resource management system, and a work progress management dashboard.

[1445] System Configuration

[1446] Terminal

[1447] Users use a device (such as a PC or smartphone) to input tasks and check their progress. The device provides a user interface and sends the input tasks to the server. The device also displays the information sent from the server to the user.

[1448] server

[1449] The server serves as the central hub of the entire system and fulfills multiple roles. The specific processing performed by the server is shown below.

[1450] Natural Language Processing Engine

[1451] When a task is input, the server first analyzes the task content using a natural language processing engine (e.g., TensorFlow or OpenNLP). This analysis extracts key keywords and context from the task. For example, if the task is "conduct market research for a new product," the keywords "new product" and "market research" are extracted.

[1452] User profile database and task recommendation engine

[1453] Based on the analyzed task content, the server references a user profile database, which stores each user's ability set, workload, and past performance data. Based on this information, the server recommends the person best suited to the task. For example, a user with extensive market research experience and a light current workload may be recommended. The recommendation results are displayed on the terminal.

[1454] Task Instruction Generation Engine

[1455] The server automatically generates specific task instructions based on the acquired task content and the recommended person in charge. For example, it may generate specific steps such as "research competing products, then analyze market trends." This automatically generated instruction is sent to the terminal and can be confirmed by the user.

[1456] Resource Management System

[1457] The server identifies the resources (e.g., survey templates and online research tools) needed to complete the task and provides links to them to the device, allowing the user to quickly access the required resources. For example, specific resources such as "Market Research Template.xlsx" or "Access Link to Competitive Analysis Tool" can be included.

[1458] Business progress management dashboard

[1459] Users use a work progress management dashboard to check progress and communicate. The server tracks the progress of tasks in real time and displays it on the dashboard. After a task is accepted by a person in charge, the progress and related communications can be viewed by all parties on the dashboard. This ensures transparency of work and enables efficient information exchange.

[1460] Examples and prompts

[1461] Specific examples

[1462] Task Input

[1463] The user types "I want to conduct market research on a new product" into the terminal.

[1464] The terminal sends this to the server.

[1465] Task Analysis

[1466] The server uses a natural language processing engine to extract key keywords such as "new product" and "market research."

[1467] The server queries the relational database to obtain similar task information and resources.

[1468] Recommendation from a representative

[1469] The server refers to the user's skill data and recommends "users with extensive market research experience."

[1470] This information, along with the reason for the recommendation, is sent to the device.

[1471] Generate task instructions

[1472] The server generates specific task instructions (e.g., "research competing products") and sends them to the device.

[1473] Provision of necessary resources

[1474] The server identifies a resource such as "Market Research Template.xlsx" and provides it to the device.

[1475] Progression and communication support

[1476] The device displays progress on a dashboard, and the person in charge updates the progress as it happens.

[1477] All stakeholders can view and comment on progress and feedback in real time through a dashboard.

[1478] Prompt Sentence Examples

[1479] "I'd like to conduct market research for a new product. Please set the task to include researching competitive products and analyzing market trends."

[1480] "What are the specific steps I should take to start researching competitive products and then analyzing market trends?"

[1481] The system of the present invention provides an environment in which users can perform their work efficiently and maximize opportunities for growth. The aim is to reduce user stress through automation and transparency and improve work productivity.

[1482] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1483] Step 1:

[1484] The user inputs a task using a terminal. Specifically, the user inputs the task content (e.g., "Conduct market research for a new product") in text format through the terminal's user interface. The terminal then sends this input content to the server. The input data is the task content in natural language format and is passed to the server.

[1485] Step 2:

[1486] The server receives the task content and analyzes it using a natural language processing engine (e.g., TensorFlow or OpenNLP). Specifically, it extracts key keywords (e.g., "new product," "market research") and contextual information from the task text. The input data is the task content in text format, and the output data is the extracted keywords and contextual information.

[1487] Step 3:

[1488] The server queries the user profile database based on the extracted keywords and context information to obtain information such as past performance data, workload, and skill sets. The server analyzes this data and recommends the most suitable agent for the task. The input data are the extracted keywords and user profile information, and the output data are the recommended agent and the reason for the recommendation.

[1489] Step 4:

[1490] The server automatically generates specific task instructions for the recommended personnel. Specific steps (e.g., "Start researching competitive products, then analyze market trends") are automatically created based on predefined templates and past task instructions. The input data is the task content and information on the recommended personnel, and the output data is specific task instructions.

[1491] Step 5:

[1492] The server identifies the resources required to execute the task and provides the terminal with links and materials. Specifically, it collects research tools and templates (e.g., "Market Research Template.xlsx") and generates access links to them. The input data is the task content and resource information, and the output data is the links and materials for the required resources.

