system

Abstract

This system improves the quality of business planning and enables efficient project progress management and effectiveness measurement. [Solution] The system includes means for providing generated business plans to users, receiving user feedback, and modifying or regenerating the business plans based on that feedback. It also includes means for dynamically generating a user interface and visually displaying the progress of business plans and projects. Furthermore, it provides means for collecting and analyzing project progress and results in real time and automatically generating effectiveness measurement reports based on this. It also trains a machine learning model using the collected data and automatically generates business simulations using this model. In addition, the system provides means for collecting each employee's work history and skill set and recommending resources and training tailored to individual needs.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance that responds to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Formulating business plans, managing progress, and measuring the effectiveness in corporate activities usually require a great deal of labor and time. Also, since the quality of business plans depends on data analysis, feedback collection, and experience, an effective platform is needed. Furthermore, individual support considering the work history and skill set of each employee is also essential for the growth of the company. The current system has difficulty comprehensively addressing these issues, and tools for efficiently realizing them have been demanded.

Means for Solving the Problems

[0005] This invention provides a system that automatically generates new business plans based on past project data and trend data using generative artificial intelligence. Specifically, it includes means for providing the generated business plans to the user, receiving user feedback, and modifying or regenerating the business plans based on that feedback. It also includes means for dynamically generating a user interface and visually displaying the progress of business plans and projects. Furthermore, it provides means for collecting and analyzing project progress and results in real time and automatically generating effectiveness measurement reports based on this. This improves the quality of business plans and enables efficient project progress management and effectiveness measurement. In addition, by training a machine learning model using the collected data and automatically generating business simulations using this model, it is possible to improve employee skills. Moreover, by collecting each employee's work history and skill set and providing means for recommending resources and training tailored to individual needs, effective support for each employee becomes possible.

[0006] "Generative artificial intelligence" is an artificial intelligence technology that automatically generates new information and plans based on past data and trends.

[0007] "Business planning" refers to the planning of specific projects and measures within a company's activities, with the aim of achieving the company's goals.

[0008] "Feedback" refers to evaluations and opinions received from users, and this information is used to modify systems and plans.

[0009] "User interface" refers to the screens and methods of operation that allow a user to interact with a system.

[0010] "Progress status" refers to the current status and progress of a project or task.

[0011] "Real-time" refers to the simultaneous processing and analysis of an event or process the moment it occurs.

[0012] "Effect measurement" is the process of evaluating the extent to which a particular action or measure has been achieved.

[0013] A "machine learning model" is an algorithm or mathematical model that uses collected data to identify specific patterns or make predictions.

[0014] "Business simulation" is a system that reproduces actual business processes in a virtual environment and allows users to experience those processes based on scenarios and storylines.

[0015] A "skill set" refers to a collection of specific abilities and knowledge that an individual possesses. [Brief explanation of the drawing]

[0016] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map on which a plurality of emotions are mapped. [Figure 10] It shows an emotion map on which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be described.

[0019] In the following embodiments, a processor with a reference numeral (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0020] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0021] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention relates to a system that automates the planning, management, and effectiveness measurement of business plans within a company, and further provides support to individual employees. The embodiments of this system are described below.

[0038] System Configuration

[0039] The system mainly consists of the following components:

[0040] server

[0041] terminal

[0042] User

[0043] 1. Generating a business plan

[0044] 1.1 Data Collection and Analysis

[0045] The server collects historical project data and trend data for the company. This collection is performed via database queries and APIs. The collected data undergoes data cleaning and preprocessing before being converted into an analyzable format.

[0046] 1.2 Planning using generative artificial intelligence

[0047] The server automatically generates new business plans using pre-processed data through generative artificial intelligence. This generative AI employs, for example, machine learning models and natural language generation algorithms. At this stage, the generated business plans are based on template formats and trend data.

[0048] 1.3 Providing proposals and feedback

[0049] The server displays the generated business plan on the user interface.

[0050] Users can review the proposed project plan and provide feedback, including additional suggestions and revisions. This feedback is then sent back to the server, which uses it to revise or regenerate the project plan.

[0051] 2. Platform: UX / Reporting

[0052] The server dynamically generates the user interface, allowing users to check business plans and project progress. The displayed dashboards are created using technologies such as HTML / CSS / JavaScript (registered trademark). This allows users to visually view real-time data and make immediate decisions on necessary actions.

[0053] 3. Generating business simulations

[0054] The server trains a machine learning model using collected employee performance data and work records. This model is used to generate simulations of actual work processes. The simulations reproduce work processes in a virtual environment and aim to improve employee skills. The generated simulation games are deployed via web and mobile platforms.

[0055] 4. Measurement of effectiveness

[0056] The server collects project progress data in real time and automatically generates effectiveness measurement reports. These reports include metrics such as project results, KPIs, and ROI after project completion. The generated reports can be downloaded and reviewed by the user.

[0057] 5. CRM-based employee support

[0058] The server manages each employee's work history and skill set. Based on this, users can submit support requests through the user interface or chatbot. The server then suggests the most suitable resources and training based on the request, supporting the employee's work. It also records employee growth data and feedback, which are used to improve future support.

[0059] Specific example

[0060] For example, the server generates a business plan titled "Marketing Strategy for New Product Launch." In doing so, it considers past successes and trends when proposing the plan. The user then reviews this plan and adds feedback, such as "We should strengthen social media advertising to expand the target market." Based on this feedback, the server revises the plan and presents an optimized marketing strategy again.

[0061] In this way, this system improves the quality of business planning and enables efficient project progress management and effectiveness measurement. Furthermore, it provides appropriate support to individual employees, thereby improving the overall performance of the company.

[0062] The following describes the processing flow.

[0063] Business plan generation

[0064] Business plan generation process

[0065] Step 1:

[0066] Server: Collects historical project data and trend data from the company's database. Extracts and preprocesses data using SQL queries.

[0067] Step 2:

[0068] Server: Cleans the collected data, imputing missing values ​​and removing outliers. Normalizes the data and converts it into a format suitable for analysis.

[0069] Step 3:

[0070] Server: Inputs pre-processed data into a generative artificial intelligence (e.g., a natural language generation algorithm) to automatically generate new business plans.

[0071] Step 4:

[0072] Server: Prepares the generated business plan for display in the user interface. This includes generating dynamic web pages using HTML / CSS / JavaScript.

[0073] Step 5:

[0074] User: Log in to the user interface and review the generated business plan. View the specific proposal details and prepare feedback at this stage.

[0075] Step 6:

[0076] User: Enter any corrections or suggestions into the feedback form and submit it to the server.

[0077] Step 7:

[0078] Server: Analyzes user feedback and executes algorithms to revise or regenerate business plans. Generative artificial intelligence is used again in this process.

[0079] UX / Reporting Process

[0080] Step 1:

[0081] Server: Build applications that collect project progress and key metrics. Collect real-time data through APIs and database connections.

[0082] Step 2:

[0083] Server: Processes collected data and generates graphs and charts for dashboards. Uses libraries such as D3.js to visualize the data.

[0084] Step 3:

[0085] Terminal: Users access the dashboard to view project progress and reports. They can view detailed information and historical data by interacting with UI elements.

[0086] Step 4:

[0087] Server: Automatically generates reports based on user-specified time periods and parameters, and outputs them in PDF or Excel format.

[0088] Step 5:

[0089] Terminal: Download the generated report and print or share it as needed.

[0090] Business simulation generation process

[0091] Step 1:

[0092] Server: Collects employee performance data and work records. Data is collected via database queries and APIs.

[0093] Step 2:

[0094] Server: Trains machine learning models using the collected data. Uses machine learning libraries such as TENSORFLOW® and PyTorch.

[0095] Step 3:

[0096] Server: Generates business simulation scenarios using a pre-trained model. Designs specific business processes and storylines.

[0097] Step 4:

[0098] Server: Deploys the generated simulation game to a web or mobile platform. Hosts the application using AWS® Lambda or Firebase.

[0099] Step 5:

[0100] User: Play simulation games and improve your skills. Collect gameplay logs and send them to the server.

[0101] Step 6:

[0102] Server: Analyzes collected gameplay data to identify areas for improvement in the simulation. Retrains the model as needed and generates improved scenarios.

[0103] Effectiveness measurement process

[0104] Step 1:

[0105] Server: Collects project progress data in real time. Data is automatically retrieved using APIs and webhooks.

[0106] Step 2:

[0107] Server: Analyzes data collected in real time and automatically generates effectiveness measurement reports based on that analysis. Inserts the analysis results into the report template.

[0108] Step 3:

[0109] User: View the generated performance measurement report on the dashboard. Download or print the report as needed.

[0110] CRM-based employee support process

[0111] Step 1:

[0112] Server: Collects each employee's work history and skill data and stores it in a database. Uses an API from the HR system.

[0113] Step 2:

[0114] Terminal: Provides an interface for employees to enter support requests. Requests are collected using chatbots or dedicated forms.

[0115] Step 3:

[0116] Server: Based on collected requests, it recommends the most suitable resources and training. It uses a matching algorithm to make appropriate suggestions.

[0117] Step 4:

[0118] Terminal: Employees use suggested resources to support their work. They refer to training materials and online guides.

[0119] Step 5:

[0120] Server: Records employee growth data and feedback, and uses it to improve future support. Analyzes feedback data to refine future proposals.

[0121] The above are the specific processing steps for carrying out the invention.

[0122] (Example 1)

[0123] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0124] In the current business planning and effectiveness measurement process, improving the quality of plans requires significant time and effort. Furthermore, the lack of centralized collection and analysis of accurate real-time data, and the absence of support tailored to individual employee skill sets, makes management cumbersome. This creates challenges in improving overall company performance.

[0125] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0126] In this invention, the server includes means for automatically generating new business plans based on past project data and trend data using a generation AI model, means for providing the generated business plans to users and receiving user feedback, and means for modifying or regenerating the generated business plans based on user feedback. This enables reduction of time and effort, accurate collection and analysis of real-time data, and centralized support for employees, which were problems in the past.

[0127] A "generative AI model" is an algorithm or program that uses generative artificial intelligence to automatically generate new information or content from given data.

[0128] A "prompt message" is an instruction given to a generative AI model to generate a specific answer or information.

[0129] "Past project data" refers to information and records about projects that a company has undertaken in the past, including, for example, project progress, results, and resources used.

[0130] "Trend data" refers to data that shows current market trends and changes, and includes, for example, social media posts, economic indicators, and industry news.

[0131] "User feedback" refers to suggestions for improvements, opinions, and additional requirements that users provide to the system.

[0132] A "template format" is a model used to format generated content or information into a specific form or structure.

[0133] A "dashboard" is an interface for centrally managing the visual display of project progress and data.

[0134] A "machine learning model" is a computer program that uses large amounts of data to train algorithms and then makes predictions, classifications, and generations based on new data.

[0135] A "virtual environment" is a digital space that simulates the physical environment of the real world, and is a system capable of reproducing various scenarios.

[0136] "Business simulation" is a system that aims to improve employee skills and operational efficiency by reproducing actual business processes in a virtual environment.

[0137] An "effectiveness measurement report" is a report created based on data collected to evaluate the results of a project.

[0138] This invention relates to a system that automates the planning, management, and effectiveness measurement of business plans within a company, and further provides support to individual employees. Specific embodiments of this system are described below.

[0139] System Configuration

[0140] The system mainly consists of the following components:

[0141] server

[0142] terminal

[0143] User

[0144] Data collection and analysis by server

[0145] The server collects historical project and trend data for companies through database queries (e.g., PostgreSQL) and APIs (e.g., Twitter API). The collected data is cleaned and preprocessed using Python scripts and ETL tools (e.g., Apache® NiFi) and converted into an analyzable format.

[0146] Server-based generation of business plans

[0147] The server inputs pre-processed data into a machine learning model (e.g., GPT-4®) and automatically generates new business plans using a generative AI model. The generated business plans are then formatted according to a template format.

[0148] Providing proposals and processing feedback

[0149] The server displays the generated business plan on a web interface. Users review the plan and provide feedback through the web interface. The server receives the user's feedback and uses the machine learning model again to revise or regenerate the plan.

[0150] User interface and display of real-time data

[0151] The server dynamically generates dashboards using HTML / CSS / JavaScript, visually displaying business plans and project progress to the user. Users can view real-time data on the dashboard.

[0152] Business simulation generation

[0153] The server trains machine learning models (e.g., TensorFlow or PyTorch) using employee performance data and work records, and generates work simulations in a virtual environment. The generated simulations are then provided through web and mobile applications.

[0154] Automatic generation of effectiveness measurement and reports

[0155] The server collects project progress data in real time and automatically generates performance measurement reports that include metrics such as KPIs and ROI. The generated reports are provided in a format that users can download and review.

[0156] Providing CRM-based employee support

[0157] The server manages each employee's work history and skill set, and allows users to submit support requests through an interface or chatbot. The server analyzes the requests and suggests the most suitable resources and training. It also records employee growth data and feedback to improve future support.

[0158] Specific example

[0159] For example, the server generates a business plan titled "Marketing Strategy for New Product Launch." In doing so, it considers past success stories and trend data to propose the plan. The user reviews this proposal and adds feedback such as, "We should strengthen social media advertising to expand the target market." Based on this feedback, the server revises the plan and presents an optimized marketing strategy again.

[0160] Example of a prompt

[0161] As an example of a prompt message to use when using a generative AI model, enter the following message:

[0162] "Based on marketing data from the past five years, please generate the optimal marketing strategy for our new product launch."

[0163] In this way, this system can improve the quality of business planning and enable efficient project progress management and effectiveness measurement. Furthermore, it can provide appropriate support to individual employees, thereby improving the overall performance of the company.

[0164] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0165] Step 1: Data Collection

[0166] The server executes database queries (e.g., PostgreSQL) to collect historical project data for a company. It uses SQL queries as input to retrieve historical project data records. The output is the retrieved project data. It also calls APIs (e.g., Twitter API) to collect trend data. It uses API requests as input to retrieve trend data as output.

[0167] Step 2: Data preprocessing and analysis

[0168] The server performs data cleaning and preprocessing on the acquired data using the Python Pandas library. It uses the acquired project data and trend data as input, handling missing values ​​and performing data type conversions. The output is preprocessed, analyzable data.

[0169] Step 3: Automatic generation of business plans

[0170] The server inputs pre-processed data into a machine learning model (e.g., GPT-4) and uses a generative AI model to automatically generate new business plans. Using pre-processed data and prompt statements as input, it obtains the generated business plan as output. Specifically, it formats the generated text based on a template format.

[0171] Step 4: Providing a proposal

[0172] The server displays the generated business plan on a web interface. It uses a formatted business plan as input and displays the business plan on a web page as output. Specifically, it dynamically generates the page using HTML / CSS / JavaScript.

[0173] Step 5: Collecting user feedback

[0174] Users review business plans and input feedback through a web interface. The system receives user feedback as input and outputs feedback data. Specifically, users input information using a feedback form.

[0175] Step 6: Revise or regenerate the plan based on feedback

[0176] The server uses the machine learning model again to revise or regenerate the business plan based on user feedback. It uses user feedback and the previously generated business plan as input, and obtains the revised or regenerated business plan as output. Specifically, it inputs the prompt and feedback again into the machine learning model and formats the generated text.

[0177] Step 7: Real-time display of progress

[0178] The server collects project progress in real time and dynamically generates a dashboard using HTML / CSS / JavaScript. It uses project progress data as input and outputs an updated dashboard display. Specifically, it periodically runs a data collection script to reflect the latest data in the dashboard.

[0179] Step 8: Automatic generation of performance measurement reports

[0180] The server automatically generates effectiveness measurement reports based on the collected progress data. It uses project progress data, KPIs, and ROI metrics as input, and outputs an effectiveness measurement report. Specifically, it executes a report generation script to create the report in PDF or web format.

[0181] Step 9: Generate Business Simulation

[0182] The server trains a machine learning model using employee performance data and work records to generate business simulations in a virtual environment. It uses employee data and work records as input and obtains business simulations as output. Specifically, it inputs data into the virtual environment system and reproduces business processes based on scenarios.

[0183] Step 10: Employee support using CRM functions

[0184] Users enter support requests through an interface or chatbot. The server analyzes the request and suggests the most suitable resources and training. It uses employee work history and skill sets, along with the request content, as input, and outputs suggested resources and training content. Specifically, it analyzes the request and searches the database for appropriate resource information.

[0185] (Application Example 1)

[0186] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0187] In modern factories, improving production efficiency and developing flexible production plans are crucial challenges. However, traditional systems relied on manual plan generation and modification based on historical data and trends, which required significant time and effort. Furthermore, real-time monitoring of production efficiency and improving the accuracy of production plans through operational simulations were difficult. Additionally, there was a lack of training tailored to each employee's skill set, sometimes resulting in a decline in overall productivity.

[0188] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0189] In this invention, the server includes means for collecting and analyzing data from sensors and IoT devices in production equipment, means for regenerating or improving the manufacturing plan based on the feedback, and means for monitoring production efficiency in real time and generating effectiveness measurement reports. This enables real-time monitoring and analysis of production efficiency, rapid regeneration and improvement of the manufacturing plan based on feedback, and the suggestion of training optimized for each employee.

[0190] "Generative artificial intelligence" is an artificial intelligence technology that automatically generates business plans and other information based on past data and trend data.

[0191] "Methods for automatically generating business plans" refers to the part of a system that automatically generates business plans using generative artificial intelligence based on collected data.

[0192] "Means of receiving feedback" refers to the part of the system that receives and processes opinions and suggestions for revisions from users.

[0193] "Means for modifying or regenerating business plans" refers to the part of the system that modifies existing business plans or generates new ones based on user feedback.

[0194] "Means for dynamically generating and displaying user interfaces" refers to the part of a system that provides dynamically generated interfaces so that users can visually check the progress of business plans and projects.

[0195] "Means for collecting and analyzing project progress and results in real time" refers to the part of a system that collects data in real time as the project progresses and analyzes that data immediately.

[0196] "Method for automatically generating effectiveness measurement reports" refers to the part of the system that measures the effectiveness of a project based on collected real-time analysis results and automatically generates a report on it.

[0197] "Methods for automatically generating business simulations" refers to the part of a system that uses machine learning models to automatically generate simulations that virtually reproduce actual business operations.

[0198] "Means for collecting employees' work history and skill sets and recommending training" refers to the part of the system that records each employee's work history and skill set and then suggests training that is appropriate to their needs based on that information.

[0199] "Means for collecting and analyzing data from sensors and IoT devices" refers to the part of the system that collects data in real time from sensors and IoT devices within a factory and analyzes that data.

[0200] "Means for regenerating or improving manufacturing plans based on feedback" refers to the part of the system that incorporates user feedback to regenerate or improve existing manufacturing plans.

[0201] "A means of monitoring production efficiency in real time and generating effectiveness measurement reports" refers to the part of a system that monitors production efficiency within a factory in real time and automatically generates effectiveness measurement reports that evaluate that efficiency.

[0202] This invention relates to a system aimed at improving production efficiency in factories and automatically generating flexible production plans. The system of this invention consists of a server, terminals, and users, and is implemented using various hardware and software.

[0203] Data collection and analysis

[0204] The server collects data in real time from sensors and IoT devices on production equipment. This data includes production volume, machine operating status, and quality inspection results. The data is preprocessed and analyzed to become foundational data for generating business plans. A database management system (e.g., MySQL®) is used to store and manage the data.

[0205] Automatic generation of business plans

[0206] The server automatically generates new business plans based on past project data and trend data using generative artificial intelligence. Machine learning algorithms (e.g., linear regression models) and natural language generation algorithms are used at this stage. The generated business plans are based on template formats and trend data.

[0207] Incorporating user feedback

[0208] The generated business plan is provided to the user via a terminal. The user reviews the proposed plan and provides any necessary feedback. The server then modifies or regenerates the business plan based on this feedback. This process generates an optimal business plan that meets the user's needs.

[0209] Production plan management and display

[0210] The server dynamically generates a user interface, visually displaying business plans and project progress to the user. This interface is created using technologies such as HTML / CSS / JavaScript, enabling real-time data display. The user reviews this information and decides on the next action as needed.

[0211] Effectiveness measurement and report generation

[0212] The server collects and analyzes project progress and results in real time and automatically generates effectiveness measurement reports. These reports include metrics such as KPIs and ROI, which users can review via their terminals.

[0213] Business simulation

[0214] The server trains a machine learning model using the collected data and automatically generates business simulations using this model. The simulations are run in a virtual environment and are intended to improve employee skills. The generated simulations are delivered via web and mobile platforms.

[0215] Employee support

[0216] The server manages each employee's work history and skill set, and based on this, suggests the most suitable resources and training. This ensures that each employee receives personalized support.

[0217] Specific example

[0218] For example, the server generates a business plan titled "Efficient Production Plan for a New Product." In doing so, it considers past production data and trends when proposing the plan. The user reviews this plan and adds feedback such as, "We need to adjust the production line to consider using a new material." Based on this feedback, the server revises the plan and presents a new, optimized production plan.

[0219] Examples of prompts for generative AI models

[0220] "Please generate a new production plan based on production data from the past three years. The feedback from management states that 'new materials should also be considered.' Please also generate a production plan that reflects this feedback."

[0221] By providing the entire system as an integrated service, the factory's production efficiency and flexibility are significantly improved. Furthermore, it contributes to improving employee skills and enhances overall performance.

[0222] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0223] Step 1:

[0224] The server collects data from sensors and IoT devices in the production equipment. This collected data includes production volume, machine operating status, and quality inspection results. This data is stored in a database (e.g., MySQL) and then cleaned and pre-processed. As a result, analyzable, formatted data can be obtained.

[0225] Step 2:

[0226] The server analyzes the formatted data and generates new business plans based on past project data and trend data. This process utilizes generative artificial intelligence technologies (e.g., machine learning algorithms and natural language generation algorithms). The business plans generated from the input data and the model are output.

[0227] Step 3:

[0228] The generated business plan is provided to the user via a terminal. The user reviews the provided business plan and enters any necessary feedback. This feedback includes specific revisions and additional requests. The user's input is sent to the server as feedback.

[0229] Step 4:

[0230] The server modifies or regenerates the business plan based on the feedback received. This process again utilizes generative artificial intelligence technology to automatically generate a new business plan that reflects the feedback. The output is the modified business plan.

[0231] Step 5:

[0232] The revised business plan is dynamically displayed on the user interface. The server generates a visually verifiable dashboard using technologies such as HTML / CSS / JavaScript. This user interface allows users to check the progress of business plans and projects in real time.

[0233] Step 6:

[0234] The server collects and analyzes project progress and results in real time. This process involves monitoring data from various sensors in real time to evaluate progress and performance. Performance metrics (e.g., KPIs and ROI) are used to assess the extent to which progress has been achieved. The evaluation results are provided as output.

[0235] Step 7:

[0236] The server automatically generates effectiveness measurement reports based on real-time analysis results. The reporting tool then uses the analysis results to generate reports based on metrics such as project completion outcomes, KPIs, and ROI. The generated reports are provided to the user to help them determine the necessary next actions.

[0237] Step 8:

[0238] The collected data is used to train a machine learning model, which is then used to automatically generate business simulations. These simulations replicate business processes in a virtual environment, aiming to improve employee skills. The generated business simulations are provided in a deployable format via web and mobile platforms.

[0239] Step 9:

[0240] The server collects each employee's work history and skill set, and recommends resources and training tailored to their needs. Based on the collected work history and skill set, it utilizes a matching algorithm to suggest the optimal training program. As a result, users are provided with individually optimized training plans.

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

[0242] This invention relates to a system that automates everything from business planning and progress management to effectiveness measurement and employee support, and further recognizes user emotions and incorporates them into the process. The following describes specific embodiments of this system.

[0243] System Configuration

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

[0245] server

[0246] terminal

[0247] User

[0248] 1. Generating a business plan

[0249] 1.1 Data Collection and Analysis

[0250] The server collects historical project data and trend data for the company. This data is retrieved via database queries and APIs, and then preprocessed through data cleaning and normalization.

[0251] 1.2 Planning using generative artificial intelligence

[0252] The server inputs pre-processed data into a generative artificial intelligence (e.g., a natural language generation algorithm) to automatically generate new business plans. The generated plans are based on template formats and trend data.

[0253] 1.3 Providing proposals and feedback

[0254] The server displays the generated business plan in the user interface. The user reviews the plan and provides feedback. This feedback is sent to the server and used for regeneration or modification.

[0255] 2. Platform: UX / Reporting

[0256] The server dynamically generates the user interface, allowing users to visually check business plans and project progress. Technologies such as HTML / CSS / JavaScript are used to visualize real-time data. Users view the data on the dashboard and decide on necessary actions.

[0257] 3. Business simulation generation

[0258] The server collects employee performance data and work records, and trains a machine learning model based on this data. This model is then used to generate work simulation scenarios. These simulations become available on web and mobile platforms.

[0259] 4. Measurement of effectiveness

[0260] The server collects project progress data in real time and automatically generates effectiveness measurement reports. These reports include project outcomes, KPIs, ROI, and more. Users can download and review the generated reports.

[0261] 5. CRM-based employee support

[0262] The server manages each employee's work history and skill set. Users can submit support requests through chatbots or dedicated forms. Based on the request, the server recommends appropriate resources and training. Employee growth data and feedback are also recorded and used to improve future support.

[0263] 6. Integrating an emotion engine

[0264] 6.1 Emotion recognition

[0265] The server uses an emotion engine to recognize user emotions and understand the user's emotional state. This allows for the collection of user emotional data during feedback sessions and work activities.

[0266] 6.2 Adjusting business plans based on emotions

[0267] The server adjusts the content of the work plan as needed based on the user's emotional state recognized by the emotion engine. For example, if the user is feeling stressed, it will make suggestions to reduce the workload.

[0268] 6.3 Improving the quality of feedback through sentiment analysis

[0269] The server analyzes the emotions expressed by users during feedback and uses the results to revise or regenerate business plans. This results in the creation of business plans that are more user-satisfying.

[0270] 6.4 Emotion-based support and suggestions

[0271] The user interface provides appropriate support and suggestions based on the user's emotions. For example, if the user is tired, it might suggest taking a break, responding in a way that matches their feelings.

[0272] Specific example

[0273] For example, when generating a business plan for a new marketing strategy, the server generates the plan by referencing past success stories. When a user reviews this plan and provides feedback, the emotion engine recognizes the user's emotions and determines whether the user is satisfied or dissatisfied. If dissatisfaction is detected, the server analyzes the reason and improves the plan. In this process, the burden on the user is reduced and an optimized plan is created.

[0274] In this way, this system can improve the quality of business planning and efficiently conduct project progress management and effectiveness measurement. Also, by providing appropriate support to individual employees and responding according to the users' emotions, it aims to improve the overall performance of the enterprise.

[0275] The following describes the process flow.

[0276] Generation of business plans

[0277] Business plan generation process

[0278] Step 1:

[0279] Server: Collect past project data and trend data from the enterprise database. Extract the necessary data using SQL queries and preprocess the data.

[0280] Step 2:

[0281] Server: Clean the collected data, perform imputation of missing values and removal of outliers. Perform normalization and feature extraction, and convert it into an analyzable format.

[0282] Step 3:

[0283] Server: Input the preprocessed data into generative artificial intelligence (natural language generation algorithm) to automatically generate a new business plan. The generated business plan is based on a template format.

[0284] Provision of plans and feedback

[0285] Step 4:

[0286] Server: Format the generated business plan into a format that can be displayed on the user interface. Generate a dynamic web page using HTML / CSS / JavaScript.

[0287] Step 5:

[0288] User: Log in to the user interface and review the generated business plan. View the specific details and prepare feedback.

[0289] Step 6:

[0290] User: Enter any corrections or suggestions in the feedback form and submit it.

[0291] Step 7:

[0292] Server: Receives feedback submitted by users and uses generative artificial intelligence to revise or regenerate the plan.

[0293] Platform: UX / Reporting Process

[0294] Step 1:

[0295] Server: Build APIs and database connections to collect project progress and key metrics, and obtain real-time data.

[0296] Step 2:

[0297] Server: Processes collected data and generates dashboards for visualization. Uses libraries such as D3.js to display real-time data as graphs and charts.

[0298] Step 3:

[0299] Terminal: Users access the dashboard to view project progress and reports. They interact with UI elements to view detailed information and historical data.

[0300] Step 4:

[0301] Server: Automatically generate a report based on the period and parameters specified by the user, and output it in PDF or Excel format.

[0302] Step 5:

[0303] Terminal: Download the generated report and perform printing and sharing as needed.

[0304] Integration of the emotion engine

[0305] Emotion recognition process

[0306] Step 1:

[0307] Server: Activate the emotion engine for recognizing the user's emotion. Extract the emotion from text or voice data using NLP technology and machine learning models.

[0308] Step 2:

[0309] Terminal: When the user inputs feedback or communication, send the data to the emotion engine.

[0310] Step 3:

[0311] Server: Analyze the data received by the emotion engine and determine the user's emotional state. This information is recorded in the database.

[0312] Adjustment of business planning based on emotion

[0313] Step 4:

[0314] Server: Reflect the user's emotion data determined by the emotion engine in the business planning. For example, when the user is feeling stressed, automatically add a proposal to reduce the workload.

[0315] Analysis and reflection of feedback

[0316] Step 5:

[0317] Server: Analyzes the emotional state of users when they provide feedback to identify the quality of the feedback and areas for improvement. Based on these analysis results, the business plan is revised or regenerated.

[0318] Emotion-based support and suggestions

[0319] Step 6:

[0320] Terminal: Displays support and suggestions tailored to the user's emotions on the user interface. For example, if the user is tired, it suggests taking appropriate rest.

[0321] Step 7:

[0322] Server: Based on user growth data and emotional feedback, it improves future business planning and support suggestions. This data will be used for future training and support.

[0323] Business simulation generation process

[0324] Step 1:

[0325] Server: Collects employee performance data and work records. Retrieves data via databases and APIs.

[0326] Step 2:

[0327] Server: Trains machine learning models using collected data. Uses libraries such as TensorFlow and PyTorch.

[0328] Step 3:

[0329] Server: Generates business simulation scenarios using a pre-trained model. Incorporates specific business processes and storylines into the scenarios.

[0330] Step 4:

[0331] Server: Deploys the generated simulation game to a web or mobile platform. Deployment is performed using AWS or Firebase.

[0332] Step 5:

[0333] User: Play simulation games and improve your skills. Collect gameplay logs and send them to the server.

[0334] Step 6:

[0335] Server: Analyzes collected gameplay data to identify areas for improvement in the simulation. Retrains the model to generate improved scenarios.

[0336] Effectiveness measurement process

[0337] Step 1:

[0338] Server: Collects project progress data in real time. Retrieves data via APIs and webhooks.

[0339] Step 2:

[0340] Server: Analyzes collected data in real time and automatically generates effectiveness measurement reports. Inserts data into report templates.

[0341] Step 3:

[0342] User: View the generated performance measurement report on the dashboard. Download and print the report as needed.

[0343] Employee support using CRM

[0344] Step 1:

[0345] Server: Collects each employee's work history and skill data and stores it in a database. Retrieves data from the HR system via API.

[0346] Step 2:

[0347] Terminal: Provides an interface for employees to enter support requests. Requests are collected using chatbots or dedicated forms.

[0348] Step 3:

[0349] Server: Recommends the most suitable resources and training based on the request. Uses a matching algorithm to make appropriate suggestions.

[0350] Step 4:

[0351] Terminal: Employees use suggested resources to support their work. They refer to training materials and online guides.

[0352] Step 5:

[0353] Server: Records employee growth data and feedback, and uses it to improve future support. Analyzes feedback data to refine future proposals.

[0354] The above are the specific processing steps for carrying out the invention.