[1493] Step 6:

[1494] The user confirms the recommended agent and specific task instructions via the terminal. The agent accepts the task, and the server tracks its progress in real time. The progress is displayed on the terminal's work progress management dashboard, allowing all parties involved to check the progress and provide comments and feedback as needed. The input data is the ongoing task information, and the output data is the progress and feedback updated in real time.

[1495] Through these series of processing steps, the system can achieve efficient management and transparency of tasks, reducing the burden on users.

[1496] (Application example 1)

[1497] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1498] In modern factory operations, task allocation and progress management have become increasingly complex, making it difficult to carry out work efficiently. While there is also a need to maximize the capabilities of robots and deploy them in the right positions, current systems are unable to fully achieve this. This leads to uneven workloads within the factory, reducing the productivity of the manufacturing process.

[1499] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1500] In this invention, the server includes means for providing an operation screen for inputting tasks, means for analyzing the input tasks using natural language processing technology, means for recommending appropriate workers based on the analyzed tasks and on the user's capabilities, workload, and past execution data, means for automatically generating specific task instructions for the recommended workers, means for identifying and providing resources necessary for executing the tasks, means for tracking the progress of tasks in real time and providing a management screen that supports communication between related parties, means for considering the capabilities of robots operating in the factory when selecting and recommending workers, and means for automatically generating specific work instructions for the recommended robots. This enables efficient task allocation and progress management, thereby achieving equalization of workloads within the factory and improved productivity.

[1501] An "operation screen" is a display screen that provides an interface for a user to input a task.

[1502] "Natural language processing technology" is a technology for analyzing and understanding documents written in human language.

[1503] A "task" is an activity or task performed to achieve a specific goal.

[1504] "User" refers to the person or administrator who operates the system and inputs tasks.

[1505] "Ability" refers to the technical skills and knowledge possessed by a user or robot.

[1506] "Workload" refers to the amount of work a worker currently has and the state of their work.

[1507] "Execution data" is data that records the performance and results of tasks performed in the past.

[1508] "Worker" refers to a human or robot that performs the tasks recommended by the system.

[1509] "Task instructions" refer to instructions that show the specific steps and methods for executing a task.

[1510] "Resources" refer to things such as tools and materials needed to perform a task.

[1511] The "management screen" is an interface for tracking the progress of tasks in real time and sharing information among stakeholders.

[1512] "Communication" refers to the exchange of information or data between parties.

[1513] "Recommendation" refers to the system selecting and suggesting appropriate workers or robots.

[1514] "Factory robots" refer to mechanical devices that actually operate in a factory environment and perform specific tasks.

[1515] The system of the present invention is a program for managing tasks within a factory, and is implemented using the following hardware and software.

[1516] Program processing explanation

[1517] 1. Task Input Module:

[1518] The server provides a user interface for entering tasks. The interface runs on a tablet or personal computer and displays a form that allows users to enter tasks. The form includes input fields for task details, assignee assignments, and so on.

[1519] 2. Task Analysis Module:

[1520] The server analyzes the input task content using natural language processing technology. Specifically, it uses natural language processing engines such as spaCy and TensorFlow to extract keywords and context from the task content. Even if the task content is ambiguous, it analyzes the context and takes appropriate action.

[1521] 3. Agent Recommendation Module:

[1522] The server then refers to a user profile database based on the analyzed task information and recommends the appropriate worker. The database contains information about each user's abilities, workload, and past performance data, and the server selects the most suitable worker based on this information. Recommendations may also be made based on the capabilities of the robots operating in the factory.

[1523] 4. Task instruction generation module:

[1524] The server automatically generates specific task instructions for the recommended workers and robots. These instructions include the specific steps and necessary work processes for the task. For example, a specific instruction such as "pick out part A and perform welding" may be generated.

[1525] 5. Resource Provision Module:

[1526] The server identifies and provides the resources needed to perform a task, including links to the necessary tools and materials for quick access by users and robots.

[1527] 6. Progress Management Module:

[1528] The server monitors the progress of tasks in real time and supports communication between stakeholders through a management interface that includes a progress timeline, progress progress, and feedback functionality.

[1529] Examples and prompts

[1530] Examples:

[1531] 1. The user enters "Assemble part A" into the tablet device.

[1532] 2. The server analyzes the task content using natural language processing and extracts the keywords "Part A" and "assembly."

[1533] 3. Based on the analyzed information, the server refers to the user profile database and recommends workers and robots with extensive experience in assembling part A.

[1534] 4. The server automatically generates specific instructions, such as "pick up part A and weld it," and sends them to the recommended worker or robot.

[1535] 5. The server provides the necessary resources, such as the welding tool and the location information of part A.

[1536] 6. The administrator checks the progress on the management screen and provides feedback as needed.

[1537] Example prompt sentence:

[1538] Here's a new task: "Assemble part A." Please use a powerful natural language processing engine to analyze it and assign it to the appropriate robot. Please also automatically generate specific task instructions and required resource information.

[1539] This enables efficient task allocation and progress management, leading to equalized workloads within the factory and improved productivity.