[0355] (Example 2)

[0356] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0357] Traditional business management systems have struggled to comprehensively automate everything from business planning and progress management to performance measurement and employee support, and have been particularly poor at providing feedback and adjusting plans to reflect user sentiment. Furthermore, while efficiency and flexibility are required for real-time project management and providing individual employee support, no system adequately met these needs.

[0358] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for automatically generating new business plans based on past project data and trend data using generative artificial intelligence; means for providing the generated business plans to the user and receiving user feedback; means for modifying or regenerating the business plans based on user feedback; means for dynamically generating a user interface and visually displaying the progress of business plans and projects to the user; means for collecting and analyzing project progress and results in real time; means for automatically generating effectiveness measurement reports based on real-time analysis results; means for training a machine learning model using the collected data and automatically generating business simulations using this model; means for collecting each employee's work history and skill set and recommending resources and training according to their needs; means for collecting user emotional data during feedback and work using an emotion engine that recognizes the user's emotional state; and means for appropriately adjusting the content of the business plans based on the user's emotional state. This enables the streamlining and optimization of the entire business process, as well as flexible, high-quality feedback and planning adjustments that reflect user sentiment.

[0359] "Generative artificial intelligence" is a general term for artificial intelligence technologies that automatically generate new information and plans based on past data and trend information.

[0360] "Business planning" refers to the planning of projects and tasks that a company or organization will carry out, and its contents include objectives, means, schedules, and resource allocation.

[0361] "Feedback" refers to opinions and evaluations provided by users, which are useful information for improving services and projects.

[0362] "User interface" is a general term for the screens and operating methods that users use to operate a system and input or retrieve information.

[0363] "Real-time" refers to the process where data and information are processed instantly, and the results are reflected immediately.

[0364] An "effectiveness measurement report" is an automatically generated report used to evaluate the progress and results of a project or task, and includes metrics such as KPIs and ROI.

[0365] A "machine learning model" refers to an algorithm or computer program that analyzes large amounts of data and learns patterns and rules from it.

[0366] "Business simulation" refers to scenarios or simulators that reproduce actual business environments and situations, allowing users to virtually try them out.

[0367] "Work history" refers to records of an employee's past work and projects, and is used to analyze performance and trends.

[0368] A "skill set" refers to the collection of abilities and skills that each employee possesses, and its contents include specialized knowledge and experience.

[0369] "Resources" refer to management resources such as personnel, time, funds, and equipment, and how these are allocated and utilized is crucial.

[0370] An "emotion engine" refers to artificial intelligence technology or systems used to recognize and analyze a user's emotional state.

[0371] "Emotional data" refers to data that indicates a user's emotional state and is used for feedback and improving business processes.

[0372] A "template format" refers to a template for documents or data created based on a specific structure or format.

[0373] "Trend data" refers to data that shows past trends or patterns in phenomena, and is used for future predictions and planning.

[0374] Modes for carrying out the invention

[0375] This invention is a system that automates everything from business planning and progress management to effectiveness measurement and employee support, and further recognizes user emotions and reflects them in the process. The following describes a specific form for implementing the invention.

[0376] System Configuration

[0377] The system primarily consists of servers, terminals, and users. The server acts as a central management device, handling data collection, processing, analysis, generation, and presentation. Terminals are devices that users use to access the server and input or verify data. Users are the primary operators of the system, generating business plans and providing feedback.

[0378] Hardware and software to be used

[0379] Hardware: Servers (server machines with high-performance CPUs and sufficient memory), terminals (PCs, tablets, smartphones)

[0380] Software: Database management system (DBMS), generative AI models (NLP algorithms), libraries for data collection and analysis (Pandas, Scikit-learn), sentiment engine (Google® AI Sentiment Analysis API), user interface technologies (HTML / CSS / JavaScript, D3.js)

[0381] Specific processing flow

[0382] The server first collects past project and trend data for the company using APIs and database queries. The collected data undergoes data cleaning and normalization, and is then input into a generative AI model (e.g., an NLP algorithm) to generate new business plans.

[0383] The generated business plan is applied to a template format and then provided to the user through the user interface. The user reviews it and provides feedback. This feedback is sent to the server and used for regeneration and modification.

[0384] The server displays real-time data using technologies such as HTML / CSS / JavaScript and D3.js to dynamically visualize business plans and project progress. Users can view this data on a dashboard and decide on necessary actions.

[0385] Furthermore, the server collects employee performance data and work records, and trains machine learning models based on this data. The trained models are then used to generate work simulation scenarios, enabling more realistic predictions and planning.

[0386] The system also includes a feature to collect project progress and results in real time and automatically generate effectiveness measurement reports. These reports include key metrics such as KPIs and ROI, and users can download the reports to view the details.

[0387] The server also manages each employee's work history and skill set, and recommends resources and training tailored to their needs. Users can submit support requests through chatbots or dedicated forms, and the server provides appropriate resources and training in response.

[0388] The emotion engine recognizes the user's emotional state and collects emotional data during feedback and work. The server has the function to adjust the content of work plans as needed based on the emotional data. This allows for suggestions to reduce the workload when the user is experiencing stress.

[0389] Specific example

[0390] For example, when generating a business plan for a new marketing strategy, the server collects data on successful case studies and market trends from the past year, and then uses an AI model to automatically generate the plan based on that data. When a user reviews this plan and provides feedback, the emotion engine recognizes the user's emotions, and the server analyzes those emotions to identify problems in the plan and makes corrections.

[0391] Example of a prompt

[0392] "Develop a new marketing strategy. Referencing successful case studies and trend data from the past year, analyze user sentiment, and propose the optimal plan."

[0393] This will improve the quality of business planning, streamline project management and effectiveness measurement, and enhance the quality of support for employees, thereby improving overall corporate performance.

[0394] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0395] Program processing flow

[0396] Step 1:

[0397] Data Acquisition and Preprocessing

[0398] The server collects historical project and trend data for companies using APIs and database queries. Input data includes sales performance and market trends for the past year. After collecting this data, the server performs data cleaning (imputing missing values ​​and removing outliers) and normalization (scaling the data). The output is a clean dataset.

[0399] Specific example of operation: The server executes an SQL query like "SELECT FROM ProjectData WHERE Year=2022" to collect data, and then uses the Python Pandas library to perform data cleaning and normalization.

[0400] Step 2:

[0401] Business plan generation

[0402] The server inputs pre-processed data into a generation AI model (such as an NLP algorithm) to automatically generate new business plans. The input is a clean dataset, and the output is a new business plan document.

[0403] Specific example of operation: The server outputs a log message saying "Generating new business plan using NLP model..." and generates a new business plan using an NLP algorithm.

[0404] Step 3:

[0405] Applying a project template

[0406] The server applies the generated business plan to a template format. The input is the generated business plan document, and the output is a plan document that fits the standard format.

[0407] Specific example of operation: The server outputs "Applying business plan to template format..." and applies the new plan to the template.

[0408] Step 4:

[0409] Providing a plan

[0410] The server displays business plans that fit a standard format in the user interface. The input is the plan document after applying the template, and the output is the business plan displayed on the user screen.

[0411] Specific example of operation: The server outputs a log message saying "Displaying business plan on user interface..." and generates and sends HTML content to the user's terminal.

[0412] Step 5:

[0413] Gathering feedback

[0414] The user reviews the displayed business plan and enters feedback. The input is the user's feedback comment, and the output is the feedback data sent to the server.

[0415] Specific example of operation: The user enters "I would like the sales target to be set a little higher" in the feedback field on the screen and presses the submit button.

[0416] Step 6:

[0417] Feedback analysis and regeneration

[0418] The server receives user feedback and uses an emotion engine to analyze the feedback content and emotional state. The input is the feedback data, and the output is the analysis results and a list of items that need correction.

[0419] Specific example of operation: The server outputs a log message saying "Received user feedback. Analyzing for plan adjustment..." and calls a sentiment analysis API to evaluate the feedback content.

[0420] Step 7:

[0421] Regenerate or modify the business plan.

[0422] The server regenerates or modifies the business plan based on the analysis results of the feedback. The input is the analysis results, and the output is the modified or regenerated business plan document.

[0423] Specific example of operation: The server uses the NLP model again and outputs a log message saying "Adjusting business plan based on user feedback..." to regenerate the plan.

[0424] Step 8:

[0425] Visual confirmation

[0426] The server redisplays the regenerated or modified business plan in the user interface. The input is the final business plan document, and the output is the updated business plan displayed on the user screen.

[0427] Specific example of operation: The server regenerates the revised business plan in HTML and displays it on the user's terminal.

[0428] Step 9:

[0429] Visualization of real-time progress

[0430] The server collects and visually displays project progress data in real time. The input is progress data, and the output is real-time graphs and charts displayed on the dashboard.

[0431] Specific example of operation: The server uses a JavaScript library (e.g., D3.js) to generate graphs in real time and display them on the user's dashboard.

[0432] Step 10:

[0433] Business simulation generation

[0434] The server collects employee performance data and work records, and uses this data to train a machine learning model. The input is performance data, and the output is the trained machine learning model.

[0435] Specific example of operation: The server outputs a log message saying "Training machine learning model with performance data..." and trains the model using Spark ML or TensorFlow.

[0436] Step 11:

[0437] Generating Simulation Scenarios

[0438] The server uses a trained model to generate business simulation scenarios. The input is the trained model, and the output is the simulation scenario.

[0439] Specific example of operation: The server outputs a log message saying "Generating business simulation scenarios...", generates a scenario, and provides it to the user.

[0440] Step 12:

[0441] Generating an effectiveness measurement report

[0442] The server automatically generates project results as effectiveness measurement reports. The input is project progress data, and the output is the effectiveness measurement report.

[0443] Specific example of operation: The server outputs a log message saying "Generating performance measurement report..." and generates a report in Excel or PDF format.

[0444] Step 13:

[0445] Report Provision

[0446] Users can view the generated performance measurement reports on the dashboard and download them as needed. The input is the performance measurement report, and the output is the report downloaded to the user's device.

[0447] Specific example of operation: A user clicks a file from the dashboard and downloads a PDF report.

[0448] Step 14:

[0449] Providing CRM-based employee support

[0450] The server manages each employee's work history and skill set, and provides appropriate resources and training based on user requests. Inputs include employee work history, skill set, and request data, while outputs include recommended resources and training plans.

[0451] Specific example of operation: The server outputs a log message saying "Recommending training resources for requested skill..." and provides relevant online courses and materials.

[0452] (Application Example 2)

[0453] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0454] Traditional business planning and project management systems automate tasks such as generating plans and measuring effectiveness based on past data, but they fail to consider the emotional state of users, potentially increasing worker stress and workload. Furthermore, real-time work instructions and dynamic task reallocation required complex settings and human intervention, making them inefficient. Additionally, a lack of individual support for factory workers could result in a decrease in overall productivity.

[0455] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically generating new business plans based on past project data and trend data using generative artificial intelligence; means for providing the generated business plans to the user and receiving user feedback; means for modifying or regenerating the generated business plans based on user feedback; means for dynamically generating a user interface and visually displaying the progress of business plans and projects to the user; means for collecting and analyzing project progress and results in real time; means for automatically generating effectiveness measurement reports based on real-time analysis results; means for training a machine learning model using the collected data and automatically generating business simulations using this model; means for collecting each employee's work history and skill set and recommending resources and training according to their needs; means for recognizing the user's emotional state using an emotion recognition engine and adjusting the content of the business plans based on the results; and means for providing work instructions in real time using a head-mounted display and performing dynamic work reallocation based on emotions. This allows for a reduction in the burden on workers by responding to user emotions, enabling improved work efficiency and increased productivity.

[0456] "Generative artificial intelligence" is an artificial intelligence technology that automatically generates new business plans by utilizing past project data and trend data.

[0457] "Providing to users" refers to the means of showing or presenting the generated business plan to users.

[0458] "Receiving user feedback" refers to the means of collecting opinions and reactions from users.

[0459] "Modifying or regenerating generated business plans" refers to the means of changing existing business plans or generating new ones based on user feedback.

[0460] "Dynamically generating a user interface" refers to a means of providing users with a visual display based on information and data that changes in real time.

[0461] "Collecting and analyzing project progress and results in real time" refers to methods for acquiring and analyzing project progress and results in real time.

[0462] "Automatically generating effectiveness measurement reports" refers to a method for automatically creating effectiveness measurement reports based on the project's progress and results.

[0463] "Training a machine learning model" refers to the process of training a machine learning algorithm using collected data.

[0464] "Automatically generating business simulations" refers to a method of automatically creating business simulations using trained machine learning models.

[0465] "Recommending resources and training tailored to individual needs" means proposing necessary resources and training based on each employee's work history and skill set.

[0466] An "emotion recognition engine" is a technology used to recognize a user's emotional state.

[0467] "Adjusting the content of the business plan" refers to the means of appropriately changing the content of the business plan based on the perceived emotional state.

[0468] A "head-mounted display" is a display device worn on the head to display work instructions in real time.

[0469] "Dynamic task reallocation" refers to a method of redistributing tasks in response to real-time situations and emotional states.

[0470] This invention relates to a smart factory support system for assisting factory workers. This system enables automatic generation of work plans, optimization of work through emotion recognition, real-time instruction provision, and dynamic work redistribution.

[0471] System Configuration

[0472] This system consists of the following main components:

[0473] server

[0474] Head-mounted display (HMD)

[0475] User (factory worker)

[0476] server

[0477] Business plan generation

[0478] The server collects past project and trend data for companies, and performs data cleaning and normalization. This pre-processed data is then input into generative artificial intelligence (such as natural language generation algorithms) to automatically generate new business plans. The generated plans are based on template formats and trend data and are displayed in the user interface.

[0479] Feedback and Sentiment Recognition

[0480] The server collects feedback from users (workers) and recognizes their emotional state using an emotion recognition engine. Based on this information, it modifies or regenerates the business plan. Emotion recognition is performed by analyzing biometric data such as facial expressions and heart rate.

[0481] Providing real-time instructions

[0482] The server has the capability to provide work instructions in real time via a head-mounted display. If the emotion recognition engine detects the user's stress level, the server dynamically redistributes tasks to reduce the workload.

[0483] Effectiveness measurement

[0484] The server collects project progress and results in real time and automatically generates effectiveness measurement reports. These reports are displayed in the user interface for easy review.

[0485] Head-mounted display

[0486] A head-mounted display (HMD) is a device worn by workers that visually displays real-time work instructions and status reports. This allows workers to check work instructions without using their hands.

[0487] User

[0488] Factory workers wear head-mounted displays to view real-time work instructions provided by a server. Emotions and feedback during work are sent to the server via an emotion recognition engine and a chatbot.

[0489] Specific example

[0490] For example, when introducing a new production line at a factory, the server references data from similar past projects to generate a new work plan. As workers wearing HMDs (Head-Mounted Displays) follow the instructions, the emotion recognition engine detects stress in the workers, and the server automatically redistributes the workload to reduce the burden on the workers. After the work is completed, progress and effectiveness measurement reports are automatically generated.

[0491] Example of a prompt

[0492] "I want to develop an application that recognizes emotions in real time using an emotion recognition model and displays work instructions on a head-mounted display. The emotion recognition model to be used is "emotion_model.h5," which recognizes facial expressions. Work instructions will be obtained from AI_ENDPOINT. For example, if a worker is feeling stressed, the application should issue instructions to reduce their workload."

[0493] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0494] Step 1:

[0495] The server collects historical project data and trend data, and performs data cleaning and normalization. Specifically, it retrieves necessary data using database queries and APIs, and removes incomplete and duplicate data. It also preprocesses the data by converting it to a unified format. It receives project data from databases and external APIs as input and outputs preprocessed data.

[0496] Step 2:

[0497] The server inputs pre-processed data into a generative artificial intelligence (natural language generation algorithm) to automatically generate new business plans. This generation process generates the optimal business plan in natural language format based on the input data. It receives pre-processed data as input and obtains the generated business plan as output.

[0498] Step 3:

[0499] The server provides the generated business plan to the user through a user interface. The user reviews the provided business plan and enters feedback. The server receives the generated business plan data and the user's feedback as input and obtains an updated plan or feedback content as output.

[0500] Step 4:

[0501] The server modifies or regenerates business plans based on user feedback. This process includes analyzing the feedback and re-inputting the analysis results into a generative artificial intelligence to generate new business plans. It receives feedback data as input and obtains modified or regenerated business plans as output.

[0502] Step 5:

[0503] The server recognizes the user's emotional state using an emotion recognition engine. Specifically, it acquires the user's facial image using a camera and inputs it into the emotion recognition model to perform an emotional evaluation. It receives real-time facial image data as input and obtains the user's emotional state as output.

[0504] Step 6:

[0505] The server adjusts the content of the business plan based on the emotion recognition results. Specifically, if the user is experiencing stress, the generative artificial intelligence will make suggestions to reduce the workload. It receives emotion data as input and obtains an adjusted business plan as output.

[0506] Step 7:

[0507] The server provides work instructions in real time via a head-mounted display. It can also dynamically modify work instructions based on emotion recognition results. It receives adjusted work plans and emotion data as input and outputs instruction data for the head-mounted display.

[0508] Step 8:

[0509] The server collects project progress and results in real time and automatically generates effectiveness measurement reports. This process includes collecting and analyzing sensor data and log data, and generating reports. It receives project progress data as input and obtains effectiveness measurement reports as output.

[0510] Step 9:

[0511] The server collects each employee's work history and skill set, and recommends resources and training tailored to their needs. Specifically, it retrieves work history and skill set data from the database and generates appropriate resources and training plans. It takes employee data as input and outputs recommended resources and training plans.

[0512] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0513] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0514] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0515] [Second Embodiment]

[0516] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0517] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0518] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0519] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0520] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0521] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0522] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0523] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0524] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0525] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0526] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0527] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0528] This invention relates to a system that automates the planning, management, and effectiveness measurement of business plans within a company, and further provides support to individual employees. The embodiments of this system are described below.

[0529] System Configuration

[0530] The system mainly consists of the following components:

[0531] server

[0532] terminal

[0533] User

[0534] 1. Generating a business plan

[0535] 1.1 Data Collection and Analysis

[0536] The server collects historical project data and trend data for the company. This collection is performed via database queries and APIs. The collected data undergoes data cleaning and preprocessing before being converted into an analyzable format.

[0537] 1.2 Planning using generative artificial intelligence

[0538] The server automatically generates new business plans using pre-processed data through generative artificial intelligence. This generative AI employs, for example, machine learning models and natural language generation algorithms. At this stage, the generated business plans are based on template formats and trend data.

[0539] 1.3 Providing proposals and feedback

[0540] The server displays the generated business plan on the user interface.

[0541] Users can review the proposed project plan and provide feedback, including additional suggestions and revisions. This feedback is then sent back to the server, which uses it to revise or regenerate the project plan.

[0542] 2. Platform: UX / Reporting

[0543] The server dynamically generates the user interface, allowing users to check business plans and project progress. The displayed dashboards are created using technologies such as HTML / CSS / JavaScript. This allows users to visually view real-time data and make immediate decisions about necessary actions.

[0544] 3. Generating business simulations

[0545] The server trains a machine learning model using collected employee performance data and work records. This model is used to generate simulations of actual work processes. The simulations reproduce work processes in a virtual environment and aim to improve employee skills. The generated simulation games are deployed via web and mobile platforms.

[0546] 4. Measurement of effectiveness

[0547] The server collects project progress data in real time and automatically generates effectiveness measurement reports. These reports include metrics such as project results, KPIs, and ROI after project completion. The generated reports can be downloaded and reviewed by the user.

[0548] 5. CRM-based employee support

[0549] The server manages each employee's work history and skill set. Based on this, users can submit support requests through the user interface or chatbot. The server then suggests the most suitable resources and training based on the request, supporting the employee's work. It also records employee growth data and feedback, which are used to improve future support.

[0550] Specific example

[0551] For example, the server generates a business plan titled "Marketing Strategy for New Product Launch." In doing so, it considers past successes and trends when proposing the plan. The user then reviews this plan and adds feedback, such as "We should strengthen social media advertising to expand the target market." Based on this feedback, the server revises the plan and presents an optimized marketing strategy again.

[0552] In this way, this system improves the quality of business planning and enables efficient project progress management and effectiveness measurement. Furthermore, it provides appropriate support to individual employees, thereby improving the overall performance of the company.

[0553] The following describes the processing flow.

[0554] Business plan generation

[0555] Business plan generation process

[0556] Step 1:

[0557] Server: Collects historical project data and trend data from the company's database. Extracts and preprocesses data using SQL queries.

[0558] Step 2:

[0559] Server: Cleans the collected data, imputing missing values ​​and removing outliers. Normalizes the data and converts it into a format suitable for analysis.

[0560] Step 3:

[0561] Server: Inputs pre-processed data into a generative artificial intelligence (e.g., a natural language generation algorithm) to automatically generate new business plans.

[0562] Step 4:

[0563] Server: Prepares the generated business plan for display in the user interface. This includes generating dynamic web pages using HTML / CSS / JavaScript.

[0564] Step 5:

[0565] User: Log in to the user interface and review the generated business plan. View the specific proposal details and prepare feedback at this stage.

[0566] Step 6:

[0567] User: Enter any corrections or suggestions into the feedback form and submit it to the server.

[0568] Step 7:

[0569] Server: Analyzes user feedback and executes algorithms to revise or regenerate business plans. Generative artificial intelligence is used again in this process.

[0570] UX / Reporting Process

[0571] Step 1:

[0572] Server: Build applications that collect project progress and key metrics. Collect real-time data through APIs and database connections.

[0573] Step 2:

[0574] Server: Processes collected data and generates graphs and charts for dashboards. Uses libraries such as D3.js to visualize the data.

[0575] Step 3:

[0576] Terminal: Users access the dashboard to view project progress and reports. They can view detailed information and historical data by interacting with UI elements.

[0577] Step 4:

[0578] Server: Automatically generates reports based on user-specified time periods and parameters, and outputs them in PDF or Excel format.

[0579] Step 5:

[0580] Terminal: Download the generated report and print or share it as needed.

[0581] Business simulation generation process

[0582] Step 1:

[0583] Server: Collects employee performance data and work records. Data is collected via database queries and APIs.

[0584] Step 2:

[0585] Server: Trains machine learning models using collected data. Uses machine learning libraries such as TensorFlow and PyTorch.

[0586] Step 3:

[0587] Server: Generates business simulation scenarios using a pre-trained model. Designs specific business processes and storylines.

[0588] Step 4:

[0589] Server: Deploys the generated simulation game to a web or mobile platform. Hosts the application using AWS Lambda or Firebase.

[0590] Step 5:

[0591] User: Play simulation games and improve your skills. Collect gameplay logs and send them to the server.

[0592] Step 6:

[0593] Server: Analyzes collected gameplay data to identify areas for improvement in the simulation. Retrains the model as needed and generates improved scenarios.

[0594] Effectiveness measurement process

[0595] Step 1:

[0596] Server: Collects project progress data in real time. Data is automatically retrieved using APIs and webhooks.

[0597] Step 2:

[0598] Server: Analyzes data collected in real time and automatically generates effectiveness measurement reports based on that analysis. Inserts the analysis results into the report template.

[0599] Step 3:

[0600] User: View the generated performance measurement report on the dashboard. Download or print the report as needed.

[0601] CRM-based employee support process

[0602] Step 1:

[0603] Server: Collects each employee's work history and skill data and stores it in a database. Uses an API from the HR system.

[0604] Step 2:

[0605] Terminal: Provides an interface for employees to enter support requests. Requests are collected using chatbots or dedicated forms.

[0606] Step 3:

[0607] Server: Based on collected requests, it recommends the most suitable resources and training. It uses a matching algorithm to make appropriate suggestions.

[0608] Step 4:

[0609] Terminal: Employees use suggested resources to support their work. They refer to training materials and online guides.

[0610] Step 5:

[0611] Server: Records employee growth data and feedback, and uses it to improve future support. Analyzes feedback data to refine future proposals.

[0612] The above are the specific processing steps for carrying out the invention.

[0613] (Example 1)

[0614] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0615] In the current business planning and effectiveness measurement process, improving the quality of plans requires significant time and effort. Furthermore, the lack of centralized collection and analysis of accurate real-time data, and the absence of support tailored to individual employee skill sets, makes management cumbersome. This creates challenges in improving overall company performance.

[0616] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0617] In this invention, the server includes means for automatically generating new business plans based on past project data and trend data using a generation AI model, means for providing the generated business plans to users and receiving user feedback, and means for modifying or regenerating the generated business plans based on user feedback. This enables reduction of time and effort, accurate collection and analysis of real-time data, and centralized support for employees, which were problems in the past.

[0618] A "generative AI model" is an algorithm or program that uses generative artificial intelligence to automatically generate new information or content from given data.

[0619] A "prompt message" is an instruction given to a generative AI model to generate a specific answer or information.

[0620] "Past project data" refers to information and records about projects that a company has undertaken in the past, including, for example, project progress, results, and resources used.

[0621] "Trend data" refers to data that shows current market trends and changes, and includes, for example, social media posts, economic indicators, and industry news.

[0622] "User feedback" refers to suggestions for improvements, opinions, and additional requirements that users provide to the system.

[0623] A "template format" is a model used to format generated content or information into a specific form or structure.

[0624] A "dashboard" is an interface for centrally managing the visual display of project progress and data.

[0625] A "machine learning model" is a computer program that uses large amounts of data to train algorithms and then makes predictions, classifications, and generations based on new data.

[0626] A "virtual environment" is a digital space that simulates the physical environment of the real world, and is a system capable of reproducing various scenarios.

[0627] "Business simulation" is a system that aims to improve employee skills and operational efficiency by reproducing actual business processes in a virtual environment.

[0628] An "effectiveness measurement report" is a report created based on data collected to evaluate the results of a project.

[0629] This invention relates to a system that automates the planning, management, and effectiveness measurement of business plans within a company, and further provides support to individual employees. Specific embodiments of this system are described below.

[0630] System Configuration

[0631] The system mainly consists of the following components:

[0632] server

[0633] terminal

[0634] User

[0635] Data collection and analysis by server

[0636] The server collects historical project and trend data for companies through database queries (e.g., PostgreSQL) and APIs (e.g., Twitter API). The collected data is cleaned and preprocessed using Python scripts or ETL tools (e.g., Apache NiFi) and converted into an analyzable format.

[0637] Server-based generation of business plans

[0638] The server inputs pre-processed data into a machine learning model (e.g., GPT-4) and automatically generates new business plans using a generative AI model. The generated business plans are then formatted according to a template format.

[0639] Providing proposals and processing feedback

[0640] The server displays the generated business plan on a web interface. Users review the plan and provide feedback through the web interface. The server receives the user's feedback and uses the machine learning model again to revise or regenerate the plan.

[0641] User interface and display of real-time data

[0642] The server dynamically generates dashboards using HTML / CSS / JavaScript, visually displaying business plans and project progress to the user. Users can view real-time data on the dashboard.

[0643] Business simulation generation

[0644] The server trains machine learning models (e.g., TensorFlow or PyTorch) using employee performance data and work records, and generates work simulations in a virtual environment. The generated simulations are then provided through web and mobile applications.

[0645] Automatic generation of effectiveness measurements and reports

[0646] The server collects project progress data in real time and automatically generates performance measurement reports that include metrics such as KPIs and ROI. The generated reports are provided in a format that users can download and review.

[0647] Providing CRM-based employee support

[0648] The server manages each employee's work history and skill set, and allows users to submit support requests through an interface or chatbot. The server analyzes the requests and suggests the most suitable resources and training. It also records employee growth data and feedback to improve future support.

[0649] Specific example

[0650] For example, the server generates a business plan titled "Marketing Strategy for New Product Launch." In doing so, it considers past success stories and trend data to propose the plan. The user reviews this proposal and adds feedback such as, "We should strengthen social media advertising to expand the target market." Based on this feedback, the server revises the plan and presents an optimized marketing strategy again.

[0651] Example of a prompt

[0652] As an example of a prompt message to use when using a generative AI model, enter the following:

[0653] "Based on marketing data from the past five years, please generate the optimal marketing strategy for our new product launch."

[0654] In this way, this system can improve the quality of business planning and enable efficient project progress management and effectiveness measurement. Furthermore, it can provide appropriate support to individual employees, thereby improving the overall performance of the company.

[0655] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0656] Step 1: Data Collection

[0657] The server executes database queries (e.g., PostgreSQL) to collect historical project data for a company. It uses SQL queries as input to retrieve historical project data records. The output is the retrieved project data. It also calls APIs (e.g., Twitter API) to collect trend data. It uses API requests as input to retrieve trend data as output.

[0658] Step 2: Data preprocessing and analysis

[0659] The server performs data cleaning and preprocessing on the acquired data using the Python Pandas library. It uses the acquired project data and trend data as input, handling missing values ​​and performing data type conversions. The output is preprocessed, analyzable data.

[0660] Step 3: Automatic generation of business plans

[0661] The server inputs pre-processed data into a machine learning model (e.g., GPT-4) and uses a generative AI model to automatically generate new business plans. Using pre-processed data and prompt statements as input, it obtains the generated business plan as output. Specifically, it formats the generated text based on a template format.

[0662] Step 4: Providing a proposal

[0663] The server displays the generated business plan on a web interface. It uses a formatted business plan as input and displays the business plan on a web page as output. Specifically, it dynamically generates the page using HTML / CSS / JavaScript.

[0664] Step 5: Collecting user feedback

[0665] Users review business plans and input feedback through a web interface. The system receives user feedback as input and outputs feedback data. Specifically, users input information using a feedback form.

[0666] Step 6: Revise or regenerate the plan based on feedback

[0667] The server uses the machine learning model again to revise or regenerate the business plan based on user feedback. It uses user feedback and the previously generated business plan as input, and obtains the revised or regenerated business plan as output. Specifically, it inputs the prompt and feedback again into the machine learning model and formats the generated text.

[0668] Step 7: Real-time display of progress

[0669] The server collects project progress in real time and dynamically generates a dashboard using HTML / CSS / JavaScript. It uses project progress data as input and outputs an updated dashboard display. Specifically, it periodically runs a data collection script to reflect the latest data in the dashboard.

[0670] Step 8: Automatic generation of performance measurement reports

[0671] The server automatically generates effectiveness measurement reports based on the collected progress data. It uses project progress data, KPIs, and ROI metrics as input, and outputs an effectiveness measurement report. Specifically, it executes a report generation script to create the report in PDF or web format.

[0672] Step 9: Generate Business Simulation

[0673] The server trains a machine learning model using employee performance data and work records to generate business simulations in a virtual environment. It uses employee data and work records as input and obtains business simulations as output. Specifically, it inputs data into the virtual environment system and reproduces business processes based on scenarios.

[0674] Step 10: Employee support using CRM functions

[0675] Users enter support requests through an interface or chatbot. The server analyzes the request and suggests the most suitable resources and training. It uses employee work history and skill sets, along with the request content, as input, and outputs suggested resources and training content. Specifically, it analyzes the request and searches the database for appropriate resource information.

[0676] (Application Example 1)

[0677] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0678] In modern factories, improving production efficiency and developing flexible production plans are crucial challenges. However, traditional systems relied on manual plan generation and modification based on historical data and trends, which required significant time and effort. Furthermore, real-time monitoring of production efficiency and improving the accuracy of production plans through operational simulations were difficult. Additionally, there was a lack of training tailored to each employee's skill set, sometimes resulting in a decline in overall productivity.

[0679] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0680] In this invention, the server includes means for collecting and analyzing data from sensors and IoT devices in production equipment, means for regenerating or improving the manufacturing plan based on the feedback, and means for monitoring production efficiency in real time and generating effectiveness measurement reports. This enables real-time monitoring and analysis of production efficiency, rapid regeneration and improvement of the manufacturing plan based on feedback, and the suggestion of training optimized for each employee.

[0681] "Generative artificial intelligence" is an artificial intelligence technology that automatically generates business plans and other information based on past data and trend data.