[1540] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1541] Step 1:

[1542] The user opens an operation screen on a tablet device or personal computer for entering tasks. Here, the user enters task details, such as "Assemble part A." The input data includes the task content, the person in charge, the deadline, etc. The entered information is sent to the server via the API.

[1543] Step 2:

[1544] The server analyzes the received task content using natural language processing technology. Specifically, it uses a natural language processing engine (e.g., spaCy or TensorFlow) to extract keywords and context from the task content. At this stage, important keywords such as "Part A" and "assembly" are identified. The analysis results are used as input data to query a relational database.

[1545] Step 3:

[1546] Based on the analysis results, the server queries a relational database to collect information on similar tasks and the resources required. The database stores information on successful and unsuccessful cases of similar tasks, as well as information on the tools used. The query results are further processed and output as information on task execution.

[1547] Step 4:

[1548] Based on the analyzed task information, the server refers to a user profile database and recommends appropriate workers. The user profile database contains information on each worker's capabilities, workload, and past performance data. The capabilities of the robots operating in the factory are also taken into consideration. The selected workers and robots are output as a recommendation list.

[1549] Step 5:

[1550] The server automatically generates specific task instructions for the most suitable workers and robots based on the recommendation list. A template-based generation system is used to create instructions that indicate specific work procedures and required processes. For example, instructions such as "pick out part A and perform welding" are included. The generated task instructions are then sent to the workers and robots.

[1551] Step 6:

[1552] The server identifies and provides the resources needed to perform a task. These resources include information on the tools and materials needed. Links and location information are also provided, allowing workers and robots to quickly access them. This allows for efficient use of resources.

[1553] Step 7:

[1554] The server monitors the progress of tasks in real time and supports communication between stakeholders through a control screen that includes a progress timeline, progress progress, and feedback functions. The progress of workers and robots is updated, and stakeholders can check their respective status and provide instructions or feedback as needed.

[1555] Through this series of steps, tasks can be efficiently assigned and progress managed, resulting in equalized workloads within the factory and improved productivity.

[1556] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1557] The system according to the present invention aims to reduce the excessive pressure of tasks in the workplace and support efficient and transparent work execution. It also incorporates an emotion engine that recognizes the user's emotions and optimizes task management based on the emotions. Hereinafter, the embodiments of the present invention will be described in detail.

[1558] Overall system configuration

[1559] The system mainly consists of the following components:

[1560] 1. User Interface

[1561] 2. Natural Language Processing Engine

[1562] 3. User Profile Database

[1563] 4. Task Recommendation Engine

[1564] 5. Task Instruction Generation Engine

[1565] 6. Resource Management System

[1566] 7. Work progress management dashboard

[1567] 8. Emotion Engine

[1568] System processing flow

[1569] Task input and emotion recognition

[1570] A user inputs a task into the system via a terminal. For example, a specific task such as "conduct market research for a new product" is input. The terminal accepts this input, and at the same time, an emotion engine is activated to analyze the user's input and behavior. The emotion engine recognizes the user's current emotional state (e.g., stress, elation, etc.).

[1571] Task Analysis

[1572] The server analyzes the received task using a natural language processing engine. This analysis extracts keywords and context (e.g., "new product" or "market research") from the task content. The server then queries a related database to retrieve similar tasks and reference materials.

[1573] Recommendation from a representative

[1574] The server references the user profile database and selects the most suitable agent based on each user's skill set, workload, and past performance data. The results of the emotion engine are also reflected in this process. For example, Agent A, who has extensive experience in market research and is currently under low stress, may be recommended. This recommendation information is sent to the terminal.

[1575] Auto-generation of task instructions

[1576] The server automatically generates specific task instructions based on the task content and related goals. The instructions are adjusted to suit the user's needs, taking into account the results of the emotion engine. For example, instructions can be flexibly adjusted according to the user's emotional state, such as "First, research competing products, then analyze market trends."

[1577] Provision of necessary resources

[1578] The server identifies the resources needed for the task (e.g., survey templates and online research tools) and provides links to them to the device, allowing users to quickly access the required resources.

[1579] Transparency in work progress and communication support

[1580] The device confirms the recommended agent and automatically generated instructions. After the agent accepts the task, their progress is tracked in real time by the server. Progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[1581] Specific examples

[1582] 1. Task Input and Emotion Recognition

[1583] The user types "I want to conduct market research on a new product" into the terminal.

[1584] Along with this task, the device also analyzes the user's input and uses an emotion engine to recognize the user's emotional state.

[1585] 2. Task Analysis

[1586] The server analyzes the task content using natural language processing and extracts keywords such as "new product" and "market research."

[1587] The server queries the relational database to obtain similar task information and resources.

[1588] 3. Recommendation of the person in charge

[1589] The server refers to the user's skill data and the results of the emotion engine and recommends agent A.