[0682] "Methods for automatically generating business plans" refers to the part of a system that automatically generates business plans using generative artificial intelligence based on collected data.

[0683] "Means of receiving feedback" refers to the part of the system that receives and processes opinions and suggestions for revisions from users.

[0684] "Means for modifying or regenerating business plans" refers to the part of the system that modifies existing business plans or generates new ones based on user feedback.

[0685] "Means for dynamically generating and displaying user interfaces" refers to the part of a system that provides dynamically generated interfaces so that users can visually check the progress of business plans and projects.

[0686] "Means for collecting and analyzing project progress and results in real time" refers to the part of a system that collects data in real time as the project progresses and analyzes that data immediately.

[0687] "Method for automatically generating effectiveness measurement reports" refers to the part of the system that measures the effectiveness of a project based on collected real-time analysis results and automatically generates a report on it.

[0688] "Methods for automatically generating business simulations" refers to the part of a system that uses machine learning models to automatically generate simulations that virtually reproduce actual business operations.

[0689] "Means for collecting employees' work history and skill sets and recommending training" refers to the part of the system that records each employee's work history and skill set and then suggests training that is appropriate to their needs based on that information.

[0690] "Means for collecting and analyzing data from sensors and IoT devices" refers to the part of the system that collects data in real time from sensors and IoT devices within a factory and analyzes that data.

[0691] "Means for regenerating or improving manufacturing plans based on feedback" refers to the part of the system that incorporates user feedback to regenerate or improve existing manufacturing plans.

[0692] "A means of monitoring production efficiency in real time and generating effectiveness measurement reports" refers to the part of a system that monitors production efficiency within a factory in real time and automatically generates effectiveness measurement reports that evaluate that efficiency.

[0693] This invention relates to a system aimed at improving production efficiency in factories and automatically generating flexible production plans. The system of this invention consists of a server, terminals, and users, and is implemented using various hardware and software.

[0694] Data collection and analysis

[0695] The server collects data in real time from sensors and IoT devices on production equipment. This data includes production volume, machine operating status, and quality inspection results. The data is preprocessed and analyzed to become foundational data for generating business plans. A database management system (e.g., MySQL) is used to store and manage the data.

[0696] Automatic generation of business plans

[0697] The server automatically generates new business plans based on past project data and trend data using generative artificial intelligence. Machine learning algorithms (e.g., linear regression models) and natural language generation algorithms are used at this stage. The generated business plans are based on template formats and trend data.

[0698] Incorporating user feedback

[0699] The generated business plan is provided to the user via a terminal. The user reviews the proposed plan and provides any necessary feedback. The server then modifies or regenerates the business plan based on this feedback. This process generates an optimal business plan that meets the user's needs.

[0700] Production plan management and display

[0701] The server dynamically generates a user interface, visually displaying business plans and project progress to the user. This interface is created using technologies such as HTML / CSS / JavaScript, enabling real-time data display. The user reviews this information and decides on the next action as needed.

[0702] Effectiveness measurement and report generation

[0703] The server collects and analyzes project progress and results in real time and automatically generates effectiveness measurement reports. These reports include metrics such as KPIs and ROI, which users can review via their terminals.

[0704] Business simulation

[0705] The server trains a machine learning model using the collected data and automatically generates business simulations using this model. The simulations are run in a virtual environment and are intended to improve employee skills. The generated simulations are delivered via web and mobile platforms.

[0706] Employee support

[0707] The server manages each employee's work history and skill set, and based on this, suggests the most suitable resources and training. This ensures that each employee receives personalized support.

[0708] Specific example

[0709] For example, the server generates a business plan titled "Efficient Production Plan for a New Product." In doing so, it considers past production data and trends when proposing the plan. The user reviews this plan and adds feedback such as, "We need to adjust the production line to consider using a new material." Based on this feedback, the server revises the plan and presents a new, optimized production plan.

[0710] Examples of prompts for generative AI models

[0711] "Please generate a new production plan based on production data from the past three years. The feedback from management states that 'new materials should also be considered.' Please also generate a production plan that reflects this feedback."

[0712] By providing the entire system as an integrated service, the factory's production efficiency and flexibility are significantly improved. Furthermore, it contributes to improving employee skills and enhances overall performance.

[0713] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0714] Step 1:

[0715] The server collects data from sensors and IoT devices in the production equipment. This collected data includes production volume, machine operating status, and quality inspection results. This data is stored in a database (e.g., MySQL) and then cleaned and pre-processed. As a result, analyzable, formatted data can be obtained.

[0716] Step 2:

[0717] The server analyzes the formatted data and generates new business plans based on past project data and trend data. This process utilizes generative artificial intelligence technologies (e.g., machine learning algorithms and natural language generation algorithms). The business plans generated from the input data and the model are output.

[0718] Step 3:

[0719] The generated business plan is provided to the user via a terminal. The user reviews the provided business plan and enters any necessary feedback. This feedback includes specific revisions and additional requests. The user's input is sent to the server as feedback.

[0720] Step 4:

[0721] The server modifies or regenerates the business plan based on the feedback received. This process again utilizes generative artificial intelligence technology to automatically generate a new business plan that reflects the feedback. The output is the modified business plan.

[0722] Step 5:

[0723] The revised business plan is dynamically displayed on the user interface. The server generates a visually verifiable dashboard using technologies such as HTML / CSS / JavaScript. This user interface allows users to check the progress of business plans and projects in real time.

[0724] Step 6:

[0725] The server collects and analyzes project progress and results in real time. This process involves monitoring data from various sensors in real time to evaluate progress and performance. Performance metrics (e.g., KPIs and ROI) are used to assess the extent to which progress has been achieved. The evaluation results are provided as output.

[0726] Step 7:

[0727] The server automatically generates effectiveness measurement reports based on real-time analysis results. The reporting tool then uses the analysis results to generate reports based on metrics such as project completion outcomes, KPIs, and ROI. The generated reports are provided to the user to help them determine the necessary next actions.

[0728] Step 8:

[0729] The collected data is used to train a machine learning model, which is then used to automatically generate business simulations. These simulations replicate business processes in a virtual environment, aiming to improve employee skills. The generated business simulations are provided in a deployable format via web and mobile platforms.

[0730] Step 9:

[0731] The server collects each employee's work history and skill set, and recommends resources and training tailored to their needs. Based on the collected work history and skill set, it utilizes a matching algorithm to suggest the optimal training program. As a result, users are provided with individually optimized training plans.

[0732] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0733] This invention relates to a system that automates everything from business planning and progress management to effectiveness measurement and employee support, and further recognizes user emotions and incorporates them into the process. The following describes specific embodiments of this system.

[0734] System Configuration

[0735] The system mainly consists of the following components:

[0736] server

[0737] terminal

[0738] User

[0739] 1. Generating a business plan

[0740] 1.1 Data Collection and Analysis

[0741] The server collects historical project data and trend data for the company. This data is retrieved via database queries and APIs, and then preprocessed through data cleaning and normalization.

[0742] 1.2 Planning using generative artificial intelligence

[0743] The server inputs pre-processed data into a generative artificial intelligence (e.g., a natural language generation algorithm) to automatically generate new business plans. The generated plans are based on template formats and trend data.

[0744] 1.3 Providing proposals and feedback

[0745] The server displays the generated business plan in the user interface. The user reviews the plan and provides feedback. This feedback is sent to the server and used for regeneration or modification.

[0746] 2. Platform: UX / Reporting

[0747] The server dynamically generates the user interface, allowing users to visually check business plans and project progress. Technologies such as HTML / CSS / JavaScript are used to visualize real-time data. Users view the data on the dashboard and decide on necessary actions.

[0748] 3. Business simulation generation

[0749] The server collects employee performance data and work records, and trains a machine learning model based on this data. This model is then used to generate work simulation scenarios. These simulations become available on web and mobile platforms.

[0750] 4. Measurement of effectiveness

[0751] The server collects project progress data in real time and automatically generates effectiveness measurement reports. These reports include project outcomes, KPIs, ROI, and more. Users can download and review the generated reports.

[0752] 5. CRM-based employee support

[0753] The server manages each employee's work history and skill set. Users can submit support requests through chatbots or dedicated forms. Based on the request, the server recommends appropriate resources and training. Employee growth data and feedback are also recorded and used to improve future support.

[0754] 6. Integrating an emotion engine

[0755] 6.1 Emotion recognition

[0756] The server uses an emotion engine to recognize user emotions and understand the user's emotional state. This allows for the collection of user emotional data during feedback sessions and work activities.

[0757] 6.2 Adjusting business plans based on emotions

[0758] The server adjusts the content of the work plan as needed based on the user's emotional state recognized by the emotion engine. For example, if the user is feeling stressed, it will make suggestions to reduce the workload.

[0759] 6.3 Improving the quality of feedback through sentiment analysis

[0760] The server analyzes the emotions expressed by users during feedback and uses the results to revise or regenerate business plans. This results in the creation of business plans that are more user-satisfying.

[0761] 6.4 Emotion-based support and suggestions

[0762] The user interface provides appropriate support and suggestions based on the user's emotions. For example, if the user is tired, it might suggest taking a break, responding in a way that matches their feelings.

[0763] Specific example

[0764] For example, when generating a business plan for a new marketing strategy, the server generates the plan by referencing past success stories. When a user reviews this plan and provides feedback, the emotion engine recognizes the user's emotions and determines whether the user is satisfied or dissatisfied. If dissatisfaction is detected, the server analyzes the reason and improves the plan. In this process, the burden on the user is reduced and an optimized plan is created.

[0765] Thus, this system improves the quality of business planning and enables efficient project progress management and effectiveness measurement. Furthermore, by providing appropriate support to individual employees and responding in a way that is sensitive to user emotions, it aims to improve the overall performance of the company.

[0766] The following describes the processing flow.

[0767] Business plan generation

[0768] Business plan generation process

[0769] Step 1:

[0770] Server: Collects historical project data and trend data from the company's database. Extracts necessary data using SQL queries and preprocesses the data.

[0771] Step 2:

[0772] Server: Cleans the collected data, imputing missing values ​​and removing outliers. Performs normalization and feature extraction, and converts the data into an analyzable format.

[0773] Step 3:

[0774] Server: Pre-processed data is input into a generative artificial intelligence (natural language generation algorithm) to automatically generate new business plans. The generated business plans are based on a template format.

[0775] Proposal of plans and feedback

[0776] Step 4:

[0777] Server: Formats the generated business plan into a format that can be displayed in the user interface. Generates dynamic web pages using HTML / CSS / JavaScript.

[0778] Step 5:

[0779] User: Log in to the user interface and review the generated business plan. View the specific details and prepare feedback.

[0780] Step 6:

[0781] User: Enter any corrections or suggestions in the feedback form and submit it.

[0782] Step 7:

[0783] Server: Receives feedback submitted by users and uses generative artificial intelligence to revise or regenerate the plan.

[0784] Platform: UX / Reporting Process

[0785] Step 1:

[0786] Server: Build APIs and database connections to collect project progress and key metrics, and obtain real-time data.

[0787] Step 2:

[0788] Server: Processes collected data and generates dashboards for visualization. Uses libraries such as D3.js to display real-time data as graphs and charts.

[0789] Step 3:

[0790] Terminal: Users access the dashboard to view project progress and reports. They interact with UI elements to view detailed information and historical data.

[0791] Step 4:

[0792] Server: Automatically generates reports based on user-specified time periods and parameters, and outputs them in PDF or Excel format.

[0793] Step 5:

[0794] Terminal: Download the generated report and print or share it as needed.

[0795] Embedding an emotion engine

[0796] Emotion recognition process

[0797] Step 1:

[0798] Server: Activates the emotion engine to recognize user emotions. It extracts emotions from text or audio data using NLP techniques and machine learning models.

[0799] Step 2:

[0800] Device: When a user enters feedback or communication, that data is sent to the emotion engine.

[0801] Step 3:

[0802] Server: Analyzes the data received by the emotion engine to determine the user's emotional state. This information is recorded in the database.

[0803] Adjusting business plans based on emotions

[0804] Step 4:

[0805] Server: Reflects user emotion data, identified by the emotion engine, into business planning. For example, if a user is experiencing stress, it automatically adds suggestions to reduce their workload.

[0806] Analysis and reflection of feedback

[0807] Step 5:

[0808] Server: Analyzes the emotional state of users when they provide feedback to identify the quality of the feedback and areas for improvement. Based on these analysis results, the business plan is revised or regenerated.

[0809] Emotion-based support and suggestions

[0810] Step 6:

[0811] Terminal: Displays support and suggestions tailored to the user's emotions on the user interface. For example, if the user is tired, it suggests taking appropriate rest.

[0812] Step 7:

[0813] Server: Based on user growth data and emotional feedback, improve future business planning and support suggestions. This data will be used for future training and support.

[0814] Business simulation generation process

[0815] Step 1:

[0816] Server: Collects employee performance data and work records. Retrieves data via databases and APIs.

[0817] Step 2:

[0818] Server: Trains machine learning models using collected data. Uses libraries such as TensorFlow and PyTorch.

[0819] Step 3:

[0820] Server: Generates business simulation scenarios using a pre-trained model. Incorporates specific business processes and storylines into the scenarios.

[0821] Step 4:

[0822] Server: Deploys the generated simulation game to a web or mobile platform. Deployment is performed using AWS or Firebase.

[0823] Step 5:

[0824] User: Play simulation games and improve your skills. Collect gameplay logs and send them to the server.

[0825] Step 6:

[0826] Server: Analyzes collected gameplay data to identify areas for improvement in the simulation. Retrains the model to generate improved scenarios.

[0827] Effectiveness measurement process

[0828] Step 1:

[0829] Server: Collects project progress data in real time. Retrieves data via APIs and webhooks.

[0830] Step 2:

[0831] Server: Analyzes collected data in real time and automatically generates effectiveness measurement reports. Inserts data into report templates.

[0832] Step 3:

[0833] User: View the generated performance measurement report on the dashboard. Download and print the report as needed.

[0834] Employee support using CRM

[0835] Step 1:

[0836] Server: Collects each employee's work history and skill data and stores it in a database. Retrieves data from the HR system via API.

[0837] Step 2:

[0838] Terminal: Provides an interface for employees to enter support requests. Requests are collected using chatbots or dedicated forms.

[0839] Step 3:

[0840] Server: Recommends the most suitable resources and training based on the request. Uses a matching algorithm to make appropriate suggestions.

[0841] Step 4:

[0842] Terminal: Employees use suggested resources to support their work. They refer to training materials and online guides.

[0843] Step 5:

[0844] Server: Records employee growth data and feedback, and uses it to improve future support. Analyzes feedback data to refine future proposals.

[0845] The above are the specific processing steps for carrying out the invention.

[0846] (Example 2)

[0847] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0848] Traditional business management systems have struggled to comprehensively automate everything from business planning and progress management to performance measurement and employee support, and have been particularly poor at providing feedback and adjusting plans to reflect user sentiment. Furthermore, while efficiency and flexibility are required for real-time project management and providing individual employee support, no system adequately met these needs.

[0849] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for automatically generating new business plans based on past project data and trend data using generative artificial intelligence; means for providing the generated business plans to the user and receiving user feedback; means for modifying or regenerating the business plans based on user feedback; means for dynamically generating a user interface and visually displaying the progress of business plans and projects to the user; means for collecting and analyzing project progress and results in real time; means for automatically generating effectiveness measurement reports based on real-time analysis results; means for training a machine learning model using the collected data and automatically generating business simulations using this model; means for collecting each employee's work history and skill set and recommending resources and training according to their needs; means for collecting user emotional data during feedback and work using an emotion engine that recognizes the user's emotional state; and means for appropriately adjusting the content of the business plans based on the user's emotional state. This enables the streamlining and optimization of the entire business process, as well as flexible, high-quality feedback and planning adjustments that reflect user sentiment.

[0850] "Generative artificial intelligence" is a general term for artificial intelligence technologies that automatically generate new information and plans based on past data and trend information.

[0851] "Business planning" refers to the planning of projects and tasks that a company or organization will carry out, and its contents include objectives, means, schedules, and resource allocation.

[0852] "Feedback" refers to opinions and evaluations provided by users, which are useful information for improving services and projects.

[0853] "User interface" is a general term for the screens and operating methods that users use to operate a system and input or retrieve information.

[0854] "Real-time" refers to the process where data and information are processed instantly, and the results are reflected immediately.

[0855] An "effectiveness measurement report" is an automatically generated report used to evaluate the progress and results of a project or task, and includes metrics such as KPIs and ROI.

[0856] A "machine learning model" refers to an algorithm or computer program that analyzes large amounts of data and learns patterns and rules from it.

[0857] "Business simulation" refers to scenarios or simulators that reproduce actual business environments and situations, allowing users to virtually try them out.

[0858] "Work history" refers to records of an employee's past work and projects, and is used to analyze performance and trends.

[0859] A "skill set" refers to the collection of abilities and skills that each employee possesses, and its contents include specialized knowledge and experience.

[0860] "Resources" refer to management resources such as personnel, time, funds, and equipment, and how these are allocated and utilized is crucial.

[0861] An "emotion engine" refers to artificial intelligence technology or systems used to recognize and analyze a user's emotional state.

[0862] "Emotional data" refers to data that indicates a user's emotional state and is used for feedback and improving business processes.

[0863] A "template format" refers to a template for documents or data created based on a specific structure or format.

[0864] "Trend data" refers to data that shows past trends or patterns in phenomena, and is used for future predictions and planning.

[0865] Modes for carrying out the invention

[0866] This invention is a system that automates everything from business planning and progress management to effectiveness measurement and employee support, and further recognizes user emotions and reflects them in the process. The following describes a specific form for implementing the invention.

[0867] System Configuration

[0868] The system primarily consists of servers, terminals, and users. The server acts as a central management device, handling data collection, processing, analysis, generation, and presentation. Terminals are devices that users use to access the server and input or verify data. Users are the primary operators of the system, generating business plans and providing feedback.

[0869] Hardware and software to be used

[0870] Hardware: Servers (server machines with high-performance CPUs and sufficient memory), terminals (PCs, tablets, smartphones)

[0871] Software: Database management systems (DBMS), generative AI models (NLP algorithms), libraries for data collection and analysis (Pandas, Scikit-learn), sentiment engine (Google AI's Sentiment Analysis API), user interface technologies (HTML / CSS / JavaScript, D3.js)

[0872] Specific processing flow

[0873] The server first collects past project and trend data for the company using APIs and database queries. The collected data undergoes data cleaning and normalization, and is then input into a generative AI model (e.g., an NLP algorithm) to generate new business plans.

[0874] The generated business plan is applied to a template format and then provided to the user through the user interface. The user reviews it and provides feedback. This feedback is sent to the server and used for regeneration and modification.

[0875] The server displays real-time data using technologies such as HTML / CSS / JavaScript and D3.js to dynamically visualize business plans and project progress. Users can view this data on a dashboard and decide on necessary actions.

[0876] Furthermore, the server collects employee performance data and work records, and trains machine learning models based on this data. The trained models are then used to generate work simulation scenarios, enabling more realistic predictions and planning.

[0877] The system also includes a feature to collect project progress and results in real time and automatically generate effectiveness measurement reports. These reports include key metrics such as KPIs and ROI, and users can download the reports to view the details.

[0878] The server also manages each employee's work history and skill set, and recommends resources and training tailored to their needs. Users can submit support requests through chatbots or dedicated forms, and the server provides appropriate resources and training in response.

[0879] The emotion engine recognizes the user's emotional state and collects emotional data during feedback and work. The server has the function to adjust the content of work plans as needed based on the emotional data. This allows for suggestions to reduce the workload when the user is experiencing stress.

[0880] Specific example

[0881] For example, when generating a business plan for a new marketing strategy, the server collects data on successful case studies and market trends from the past year, and then uses an AI model to automatically generate the plan based on that data. When a user reviews this plan and provides feedback, the emotion engine recognizes the user's emotions, and the server analyzes those emotions to identify problems in the plan and makes corrections.

[0882] Example of a prompt

[0883] "Develop a new marketing strategy. Referencing successful case studies and trend data from the past year, analyze user sentiment, and propose the optimal plan."

[0884] This will improve the quality of business planning, streamline project management and effectiveness measurement, and enhance the quality of support for employees, thereby improving overall corporate performance.

[0885] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0886] Program processing flow

[0887] Step 1:

[0888] Data Acquisition and Preprocessing

[0889] The server collects historical project and trend data for companies using APIs and database queries. Input data includes sales performance and market trends for the past year. After collecting this data, the server performs data cleaning (imputing missing values ​​and removing outliers) and normalization (scaling the data). The output is a clean dataset.

[0890] Specific example of operation: The server executes an SQL query like "SELECT FROM ProjectData WHERE Year=2022" to collect data, and then uses the Python Pandas library to perform data cleaning and normalization.

[0891] Step 2:

[0892] Business plan generation

[0893] The server inputs pre-processed data into a generation AI model (such as an NLP algorithm) to automatically generate new business plans. The input is a clean dataset, and the output is a new business plan document.

[0894] Specific example of operation: The server outputs a log message saying "Generating new business plan using NLP model..." and generates a new business plan using an NLP algorithm.

[0895] Step 3:

[0896] Applying a project template

[0897] The server applies the generated business plan to a template format. The input is the generated business plan document, and the output is a plan document that fits the standard format.

[0898] Specific example of operation: The server outputs "Applying business plan to template format..." and applies the new plan to the template.

[0899] Step 4:

[0900] Providing a plan

[0901] The server displays business plans that fit a standard format in the user interface. The input is the plan document after applying the template, and the output is the business plan displayed on the user screen.

[0902] Specific example of operation: The server outputs a log message saying "Displaying business plan on user interface..." and generates and sends HTML content to the user's terminal.

[0903] Step 5:

[0904] Gathering feedback

[0905] The user reviews the displayed business plan and enters feedback. The input is the user's feedback comment, and the output is the feedback data sent to the server.

[0906] Specific example of operation: The user enters "I would like the sales target to be set a little higher" in the feedback field on the screen and presses the submit button.

[0907] Step 6:

[0908] Feedback analysis and regeneration

[0909] The server receives user feedback and uses an emotion engine to analyze the feedback content and emotional state. The input is the feedback data, and the output is the analysis results and a list of items that need correction.

[0910] Specific example of operation: The server outputs a log message saying "Received user feedback. Analyzing for plan adjustment..." and calls a sentiment analysis API to evaluate the feedback content.

[0911] Step 7:

[0912] Regenerate or modify the business plan.

[0913] The server regenerates or modifies the business plan based on the analysis results of the feedback. The input is the analysis results, and the output is the modified or regenerated business plan document.

[0914] Specific example of operation: The server uses the NLP model again and outputs a log message saying "Adjusting business plan based on user feedback..." to regenerate the plan.

[0915] Step 8:

[0916] Visual confirmation

[0917] The server redisplays the regenerated or modified business plan in the user interface. The input is the final business plan document, and the output is the updated business plan displayed on the user screen.

[0918] Specific example of operation: The server regenerates the revised business plan in HTML and displays it on the user's terminal.

[0919] Step 9:

[0920] Visualization of real-time progress

[0921] The server collects and visually displays project progress data in real time. The input is progress data, and the output is real-time graphs and charts displayed on the dashboard.

[0922] Specific example of operation: The server uses a JavaScript library (e.g., D3.js) to generate graphs in real time and display them on the user's dashboard.

[0923] Step 10:

[0924] Business simulation generation

[0925] The server collects employee performance data and work records, and uses this data to train a machine learning model. The input is performance data, and the output is the trained machine learning model.

[0926] Specific example of operation: The server outputs a log message saying "Training machine learning model with performance data..." and trains the model using Spark ML or TensorFlow.

[0927] Step 11:

[0928] Generating Simulation Scenarios

[0929] The server uses a trained model to generate business simulation scenarios. The input is the trained model, and the output is the simulation scenario.

[0930] Specific example of operation: The server outputs a log message saying "Generating business simulation scenarios...", generates a scenario, and provides it to the user.

[0931] Step 12:

[0932] Generating an effectiveness measurement report

[0933] The server automatically generates project results as effectiveness measurement reports. The input is project progress data, and the output is the effectiveness measurement report.

[0934] Specific example of operation: The server outputs a log message saying "Generating performance measurement report..." and generates a report in Excel or PDF format.

[0935] Step 13:

[0936] Report Provision

[0937] Users can view the generated performance measurement reports on the dashboard and download them as needed. The input is the performance measurement report, and the output is the report downloaded to the user's device.

[0938] Specific example of operation: A user clicks a file from the dashboard and downloads a PDF report.

[0939] Step 14:

[0940] Providing CRM-based employee support

[0941] The server manages each employee's work history and skill set, and provides appropriate resources and training based on user requests. Inputs include employee work history, skill set, and request data, while outputs include recommended resources and training plans.

[0942] Specific example of operation: The server outputs a log message saying "Recommending training resources for requested skill..." and provides relevant online courses and materials.

[0943] (Application Example 2)

[0944] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0945] Traditional business planning and project management systems automate tasks such as generating plans and measuring effectiveness based on past data, but they fail to consider the emotional state of users, potentially increasing worker stress and workload. Furthermore, real-time work instructions and dynamic task reallocation required complex settings and human intervention, making them inefficient. Additionally, a lack of individual support for factory workers could result in a decrease in overall productivity.

[0946] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically generating new business plans based on past project data and trend data using generative artificial intelligence; means for providing the generated business plans to the user and receiving user feedback; means for modifying or regenerating the generated business plans based on user feedback; means for dynamically generating a user interface and visually displaying the progress of business plans and projects to the user; means for collecting and analyzing project progress and results in real time; means for automatically generating effectiveness measurement reports based on real-time analysis results; means for training a machine learning model using the collected data and automatically generating business simulations using this model; means for collecting each employee's work history and skill set and recommending resources and training according to their needs; means for recognizing the user's emotional state using an emotion recognition engine and adjusting the content of the business plans based on the results; and means for providing work instructions in real time using a head-mounted display and performing dynamic work reallocation based on emotions. This allows for a reduction in the burden on workers by responding to user emotions, enabling improved work efficiency and increased productivity.

[0947] "Generative artificial intelligence" is an artificial intelligence technology that automatically generates new business plans by utilizing past project data and trend data.

[0948] "Providing to users" refers to the means of showing or presenting the generated business plan to users.

[0949] "Receiving user feedback" refers to the means of collecting opinions and reactions from users.

[0950] "Modifying or regenerating generated business plans" refers to the means of changing existing business plans or generating new ones based on user feedback.

[0951] "Dynamically generating a user interface" refers to a means of providing users with a visual display based on information and data that changes in real time.

[0952] "Collecting and analyzing project progress and results in real time" refers to methods for acquiring and analyzing project progress and results in real time.

[0953] "Automatically generating effectiveness measurement reports" refers to a method of automatically creating effectiveness measurement reports based on the progress and results of a project.

[0954] "Training a machine learning model" refers to the process of training a machine learning algorithm using collected data.

[0955] "Automatically generating business simulations" refers to a method of automatically creating business simulations using trained machine learning models.

[0956] "Recommending resources and training tailored to individual needs" means proposing necessary resources and training based on each employee's work history and skill set.

[0957] An "emotion recognition engine" is a technology used to recognize a user's emotional state.

[0958] "Adjusting the content of the business plan" refers to the means of appropriately changing the content of the business plan based on the perceived emotional state.

[0959] A "head-mounted display" is a display device worn on the head to display work instructions in real time.

[0960] "Dynamic task reallocation" refers to a method of redistributing tasks in response to real-time situations and emotional states.

[0961] This invention relates to a smart factory support system for assisting factory workers. This system enables automatic generation of work plans, optimization of work through emotion recognition, real-time instruction provision, and dynamic work redistribution.

[0962] System Configuration

[0963] This system consists of the following main components:

[0964] server

[0965] Head-mounted display (HMD)

[0966] User (factory worker)

[0967] server

[0968] Business plan generation

[0969] The server collects past project and trend data for companies, and performs data cleaning and normalization. This pre-processed data is then input into generative artificial intelligence (such as natural language generation algorithms) to automatically generate new business plans. The generated plans are based on template formats and trend data and are displayed in the user interface.

[0970] Feedback and Sentiment Recognition

[0971] The server collects feedback from users (workers) and recognizes their emotional state using an emotion recognition engine. Based on this information, it modifies or regenerates the business plan. Emotion recognition is performed by analyzing biometric data such as facial expressions and heart rate.

[0972] Providing real-time instructions

[0973] The server has the capability to provide work instructions in real time via a head-mounted display. If the emotion recognition engine detects the user's stress level, the server dynamically redistributes tasks to reduce the workload.

[0974] Effectiveness measurement

[0975] The server collects project progress and results in real time and automatically generates effectiveness measurement reports. These reports are displayed in the user interface for easy review.

[0976] Head-mounted display

[0977] A head-mounted display (HMD) is a device worn by workers that visually displays real-time work instructions and status reports. This allows workers to check work instructions without using their hands.

[0978] User

[0979] Factory workers wear head-mounted displays to view real-time work instructions provided by a server. Emotions and feedback during work are sent to the server via an emotion recognition engine and a chatbot.

[0980] Specific example

[0981] For example, when introducing a new production line at a factory, the server references data from similar past projects to generate a new work plan. As workers wearing HMDs (Head-Mounted Displays) follow the instructions, the emotion recognition engine detects stress in the workers, and the server automatically redistributes the workload to reduce the burden on the workers. After the work is completed, progress and effectiveness measurement reports are automatically generated.

[0982] Example of a prompt

[0983] "I want to develop an application that recognizes emotions in real time using an emotion recognition model and displays work instructions on a head-mounted display. The emotion recognition model to be used is "emotion_model.h5," which recognizes facial expressions. Work instructions will be obtained from AI_ENDPOINT. For example, if a worker is feeling stressed, the application should issue instructions to reduce their workload."

[0984] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0985] Step 1:

[0986] The server collects historical project data and trend data, and performs data cleaning and normalization. Specifically, it retrieves necessary data using database queries and APIs, and removes incomplete and duplicate data. It also preprocesses the data by converting it to a unified format. It receives project data from databases and external APIs as input and outputs preprocessed data.

[0987] Step 2:

[0988] The server inputs pre-processed data into a generative artificial intelligence (natural language generation algorithm) to automatically generate new business plans. This generation process generates the optimal business plan in natural language format based on the input data. It receives pre-processed data as input and obtains the generated business plan as output.

[0989] Step 3:

[0990] The server provides the generated business plan to the user through a user interface. The user reviews the provided business plan and enters feedback. The server receives the generated business plan data and the user's feedback as input and obtains an updated plan or feedback content as output.

[0991] Step 4:

[0992] The server modifies or regenerates business plans based on user feedback. This process includes analyzing the feedback and re-inputting the analysis results into a generative artificial intelligence to generate new business plans. It receives feedback data as input and obtains modified or regenerated business plans as output.

[0993] Step 5:

[0994] The server recognizes the user's emotional state using an emotion recognition engine. Specifically, it acquires the user's facial image using a camera and inputs it into the emotion recognition model to perform an emotional evaluation. It receives real-time facial image data as input and obtains the user's emotional state as output.

[0995] Step 6:

[0996] The server adjusts the content of the business plan based on the emotion recognition results. Specifically, if the user is experiencing stress, the generative artificial intelligence will make suggestions to reduce the workload. It receives emotion data as input and obtains an adjusted business plan as output.

[0997] Step 7:

[0998] The server provides work instructions in real time via a head-mounted display. It can also dynamically modify work instructions based on emotion recognition results. It receives adjusted work plans and emotion data as input and outputs instruction data for the head-mounted display.

[0999] Step 8:

[1000] The server collects project progress and results in real time and automatically generates effectiveness measurement reports. This process includes collecting and analyzing sensor data and log data, and generating reports. It receives project progress data as input and obtains effectiveness measurement reports as output.