[1590] The server generates the reason for recommendation and displays it on the terminal.

[1591] 4. Generate task instructions

[1592] The server generates specific task instructions (e.g., "Research competing products") and sends them to the device, reflecting the results of the emotion engine.

[1593] 5. Providing necessary resources

[1594] The server collects links to resources necessary for market research and provides them to the terminal.

[1595] 6. Progression and communication support

[1596] The device displays the dashboard and person in charge A updates the progress.

[1597] All stakeholders can see progress in real time and provide comments and feedback as needed.

[1598] This system provides an environment in which users can perform their work efficiently and make the most of opportunities for growth. In addition, incorporating an emotion engine enables flexible task management that takes into account the user's emotional state, which is expected to reduce work stress.

[1599] The processing flow will be explained below.

[1600] Step 1:

[1601] The user inputs a task via a terminal, for example, "conduct market research for a new product."

[1602] Step 2:

[1603] The device accepts the input task and sends it to the server. At the same time, the device sends the user's input and actions to the emotion engine, which analyzes the user's emotional state.

[1604] Step 3:

[1605] The emotion engine analyzes the user's input and behavioral patterns to recognize the emotions the user is currently feeling (e.g., stress, elation, etc.).

[1606] Step 4:

[1607] The server receives the task and begins analyzing it with a natural language processing engine, extracting keywords and context (e.g., "new product," "market research") from the task content.

[1608] Step 5:

[1609] The server queries a related database to collect similar tasks and related resources based on the extracted keywords.

[1610] Step 6:

[1611] The server checks the user profile database and analyzes each user's skill set, current workload, and past performance data.

[1612] Step 7:

[1613] The server selects the most suitable agent based on the analytical data and the results of the emotion engine. For example, it recommends Agent A, who has extensive experience in market research and is currently under low stress.

[1614] Step 8:

[1615] The server generates the reason for recommending agent A and sends this information to the terminal. The terminal displays a list of recommended agents and the reason.

[1616] Step 9:

[1617] The server automatically generates specific task instructions based on the task content. The instructions are adjusted to be more user-friendly, taking into account the results of the emotion engine. For example, it generates specific steps such as "First, research competing products, then analyze market trends."

[1618] Step 10:

[1619] The server generates specific task instructions and sends them to the device, where they are displayed and viewed by the user.

[1620] Step 11:

[1621] The server identifies the resources needed to complete the task and generates links to access them, such as survey templates and online research tools.

[1622] Step 12:

[1623] The server sends these resource links to the terminal, which displays the access links and their descriptions.

[1624] Step 13:

[1625] The device checks the recommended agent and automatically generated instructions. When agent A accepts the task, the status is sent from the device to the server.

[1626] Step 14:

[1627] The server tracks the progress of tasks in real time and collects progress data, which is then reflected in the work progress management dashboard.

[1628] Step 15:

[1629] The device displays a progress management dashboard, allowing all stakeholders to see the progress and provide comments and feedback.

[1630] Step 16:

[1631] Users communicate in real time through the dashboard to provide any necessary coordination or assistance.

[1632] Example 2

[1633] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1634] Conventional task management systems assign tasks without considering the user's emotional state, which increases work stress and pressure, potentially leading to reduced productivity and mental exhaustion. Furthermore, the recommendation of appropriate personnel and the generation of specific task instructions are not sufficiently automated, resulting in reduced management efficiency and difficulty in transparent work progress. There is a need to solve these problems and realize flexible task management that takes the user's emotional state into account.

[1635] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1636] In this invention, the server includes: means for providing a user interface for inputting tasks; means for analyzing the input tasks using natural language processing technology; means for recommending appropriate personnel based on the analyzed tasks and the user's skill set, workload, and past performance data; means for automatically generating specific task instructions for the recommended personnel; means for identifying and providing resources necessary to perform the tasks; means for incorporating an emotion engine that recognizes the user's emotional state and optimizes task management based thereon; and means for tracking task progress in real time and providing a dashboard that supports communication between parties involved. This enables flexible and efficient task management that takes the user's emotional state into consideration, thereby reducing work stress and improving productivity.

[1637] A "user interface" is an interface through which a user accesses a system to input tasks or obtain information.

[1638] "Natural language processing technology" is a technology for analyzing and understanding natural human language.

[1639] "User skill set" is a collective term for the skills, knowledge, and experience possessed by a particular user.

[1640] "Workload" refers to the amount and complexity of tasks currently being handled by each user.

[1641] "Past performance data" refers to data on the results and evaluations of tasks that each user has performed in the past.

[1642] "Rep recommendation" is the process of selecting the most suitable representative based on the user profile database.

[1643] "Automatic generation of task instructions" refers to automatically creating specific instructions based on task content and goals.

[1644] "Providing resources" means providing users with the tools, data, and templates necessary to complete a task.

[1645] The "emotion engine" is part of a system that recognizes the user's emotional state through analysis of their facial expressions and voice, and reflects this in task management.