[1001] Step 9:

[1002] The server collects each employee's work history and skill set, and recommends resources and training tailored to their needs. Specifically, it retrieves work history and skill set data from the database and generates appropriate resources and training plans. It takes employee data as input and outputs recommended resources and training plans.

[1003] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1004] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1005] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[1006] [Third Embodiment]

[1007] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[1008] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1009] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1010] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[1011] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1012] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1013] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1014] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1015] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1016] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1017] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1018] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[1019] This invention relates to a system that automates the planning, management, and effectiveness measurement of business plans within a company, and further provides support to individual employees. The embodiments of this system are described below.

[1020] System Configuration

[1021] The system mainly consists of the following components:

[1022] server

[1023] terminal

[1024] User

[1025] 1. Generating a business plan

[1026] 1.1 Data Collection and Analysis

[1027] The server collects historical project data and trend data for the company. This collection is performed via database queries and APIs. The collected data undergoes data cleaning and preprocessing before being converted into an analyzable format.

[1028] 1.2 Planning using generative artificial intelligence

[1029] The server automatically generates new business plans using pre-processed data through generative artificial intelligence. This generative AI employs, for example, machine learning models and natural language generation algorithms. At this stage, the generated business plans are based on template formats and trend data.

[1030] 1.3 Providing proposals and feedback

[1031] The server displays the generated business plan on the user interface.

[1032] Users can review the proposed project plan and provide feedback, including additional suggestions and revisions. This feedback is then sent back to the server, which uses it to revise or regenerate the project plan.

[1033] 2. Platform: UX / Reporting

[1034] The server dynamically generates the user interface, allowing users to check business plans and project progress. The displayed dashboards are created using technologies such as HTML / CSS / JavaScript. This allows users to visually view real-time data and make immediate decisions about necessary actions.

[1035] 3. Generating business simulations

[1036] The server trains a machine learning model using collected employee performance data and work records. This model is used to generate simulations of actual work processes. The simulations reproduce work processes in a virtual environment and aim to improve employee skills. The generated simulation games are deployed via web and mobile platforms.

[1037] 4. Measurement of effectiveness

[1038] The server collects project progress data in real time and automatically generates effectiveness measurement reports. These reports include metrics such as project results, KPIs, and ROI after project completion. The generated reports can be downloaded and reviewed by the user.

[1039] 5. CRM-based employee support

[1040] The server manages each employee's work history and skill set. Based on this, users can submit support requests through the user interface or chatbot. The server then suggests the most suitable resources and training based on the request, supporting the employee's work. It also records employee growth data and feedback, which are used to improve future support.

[1041] Specific example

[1042] For example, the server generates a business plan titled "Marketing Strategy for New Product Launch." In doing so, it considers past successes and trends when proposing the plan. The user then reviews this plan and adds feedback, such as "We should strengthen social media advertising to expand the target market." Based on this feedback, the server revises the plan and presents an optimized marketing strategy again.

[1043] In this way, this system improves the quality of business planning and enables efficient project progress management and effectiveness measurement. Furthermore, it provides appropriate support to individual employees, thereby improving the overall performance of the company.

[1044] The following describes the processing flow.

[1045] Business plan generation

[1046] Business plan generation process

[1047] Step 1:

[1048] Server: Collects historical project data and trend data from the company's database. Extracts and preprocesses data using SQL queries.

[1049] Step 2:

[1050] Server: Cleans the collected data, imputing missing values ​​and removing outliers. Normalizes the data and converts it into a format suitable for analysis.

[1051] Step 3:

[1052] Server: Inputs pre-processed data into a generative artificial intelligence (e.g., a natural language generation algorithm) to automatically generate new business plans.

[1053] Step 4:

[1054] Server: Prepares the generated business plan for display in the user interface. This includes generating dynamic web pages using HTML / CSS / JavaScript.

[1055] Step 5:

[1056] User: Log in to the user interface and review the generated business plan. View the specific proposal details and prepare feedback at this stage.

[1057] Step 6:

[1058] User: Enter any corrections or suggestions into the feedback form and submit it to the server.

[1059] Step 7:

[1060] Server: Analyzes user feedback and executes algorithms to revise or regenerate business plans. Generative artificial intelligence is used again in this process.

[1061] UX / Reporting Process

[1062] Step 1:

[1063] Server: Build applications that collect project progress and key metrics. Collect real-time data through APIs and database connections.

[1064] Step 2:

[1065] Server: Processes collected data and generates graphs and charts for dashboards. Uses libraries such as D3.js to visualize the data.

[1066] Step 3:

[1067] Terminal: Users access the dashboard to view project progress and reports. They can view detailed information and historical data by interacting with UI elements.

[1068] Step 4:

[1069] Server: Automatically generates reports based on user-specified time periods and parameters, and outputs them in PDF or Excel format.

[1070] Step 5:

[1071] Terminal: Download the generated report and print or share it as needed.

[1072] Business simulation generation process

[1073] Step 1:

[1074] Server: Collects employee performance data and work records. Data is collected via database queries and APIs.

[1075] Step 2:

[1076] Server: Trains machine learning models using collected data. Uses machine learning libraries such as TensorFlow and PyTorch.

[1077] Step 3:

[1078] Server: Generates business simulation scenarios using a pre-trained model. Designs specific business processes and storylines.

[1079] Step 4:

[1080] Server: Deploys the generated simulation game to a web or mobile platform. Hosts the application using AWS Lambda or Firebase.

[1081] Step 5:

[1082] User: Play simulation games and improve your skills. Collect gameplay logs and send them to the server.

[1083] Step 6:

[1084] Server: Analyzes collected gameplay data to identify areas for improvement in the simulation. Retrains the model as needed and generates improved scenarios.

[1085] Effectiveness measurement process

[1086] Step 1:

[1087] Server: Collects project progress data in real time. Data is automatically retrieved using APIs and webhooks.

[1088] Step 2:

[1089] Server: Analyzes data collected in real time and automatically generates effectiveness measurement reports based on that analysis. Inserts the analysis results into the report template.

[1090] Step 3:

[1091] User: View the generated performance measurement report on the dashboard. Download or print the report as needed.

[1092] CRM-based employee support process

[1093] Step 1:

[1094] Server: Collects each employee's work history and skill data and stores it in a database. Uses an API from the HR system.

[1095] Step 2:

[1096] Terminal: Provides an interface for employees to enter support requests. Requests are collected using chatbots or dedicated forms.

[1097] Step 3:

[1098] Server: Based on collected requests, it recommends the most suitable resources and training. It uses a matching algorithm to make appropriate suggestions.

[1099] Step 4:

[1100] Terminal: Employees use suggested resources to support their work. They refer to training materials and online guides.

[1101] Step 5:

[1102] Server: Records employee growth data and feedback, and uses it to improve future support. Analyzes feedback data to refine future proposals.

[1103] The above are the specific processing steps for carrying out the invention.

[1104] (Example 1)

[1105] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1106] In the current business planning and effectiveness measurement process, improving the quality of plans requires significant time and effort. Furthermore, the lack of centralized collection and analysis of accurate real-time data, and the absence of support tailored to individual employee skill sets, makes management cumbersome. This creates challenges in improving overall company performance.

[1107] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1108] In this invention, the server includes means for automatically generating new business plans based on past project data and trend data using a generation AI model, means for providing the generated business plans to users and receiving user feedback, and means for modifying or regenerating the generated business plans based on user feedback. This enables reduction of time and effort, accurate collection and analysis of real-time data, and centralized support for employees, which were problems in the past.

[1109] A "generative AI model" is an algorithm or program that uses generative artificial intelligence to automatically generate new information or content from given data.

[1110] A "prompt message" is an instruction given to a generative AI model to generate a specific answer or information.

[1111] "Past project data" refers to information and records about projects that a company has undertaken in the past, including, for example, project progress, results, and resources used.

[1112] "Trend data" refers to data that shows current market trends and changes, and includes, for example, social media posts, economic indicators, and industry news.

[1113] "User feedback" refers to suggestions for improvements, opinions, and additional requirements that users provide to the system.

[1114] A "template format" is a model used to format generated content or information into a specific form or structure.

[1115] A "dashboard" is an interface for centrally managing the visual display of project progress and data.

[1116] A "machine learning model" is a computer program that uses large amounts of data to train algorithms and then makes predictions, classifications, and generations based on new data.

[1117] A "virtual environment" is a digital space that simulates the physical environment of the real world, and is a system capable of reproducing various scenarios.

[1118] "Business simulation" is a system that aims to improve employee skills and operational efficiency by reproducing actual business processes in a virtual environment.

[1119] An "effectiveness measurement report" is a report created based on data collected to evaluate the results of a project.

[1120] This invention relates to a system that automates the planning, management, and effectiveness measurement of business plans within a company, and further provides support to individual employees. Specific embodiments of this system are described below.

[1121] System Configuration

[1122] The system mainly consists of the following components:

[1123] server

[1124] terminal

[1125] User

[1126] Data collection and analysis by server

[1127] The server collects historical project and trend data for companies through database queries (e.g., PostgreSQL) and APIs (e.g., Twitter API). The collected data is cleaned and preprocessed using Python scripts or ETL tools (e.g., Apache NiFi) and converted into an analyzable format.

[1128] Server-based generation of business plans

[1129] The server inputs pre-processed data into a machine learning model (e.g., GPT-4) and automatically generates new business plans using a generative AI model. The generated business plans are then formatted according to a template format.

[1130] Providing proposals and processing feedback

[1131] The server displays the generated business plan on a web interface. Users review the plan and provide feedback through the web interface. The server receives the user's feedback and uses the machine learning model again to revise or regenerate the plan.

[1132] User interface and display of real-time data

[1133] The server dynamically generates dashboards using HTML / CSS / JavaScript, visually displaying business plans and project progress to the user. Users can view real-time data on the dashboard.

[1134] Business simulation generation

[1135] The server trains machine learning models (e.g., TensorFlow or PyTorch) using employee performance data and work records, and generates work simulations in a virtual environment. The generated simulations are then provided through web and mobile applications.

[1136] Automatic generation of effectiveness measurements and reports

[1137] The server collects project progress data in real time and automatically generates performance measurement reports that include metrics such as KPIs and ROI. The generated reports are provided in a format that users can download and review.

[1138] Providing CRM-based employee support

[1139] The server manages each employee's work history and skill set, and allows users to submit support requests through an interface or chatbot. The server analyzes the requests and suggests the most suitable resources and training. It also records employee growth data and feedback to improve future support.

[1140] Specific example

[1141] For example, the server generates a business plan titled "Marketing Strategy for New Product Launch." In doing so, it considers past success stories and trend data to propose the plan. The user reviews this proposal and adds feedback such as, "We should strengthen social media advertising to expand the target market." Based on this feedback, the server revises the plan and presents an optimized marketing strategy again.

[1142] Example of a prompt

[1143] As an example of a prompt message to use when using a generative AI model, enter the following:

[1144] "Based on marketing data from the past five years, please generate the optimal marketing strategy for our new product launch."

[1145] In this way, this system can improve the quality of business planning and enable efficient project progress management and effectiveness measurement. Furthermore, it can provide appropriate support to individual employees, thereby improving the overall performance of the company.

[1146] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1147] Step 1: Data Collection

[1148] The server executes database queries (e.g., PostgreSQL) to collect historical project data for a company. It uses SQL queries as input to retrieve historical project data records. The output is the retrieved project data. It also calls APIs (e.g., Twitter API) to collect trend data. It uses API requests as input to retrieve trend data as output.

[1149] Step 2: Data preprocessing and analysis

[1150] The server performs data cleaning and preprocessing on the acquired data using the Python Pandas library. It uses the acquired project data and trend data as input, handling missing values ​​and performing data type conversions. The output is preprocessed, analyzable data.

[1151] Step 3: Automatic generation of business plans

[1152] The server inputs pre-processed data into a machine learning model (e.g., GPT-4) and uses a generative AI model to automatically generate new business plans. Using pre-processed data and prompt statements as input, it obtains the generated business plan as output. Specifically, it formats the generated text based on a template format.

[1153] Step 4: Providing a proposal

[1154] The server displays the generated business plan on a web interface. It uses a formatted business plan as input and displays the business plan on a web page as output. Specifically, it dynamically generates the page using HTML / CSS / JavaScript.

[1155] Step 5: Collecting user feedback

[1156] Users review business plans and input feedback through a web interface. The system receives user feedback as input and outputs feedback data. Specifically, users input information using a feedback form.

[1157] Step 6: Revise or regenerate the plan based on feedback

[1158] The server uses the machine learning model again to revise or regenerate the business plan based on user feedback. It uses user feedback and the previously generated business plan as input, and obtains the revised or regenerated business plan as output. Specifically, it inputs the prompt and feedback again into the machine learning model and formats the generated text.

[1159] Step 7: Real-time display of progress

[1160] The server collects project progress in real time and dynamically generates a dashboard using HTML / CSS / JavaScript. It uses project progress data as input and outputs an updated dashboard display. Specifically, it periodically runs a data collection script to reflect the latest data in the dashboard.

[1161] Step 8: Automatic generation of performance measurement reports

[1162] The server automatically generates effectiveness measurement reports based on the collected progress data. It uses project progress data, KPIs, and ROI metrics as input, and outputs an effectiveness measurement report. Specifically, it executes a report generation script to create the report in PDF or web format.

[1163] Step 9: Generate Business Simulation

[1164] The server trains a machine learning model using employee performance data and work records to generate business simulations in a virtual environment. It uses employee data and work records as input and obtains business simulations as output. Specifically, it inputs data into the virtual environment system and reproduces business processes based on scenarios.

[1165] Step 10: Employee support using CRM functions

[1166] Users enter support requests through an interface or chatbot. The server analyzes the request and suggests the most suitable resources and training. It uses employee work history and skill sets, along with the request content, as input, and outputs suggested resources and training content. Specifically, it analyzes the request and searches the database for appropriate resource information.

[1167] (Application Example 1)

[1168] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1169] In modern factories, improving production efficiency and developing flexible production plans are crucial challenges. However, traditional systems relied on manual plan generation and modification based on historical data and trends, which required significant time and effort. Furthermore, real-time monitoring of production efficiency and improving the accuracy of production plans through operational simulations were difficult. Additionally, there was a lack of training tailored to each employee's skill set, sometimes resulting in a decline in overall productivity.

[1170] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1171] In this invention, the server includes means for collecting and analyzing data from sensors and IoT devices in production equipment, means for regenerating or improving the manufacturing plan based on the feedback, and means for monitoring production efficiency in real time and generating effectiveness measurement reports. This enables real-time monitoring and analysis of production efficiency, rapid regeneration and improvement of the manufacturing plan based on feedback, and the suggestion of training optimized for each employee.

[1172] "Generative artificial intelligence" is an artificial intelligence technology that automatically generates business plans and other information based on past data and trend data.

[1173] "Methods for automatically generating business plans" refers to the part of a system that automatically generates business plans using generative artificial intelligence based on collected data.

[1174] "Means of receiving feedback" refers to the part of the system that receives and processes opinions and suggestions for revisions from users.

[1175] "Means for modifying or regenerating business plans" refers to the part of the system that modifies existing business plans or generates new ones based on user feedback.

[1176] "Means for dynamically generating and displaying user interfaces" refers to the part of a system that provides dynamically generated interfaces so that users can visually check the progress of business plans and projects.

[1177] "Means for collecting and analyzing project progress and results in real time" refers to the part of a system that collects data in real time as the project progresses and analyzes that data immediately.

[1178] "Method for automatically generating effectiveness measurement reports" refers to the part of the system that measures the effectiveness of a project based on collected real-time analysis results and automatically generates a report on it.

[1179] "Methods for automatically generating business simulations" refers to the part of a system that uses machine learning models to automatically generate simulations that virtually reproduce actual business operations.

[1180] "Means for collecting employees' work history and skill sets and recommending training" refers to the part of the system that records each employee's work history and skill set and then suggests training that is appropriate to their needs based on that information.