[1646] A "dashboard" is an interface that displays task progress and related information in real time and supports communication between stakeholders.

[1647] This invention is a system that reduces excessive task pressure in the workplace and supports efficient and transparent work execution. In particular, it aims to reduce work stress by incorporating an emotion engine that recognizes the user's emotions and optimizes task management based on those emotions. Specific embodiments for implementing this invention are described below.

[1648] Overall system configuration

[1649] The system mainly consists of the following components:

[1650] 1. User Interface

[1651] 2. Natural Language Processing Engine (NLP Engine)

[1652] 3. User Profile Database (DB)

[1653] 4. Task Recommendation Engine

[1654] 5. Task Instruction Generation Engine

[1655] 6. Resource Management System

[1656] 7. Work progress management dashboard

[1657] 8. Emotion Engine

[1658] Hardware and software used

[1659] To realize this system, the following hardware and software are used.

[1660] Device: The device (computer, tablet, smartphone, etc.) through which the user enters the task.

[1661] Server: A device that analyzes tasks, recommends task managers, generates task instructions, tracks progress, etc. It is equipped with a high-performance CPU and memory.

[1662] Camera and microphone: Used as input devices to analyze the user's emotions.

[1663] NLP engine: Software that analyzes text. Specifically, it uses the Python library Natural Language Toolkit (NLTK) and SpaCy.

[1664] Emotion engine: Software for analyzing the user's facial expressions and voice. Specifically, it uses OpenCV, DeepFace, and the Google Speech-to-Text API for voice recognition.

[1665] Specific operation of the system

[1666] Task input and emotion recognition

[1667] The user inputs a task into the system via a terminal. For example, the user inputs an instruction such as "conduct market research for a new product." The terminal then sends this input to the server. At the same time, the server analyzes the user's current emotional state using a camera and microphone connected to the terminal. As a result, the server recognizes information such as "the user is excited."

[1668] Task Analysis

[1669] The server analyzes the received task using a natural language processing engine. It uses NLP engines such as NLTK and SpaCy to extract keywords and context from the input text. It then queries a related database to retrieve similar tasks and reference materials. For example, keywords such as "new product" and "market research" are extracted.

[1670] Recommendation from a representative

[1671] The server refers to the user profile database and selects the most suitable agent based on each user's skill set, workload, and past performance data. This process also takes into account the results of the emotion engine. For example, it may recommend "agent A, who has extensive experience in market research and is currently under low stress." This recommendation information is sent to the terminal and can be viewed by the user.

[1672] Auto-generation of task instructions

[1673] The server automatically generates specific task instructions based on the task content and related goals. Taking into account the results of the emotion engine, the instructions are adjusted to be more user-friendly. For example, specific instructions such as "First, research competitor products, then analyze market trends" are generated. These instructions are then sent to the device.

[1674] Provision of necessary resources

[1675] The server identifies the resources needed for the task and provides links to them to the device, such as survey templates and links to online research tools, for quick access by the user.

[1676] Transparency in work progress and communication support

[1677] The device confirms the recommended agent and automatically generated instructions. After the agent accepts the task, the progress is tracked in real time by the server. The progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[1678] Specific prompt examples

[1679] "Conduct market research for new products"

[1680] "First, research competitor products, then analyze market trends."

[1681] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1682] Step 1: Enter your task

[1683] A user inputs a task into the system via a terminal. For example, the user inputs a specific task such as "conduct market research for a new product." This input is saved as text data on the terminal. The terminal then sends this input data to the server.

[1684] Input: Task input from user (text format)

[1685] Output: Task input data (sent to server)

[1686] Step 2: Recognize emotions

[1687] The device activates an emotion engine to analyze the user's input and behavior. The device collects the user's facial expressions and voice through the camera and microphone and sends the data to the emotion engine. The emotion engine uses image analysis software (OpenCV and DeepFace) and voice analysis software (Google Speech-to-Text API) to recognize the user's emotional state.

[1688] Input: User's facial expression data, voice data

[1689] Output: Emotional state (e.g., "high stress," "relaxed")

[1690] Step 3: Analyzing the task

[1691] The server analyzes the received task input data using a natural language processing engine (NLTK or SpaCy). The server performs morphological and contextual analysis to extract keywords and context from the input data. At the same time, the server queries a related database to retrieve similar tasks and reference materials.

[1692] Input: Task input data

[1693] Output: Extracted keywords (e.g., "new product," "market research"), related materials

[1694] Step 4: Recommend a Representative

[1695] The server refers to the user profile database and selects the most suitable agent based on each user's skill set, workload, and past performance data. The output information of the emotion engine is also taken into consideration, so for example, Agent A, who has extensive experience in market research and is currently under low stress, may be selected. The server generates the reason for the recommendation and sends it to the terminal.

[1696] Inputs: Skill set data, workload data, performance data, emotional state

[1697] Output: Recommender (e.g., Person A), reason for recommendation

[1698] Step 5: Auto-generate task instructions

[1699] The server automatically generates specific task instructions based on the task content and related goals. Taking into account the results of the emotion engine, the instructions are adjusted to be more user-friendly. For example, specific instructions such as "First, research competing products, then analyze market trends" are generated. These instructions are then sent to the device.

[1700] Input: Task content, goal, emotional state

[1701] Output: Specific task instructions (e.g., "Research competing products")

[1702] Step 6: Providing necessary resources

[1703] The server identifies the resources needed for the task and provides links to them to the device, such as survey templates and links to online research tools needed for market research, allowing users to quickly access them.

[1704] Input: Task details, required resource information

[1705] Output: Resource links (e.g., survey templates, online tools)

[1706] Step 7: Transparency and communication support for work progress

[1707] The device checks the recommended agent and automatically generated instructions, then begins the process of verifying whether the agent has accepted the task. After the agent accepts the task, the server tracks its progress in real time. The progress and related communications are displayed on the work progress management dashboard, allowing all parties involved to share information transparently.

[1708] Input: Acceptance status of person in charge, task instructions

[1709] Output: Real-time progress, dashboard display

[1710] This allows users to manage tasks efficiently while taking their emotional state into account, reducing work stress and improving productivity.

[1711] (Application example 2)

[1712] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1713] Imbalances in workloads and increased work stress in factories can lead to reduced production efficiency and work errors. In particular, allocating tasks without considering the emotional state of robots and operators poses challenges in efficient work execution and in optimal production management. Furthermore, it is difficult to grasp the progress in real time, and effective communication support is lacking. Solutions to these issues are needed.

[1714] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1715] In this invention, the server includes: a means for providing a user interface for inputting tasks; a means for analyzing the input tasks using natural language processing; a means for recommending appropriate personnel based on the analyzed tasks and the user's skill set, workload, and past performance data; a means for automatically generating specific task instructions for the recommended personnel; a means for identifying and providing resources necessary to perform the tasks; a means for tracking task progress in real time and providing a dashboard to support communication between stakeholders; and a means for recognizing the emotional state of robots and optimally allocating tasks based on this. This enables even workload distribution within a factory and improves production efficiency. Furthermore, it also enables real-time progress monitoring and effective communication support.

[1716] "User interface" refers to the means and screen configuration for a user to input tasks into the system.

[1717] "Natural language processing technology" refers to the technology used to analyze the content of a task, and to extract keywords and context from the input text.

[1718] "Skill set" refers to the specific technical abilities and knowledge possessed by a user or robot.

[1719] "Workload" refers to the amount of work currently being done by a user or a robot.

[1720] "Performance Data" refers to data relating to the past work results and evaluations of a user or robot.

[1721] "Rep" refers to a person or robot that is assigned a specific task and is responsible for carrying it out.

[1722] "Task instructions" refer to instructions that explain specifically how to perform an assigned task.

[1723] "Resources" refer to the materials and tools needed to perform a task.

[1724] "Dashboard" refers to an interface for visually managing and displaying task progress and related information.

[1725] "Emotional state" refers to the current psychological state of the robot or user.

[1726] "Task recommendation engine" refers to algorithms and systems that recommend the most suitable person based on the analyzed task.

[1727] "Task allocation" refers to the process of appropriately assigning multiple tasks to each person in charge.

[1728] The present invention relates to a "factory workload management system" for resolving imbalances in workloads and increased work stress in factories. The system aims to recognize the emotional states of robots and operators and optimally allocate work tasks based on the recognition. Specific embodiments for carrying out the present invention will be described in detail below.

[1729] Overall system configuration

[1730] The system mainly consists of the following components:

[1731] 1. User interface: The means by which the user inputs the task.

[1732] 2. Natural language processing technology: A means of analyzing the content of the input task and extracting keywords and context.

[1733] 3. User profile database: A database that stores users' skill sets, workloads, and past performance data.

[1734] 4. Task recommendation engine: A means of recommending the most suitable person to handle a task based on the analyzed task.

[1735] 5. Task instruction generation engine: A means of automatically generating specific task instructions for recommended personnel.

[1736] 6. Resource Management System: A means of identifying and providing the resources needed to perform a task.

[1737] 7. Work Progress Management Dashboard: A means of tracking task progress in real time and supporting communication between stakeholders.

[1738] 8. Emotion engine: A means of recognizing the emotional state of the robot and optimally allocating tasks.

[1739] Hardware and Software Configuration

[1740] Hardware

[1741] Factory robots: Each robot is equipped with an emotion recognition sensor that can detect its emotional state in real time.

[1742] Central management server: Manages the entire system and processes data from each component.

[1743] software

[1744] Python language: A programming language for implementing task analysis and allocation algorithms.

[1745] Database management system (e.g., MySQL): stores and manages user profile data, task data, and resource data.

[1746] Emotion recognition software: Software for analyzing the emotional state of each robot.

[1747] System processing flow

[1748] The server receives task input from a user or automated system and processes it according to the following steps:

[1749] 1. Task Input and Emotion Recognition

[1750] The terminal inputs the task, and the emotion engine recognizes the robot's emotional state.

[1751] 2. Task Analysis

[1752] The server analyzes the task content using natural language processing technology and extracts relevant keywords and context.

[1753] 3. Recommendation of the person in charge

[1754] The task recommendation engine references a user profile database and recommends the best person based on skill set, workload, performance data, and emotional state.

[1755] 4. Automatic generation of task instructions

[1756] The server generates specific task instructions and notifies the person in charge.

[1757] 5. Identifying and Providing Resources

[1758] The server identifies and provides the resources needed for the task.

[1759] 6. Progression and communication support

[1760] A progress management dashboard tracks progress in real time and supports communication between stakeholders.

[1761] Specific examples

[1762] For example, if a robot is assigned the task of "conducting market research for a new product" in a factory, the emotion engine will classify the robot's emotional state as "happy," "neutral," or "stressed," and assign the task to the robot that is most suitable for the task. This will enable the equalization of workloads and improved production efficiency.

[1763] Prompt Sentence Examples

[1764] Design a system for optimal task allocation for factory robots based on each robot's emotional state and task load. Write a program in Python to create a flow for manually assigning the following tasks. Create a program that assigns tasks to the optimal robot and displays the final task load for each robot.

[1765] In this way, by using a system based on this invention, it is possible to evenly distribute the workload within a factory and improve production efficiency. It also makes it possible to allocate tasks taking into account the emotional state of the robot, which is expected to reduce work stress.

[1766] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1767] Step 1:

[1768] The terminal inputs a task and emotion recognition by the emotion engine begins. The user inputs a task into the terminal, such as "conduct market research for a new product." While receiving the input task, the emotion engine detects the robot's emotional state using the emotion recognition sensor. The input is the task content and the robot's current emotional state, and the output is task data and emotion data for analysis.

[1769] Step 2:

[1770] The server analyzes the task content using natural language processing technology. The server extracts keywords and context from the input task content, obtaining keywords such as "market research" and "new product." The input is the task data, and the output is the analyzed keywords and context information.

[1771] Step 3:

[1772] The server refers to the user profile database and recommends the most suitable agent using the task recommendation engine. The server selects the most suitable robot by taking into account the user's skill set, workload, past performance data, and emotional state. The input is keywords, context information, and information from the user profile database, and the output is a list of recommended agents.

[1773] Step 4:

[1774] The server automatically generates specific task instructions and notifies the person in charge. For example, instructions such as "First, research competing products, then analyze market trends" are generated. The input is the recommended person in charge and the task content, and the output is specific task instructions.

[1775] Step 5:

[1776] The server identifies and provides the resources needed for the task. For example, it collects survey templates and links to online research tools and provides them to the device. The input is specific task instructions, and the output is resource links.

[1777] Step 6:

[1778] The work progress management dashboard tracks progress in real time and supports communication between stakeholders. The person in charge updates the progress of the task, and all stakeholders can see it in real time. The input is progress data from the person in charge, and the output is dashboard information updated in real time.

[1779] The above processing steps enable the even distribution of work loads within the factory, improving production efficiency. It also enables task allocation that takes into account the emotional state of the robot, reducing stress during work and tasks.

[1780] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1781] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1782] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1783] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1784] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1785] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1786] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1787] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1788] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1789] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1790] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1791] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1792] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1793] 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.

[1794] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1795] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1796] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1797] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1798] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1799] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1800] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1801] The following is further disclosed regarding the above embodiment.

[1802] (Claim 1)

[1803] means for providing a user interface for inputting tasks;

[1804] A means for analyzing the input task using natural language processing technology;

[1805] Based on the analyzed tasks, a means for recommending appropriate personnel based on the user's skill set, workload, and past performance data;

[1806] a means for automatically generating specific task instructions for the recommended personnel;

[1807] A means of identifying and providing the resources needed to perform the task;

[1808] A means to track task progress in real time and provide a dashboard to support communication between stakeholders;

[1809] A system including:

[1810] (Claim 2)

[1811] 2. The system of claim 1, wherein the task analysis means extracts keywords and contexts from the task content and executes queries against a related database to collect information.

[1812] (Claim 3)

[1813] The system described in claim 1, characterized in that the means for automatically generating specific task instructions for the recommended personnel automatically generates specific steps such as "research competing products" and "analyze market trends."

[1814] "Example 1"

[1815] (Claim 1)

[1816] means for providing a terminal for inputting tasks;

[1817] a server that analyzes the input task using natural language processing technology;

[1818] A server that recommends an appropriate person based on the analyzed task, the user's ability set, workload, and past performance data;

[1819] a server that automatically generates specific task instructions for the recommended personnel;

[1820] a server that identifies and provides the resources needed to perform a task;

[1821] A terminal that provides a dashboard to track the progress of tasks in real time and support the exchange of information between stakeholders;

[1822] A system including:

[1823] (Claim 2)

[1824] 2. The system according to claim 1, wherein the server that analyzes the tasks extracts keywords and situations from the task content and executes queries against a related database to collect information.

[1825] (Claim 3)

[1826] The system described in claim 1, characterized in that the server that automatically generates specific task instructions for the recommended personnel automatically generates specific steps such as "researching competing products" and "analyzing market trends."

[1827] "Application Example 1"

[1828] (Claim 1)

[1829] means for providing an operation screen for inputting a task;

[1830] A means for analyzing the input task using natural language processing technology;

[1831] A means for recommending an appropriate worker based on the analyzed task and based on the user's ability, workload, and past execution data;

[1832] means for automatically generating specific task instructions for the recommended workers;

[1833] A means of identifying and providing the resources needed to perform the task;

[1834] A means to track task progress in real time and provide a management interface to support communication between stakeholders;

[1835] A means for considering and recommending the capabilities of robots operating in the factory when selecting workers;

[1836] A means for automatically generating specific work instructions for the recommended robot;

[1837] A system including:

[1838] (Claim 2)

[1839] 2. The system of claim 1, wherein the task analysis means extracts keywords and contexts from the task content and executes queries against a related database to collect information.

[1840] (Claim 3)

[1841] The system of claim 1, characterized in that the means for automatically generating specific task instructions for the recommended workers and robots automatically generates specific steps such as "remove parts" and "weld."

[1842] "Example 2: Combining Emotion Engines"

[1843] (Claim 1)

[1844] means for providing a user interface for inputting tasks;

[1845] A means for analyzing the input task using natural language processing technology;

[1846] Based on the analyzed tasks, a means for recommending appropriate personnel based on the user's skill set, workload, and past performance data;

[1847] a means for automatically generating specific task instructions for the recommended personnel;

[1848] A means of identifying and providing the resources needed to perform the task;

[1849] means for incorporating an emotion engine that recognizes the user's emotional state and optimizes task management based thereon;

[1850] A means to track task progress in real time and provide a dashboard to support communication between stakeholders;

[1851] A system including:

[1852] (Claim 2)

[1853] 2. The system of claim 1, wherein the task analysis means extracts keywords and contexts from the task content and executes queries against a related database to collect information.

[1854] (Claim 3)

[1855] The system described in claim 1, characterized in that the means for automatically generating specific task instructions for the recommended personnel automatically generates specific steps such as "research competing products" and "analyze market trends."

[1856] "Application example 2 when combining emotion engines"

[1857] (Claim 1)

[1858] means for providing a user interface for inputting tasks;

[1859] A means for analyzing the input task using natural language processing technology;

[1860] Based on the analyzed tasks, a means for recommending appropriate personnel based on the user's skill set, workload, and past performance data;

[1861] a means for automatically generating specific task instructions for the recommended personnel;

[1862] A means of identifying and providing the resources needed to perform the task;

[1863] A means to track task progress in real time and provide a dashboard to support communication between stakeholders;

[1864] a means for recognizing the emotional state of the robot and optimally allocating tasks based thereon;

[1865] A system including:

[1866] (Claim 2)

[1867] 2. The system of claim 1, wherein the task analysis means extracts keywords and contexts from the task content and executes queries against a related database to collect information.

[1868] (Claim 3)

[1869] The system described in claim 1, characterized in that the means for automatically generating specific task instructions for the recommended personnel automatically generates specific steps such as "research competing products" and "analyze market trends."

[1870] (Claim 4)

[1871] 2. The system of claim 1, wherein the means for recognizing the emotional state of the robot uses an emotion recognition sensor and provides feedback to the task recommendation engine based on the recognized emotion.

[1872] (Claim 5)

[1873] 2. The system of claim 1, wherein the means for optimally allocating tasks evaluates the emotional state and workload of each robot and assigns the task to the most suitable robot. [Explanation of symbols]

[1874] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for providing a user interface for inputting tasks; A means for analyzing the input task using natural language processing technology; Based on the analyzed tasks, a means for recommending appropriate personnel based on the user's skill set, workload, and past performance data; a means for automatically generating specific task instructions for the recommended personnel; A means of identifying and providing the resources needed to perform the task; A means to track task progress in real time and provide a dashboard to support communication between stakeholders; A system including:

2. 2. The system of claim 1, wherein the means for analyzing the task extracts keywords and contexts from the task content and executes queries against a related database to collect information.

3. The system of claim 1, characterized in that the means for automatically generating specific task instructions for the recommended personnel automatically generates specific steps such as "research competing products" and "analyze market trends."

Images