[1181] "Means for collecting and analyzing data from sensors and IoT devices" refers to the part of the system that collects data in real time from sensors and IoT devices within a factory and analyzes that data.

[1182] "Means for regenerating or improving manufacturing plans based on feedback" refers to the part of the system that incorporates user feedback to regenerate or improve existing manufacturing plans.

[1183] "A means of monitoring production efficiency in real time and generating effectiveness measurement reports" refers to the part of a system that monitors production efficiency within a factory in real time and automatically generates effectiveness measurement reports that evaluate that efficiency.

[1184] This invention relates to a system aimed at improving production efficiency in factories and automatically generating flexible production plans. The system of this invention consists of a server, terminals, and users, and is implemented using various hardware and software.

[1185] Data collection and analysis

[1186] The server collects data in real time from sensors and IoT devices on production equipment. This data includes production volume, machine operating status, and quality inspection results. The data is preprocessed and analyzed to become foundational data for generating business plans. A database management system (e.g., MySQL) is used to store and manage the data.

[1187] Automatic generation of business plans

[1188] The server automatically generates new business plans based on past project data and trend data using generative artificial intelligence. Machine learning algorithms (e.g., linear regression models) and natural language generation algorithms are used at this stage. The generated business plans are based on template formats and trend data.

[1189] Incorporating user feedback

[1190] The generated business plan is provided to the user via a terminal. The user reviews the proposed plan and provides any necessary feedback. The server then modifies or regenerates the business plan based on this feedback. This process generates an optimal business plan that meets the user's needs.

[1191] Production plan management and display

[1192] The server dynamically generates a user interface, visually displaying business plans and project progress to the user. This interface is created using technologies such as HTML / CSS / JavaScript, enabling real-time data display. The user reviews this information and decides on the next action as needed.

[1193] Effectiveness measurement and report generation

[1194] The server collects and analyzes project progress and results in real time and automatically generates effectiveness measurement reports. These reports include metrics such as KPIs and ROI, which users can review via their terminals.

[1195] Business simulation

[1196] The server trains a machine learning model using the collected data and automatically generates business simulations using this model. The simulations are run in a virtual environment and are intended to improve employee skills. The generated simulations are delivered via web and mobile platforms.

[1197] Employee support

[1198] The server manages each employee's work history and skill set, and based on this, suggests the most suitable resources and training. This ensures that each employee receives personalized support.

[1199] Specific example

[1200] For example, the server generates a business plan titled "Efficient Production Plan for a New Product." In doing so, it considers past production data and trends when proposing the plan. The user reviews this plan and adds feedback such as, "We need to adjust the production line to consider using a new material." Based on this feedback, the server revises the plan and presents a new, optimized production plan.

[1201] Examples of prompts for generative AI models

[1202] "Please generate a new production plan based on production data from the past three years. The feedback from management states that 'new materials should also be considered.' Please also generate a production plan that reflects this feedback."

[1203] By providing the entire system as an integrated service, the factory's production efficiency and flexibility are significantly improved. Furthermore, it contributes to improving employee skills and enhances overall performance.

[1204] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1205] Step 1:

[1206] The server collects data from sensors and IoT devices in the production equipment. This collected data includes production volume, machine operating status, and quality inspection results. This data is stored in a database (e.g., MySQL) and then cleaned and pre-processed. As a result, analyzable, formatted data can be obtained.

[1207] Step 2:

[1208] The server analyzes the formatted data and generates new business plans based on past project data and trend data. This process utilizes generative artificial intelligence technologies (e.g., machine learning algorithms and natural language generation algorithms). The business plans generated from the input data and the model are output.

[1209] Step 3:

[1210] The generated business plan is provided to the user via a terminal. The user reviews the provided business plan and enters any necessary feedback. This feedback includes specific revisions and additional requests. The user's input is sent to the server as feedback.

[1211] Step 4:

[1212] The server modifies or regenerates the business plan based on the feedback received. This process again utilizes generative artificial intelligence technology to automatically generate a new business plan that reflects the feedback. The output is the modified business plan.

[1213] Step 5:

[1214] The revised business plan is dynamically displayed on the user interface. The server generates a visually verifiable dashboard using technologies such as HTML / CSS / JavaScript. This user interface allows users to check the progress of business plans and projects in real time.

[1215] Step 6:

[1216] The server collects and analyzes project progress and results in real time. This process involves monitoring data from various sensors in real time to evaluate progress and performance. Performance metrics (e.g., KPIs and ROI) are used to assess the extent to which progress has been achieved. The evaluation results are provided as output.

[1217] Step 7:

[1218] The server automatically generates effectiveness measurement reports based on real-time analysis results. The reporting tool then uses the analysis results to generate reports based on metrics such as project completion outcomes, KPIs, and ROI. The generated reports are provided to the user to help them determine the necessary next actions.

[1219] Step 8:

[1220] The collected data is used to train a machine learning model, which is then used to automatically generate business simulations. These simulations replicate business processes in a virtual environment, aiming to improve employee skills. The generated business simulations are provided in a deployable format via web and mobile platforms.

[1221] Step 9:

[1222] The server collects each employee's work history and skill set, and recommends resources and training tailored to their needs. Based on the collected work history and skill set, it utilizes a matching algorithm to suggest the optimal training program. As a result, users are provided with individually optimized training plans.

[1223] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1224] This invention relates to a system that automates everything from business planning and progress management to effectiveness measurement and employee support, and further recognizes user emotions and incorporates them into the process. The following describes specific embodiments of this system.

[1225] System Configuration

[1226] The system mainly consists of the following components:

[1227] server

[1228] terminal

[1229] User

[1230] 1. Generating a business plan

[1231] 1.1 Data Collection and Analysis

[1232] The server collects historical project data and trend data for the company. This data is retrieved via database queries and APIs, and then preprocessed through data cleaning and normalization.

[1233] 1.2 Planning using generative artificial intelligence

[1234] The server inputs pre-processed data into a generative artificial intelligence (e.g., a natural language generation algorithm) to automatically generate new business plans. The generated plans are based on template formats and trend data.

[1235] 1.3 Providing proposals and feedback

[1236] The server displays the generated business plan in the user interface. The user reviews the plan and provides feedback. This feedback is sent to the server and used for regeneration or modification.

[1237] 2. Platform: UX / Reporting

[1238] The server dynamically generates the user interface, allowing users to visually check business plans and project progress. Technologies such as HTML / CSS / JavaScript are used to visualize real-time data. Users view the data on the dashboard and decide on necessary actions.

[1239] 3. Business simulation generation

[1240] The server collects employee performance data and work records, and trains a machine learning model based on this data. This model is then used to generate work simulation scenarios. These simulations become available on web and mobile platforms.

[1241] 4. Measurement of effectiveness

[1242] The server collects project progress data in real time and automatically generates effectiveness measurement reports. These reports include project outcomes, KPIs, ROI, and more. Users can download and review the generated reports.

[1243] 5. CRM-based employee support

[1244] The server manages each employee's work history and skill set. Users can submit support requests through chatbots or dedicated forms. Based on the request, the server recommends appropriate resources and training. Employee growth data and feedback are also recorded and used to improve future support.

[1245] 6. Integrating an emotion engine

[1246] 6.1 Emotion recognition

[1247] The server uses an emotion engine to recognize user emotions and understand the user's emotional state. This allows for the collection of user emotional data during feedback sessions and work activities.

[1248] 6.2 Adjusting business plans based on emotions

[1249] The server adjusts the content of the work plan as needed based on the user's emotional state recognized by the emotion engine. For example, if the user is feeling stressed, it will make suggestions to reduce the workload.

[1250] 6.3 Improving the quality of feedback through sentiment analysis

[1251] The server analyzes the emotions expressed by users during feedback and uses the results to revise or regenerate business plans. This results in the creation of business plans that are more user-satisfying.

[1252] 6.4 Emotion-based support and suggestions

[1253] The user interface provides appropriate support and suggestions based on the user's emotions. For example, if the user is tired, it might suggest taking a break, responding in a way that matches their feelings.

[1254] Specific example

[1255] For example, when generating a business plan for a new marketing strategy, the server generates the plan by referencing past success stories. When a user reviews this plan and provides feedback, the emotion engine recognizes the user's emotions and determines whether the user is satisfied or dissatisfied. If dissatisfaction is detected, the server analyzes the reason and improves the plan. In this process, the burden on the user is reduced and an optimized plan is created.

[1256] Thus, this system improves the quality of business planning and enables efficient project progress management and effectiveness measurement. Furthermore, by providing appropriate support to individual employees and responding in a way that is sensitive to user emotions, it aims to improve the overall performance of the company.

[1257] The following describes the processing flow.

[1258] Business plan generation

[1259] Business plan generation process

[1260] Step 1:

[1261] Server: Collects historical project data and trend data from the company's database. Extracts necessary data using SQL queries and preprocesses the data.

[1262] Step 2:

[1263] Server: Cleans the collected data, imputing missing values ​​and removing outliers. Performs normalization and feature extraction, and converts the data into an analyzable format.

[1264] Step 3:

[1265] Server: Pre-processed data is input into a generative artificial intelligence (natural language generation algorithm) to automatically generate new business plans. The generated business plans are based on a template format.

[1266] Proposal of plans and feedback

[1267] Step 4:

[1268] Server: Formats the generated business plan into a format that can be displayed in the user interface. Generates dynamic web pages using HTML / CSS / JavaScript.

[1269] Step 5:

[1270] User: Log in to the user interface and review the generated business plan. View the specific details and prepare feedback.

[1271] Step 6:

[1272] User: Enter any corrections or suggestions in the feedback form and submit it.

[1273] Step 7:

[1274] Server: Receives feedback submitted by users and uses generative artificial intelligence to revise or regenerate the plan.

[1275] Platform: UX / Reporting Process

[1276] Step 1:

[1277] Server: Build APIs and database connections to collect project progress and key metrics, and obtain real-time data.

[1278] Step 2:

[1279] Server: Processes collected data and generates dashboards for visualization. Uses libraries such as D3.js to display real-time data as graphs and charts.

[1280] Step 3:

[1281] Terminal: Users access the dashboard to view project progress and reports. They interact with UI elements to view detailed information and historical data.

[1282] Step 4:

[1283] Server: Automatically generates reports based on user-specified time periods and parameters, and outputs them in PDF or Excel format.

[1284] Step 5:

[1285] Terminal: Download the generated report and print or share it as needed.

[1286] Embedding an emotion engine

[1287] Emotion recognition process

[1288] Step 1:

[1289] Server: Activates the emotion engine to recognize user emotions. It extracts emotions from text or audio data using NLP techniques and machine learning models.

[1290] Step 2:

[1291] Device: When a user enters feedback or communication, that data is sent to the emotion engine.

[1292] Step 3:

[1293] Server: Analyzes the data received by the emotion engine to determine the user's emotional state. This information is recorded in the database.

[1294] Adjusting business plans based on emotions

[1295] Step 4:

[1296] Server: Reflects user emotion data, identified by the emotion engine, into business planning. For example, if a user is experiencing stress, it automatically adds suggestions to reduce their workload.

[1297] Analysis and reflection of feedback

[1298] Step 5:

[1299] Server: Analyzes the emotional state of users when they provide feedback to identify the quality of the feedback and areas for improvement. Based on these analysis results, the business plan is revised or regenerated.

[1300] Emotion-based support and suggestions

[1301] Step 6:

[1302] Terminal: Displays support and suggestions tailored to the user's emotions on the user interface. For example, if the user is tired, it suggests taking appropriate rest.

[1303] Step 7:

[1304] Server: Based on user growth data and emotional feedback, improve future business planning and support suggestions. This data will be used for future training and support.

[1305] Business simulation generation process

[1306] Step 1:

[1307] Server: Collects employee performance data and work records. Retrieves data via databases and APIs.

[1308] Step 2:

[1309] Server: Trains machine learning models using collected data. Uses libraries such as TensorFlow and PyTorch.

[1310] Step 3:

[1311] Server: Generates business simulation scenarios using a pre-trained model. Incorporates specific business processes and storylines into the scenarios.

[1312] Step 4:

[1313] Server: Deploys the generated simulation game to a web or mobile platform. Deployment is performed using AWS or Firebase.

[1314] Step 5:

[1315] User: Play simulation games and improve your skills. Collect gameplay logs and send them to the server.

[1316] Step 6:

[1317] Server: Analyzes collected gameplay data to identify areas for improvement in the simulation. Retrains the model to generate improved scenarios.

[1318] Effectiveness measurement process

[1319] Step 1:

[1320] Server: Collects project progress data in real time. Retrieves data via APIs and webhooks.

[1321] Step 2:

[1322] Server: Analyzes collected data in real time and automatically generates effectiveness measurement reports. Inserts data into report templates.

[1323] Step 3:

[1324] User: View the generated performance measurement report on the dashboard. Download and print the report as needed.

[1325] Employee support using CRM

[1326] Step 1:

[1327] Server: Collects each employee's work history and skill data and stores it in a database. Retrieves data from the HR system via API.

[1328] Step 2:

[1329] Terminal: Provides an interface for employees to enter support requests. Requests are collected using chatbots or dedicated forms.

[1330] Step 3:

[1331] Server: Recommends the most suitable resources and training based on the request. Uses a matching algorithm to make appropriate suggestions.

[1332] Step 4:

[1333] Terminal: Employees use suggested resources to support their work. They refer to training materials and online guides.

[1334] Step 5:

[1335] Server: Records employee growth data and feedback, and uses it to improve future support. Analyzes feedback data to refine future proposals.

[1336] The above are the specific processing steps for carrying out the invention.

[1337] (Example 2)

[1338] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1339] Traditional business management systems have struggled to comprehensively automate everything from business planning and progress management to performance measurement and employee support, and have been particularly poor at providing feedback and adjusting plans to reflect user sentiment. Furthermore, while efficiency and flexibility are required for real-time project management and providing individual employee support, no system adequately met these needs.

[1340] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for automatically generating new business plans based on past project data and trend data using generative artificial intelligence; means for providing the generated business plans to the user and receiving user feedback; means for modifying or regenerating the business plans based on user feedback; means for dynamically generating a user interface and visually displaying the progress of business plans and projects to the user; means for collecting and analyzing project progress and results in real time; means for automatically generating effectiveness measurement reports based on real-time analysis results; means for training a machine learning model using the collected data and automatically generating business simulations using this model; means for collecting each employee's work history and skill set and recommending resources and training according to their needs; means for collecting user emotional data during feedback and work using an emotion engine that recognizes the user's emotional state; and means for appropriately adjusting the content of the business plans based on the user's emotional state. This enables the streamlining and optimization of the entire business process, as well as flexible, high-quality feedback and planning adjustments that reflect user sentiment.

[1341] "Generative artificial intelligence" is a general term for artificial intelligence technologies that automatically generate new information and plans based on past data and trend information.

[1342] "Business planning" refers to the planning of projects and tasks that a company or organization will carry out, and its contents include objectives, means, schedules, and resource allocation.

[1343] "Feedback" refers to opinions and evaluations provided by users, which are useful information for improving services and projects.

[1344] "User interface" is a general term for the screens and operating methods that users use to operate a system and input or retrieve information.

[1345] "Real-time" refers to the process where data and information are processed instantly, and the results are reflected immediately.

[1346] An "effectiveness measurement report" is an automatically generated report used to evaluate the progress and results of a project or task, and includes metrics such as KPIs and ROI.

[1347] A "machine learning model" refers to an algorithm or computer program that analyzes large amounts of data and learns patterns and rules from it.

[1348] "Business simulation" refers to scenarios or simulators that reproduce actual business environments and situations, allowing users to virtually try them out.

[1349] "Work history" refers to records of an employee's past work and projects, and is used to analyze performance and trends.

[1350] A "skill set" refers to the collection of abilities and skills that each employee possesses, and its contents include specialized knowledge and experience.

[1351] "Resources" refer to management resources such as personnel, time, funds, and equipment, and how these are allocated and utilized is crucial.

[1352] An "emotion engine" refers to artificial intelligence technology or systems used to recognize and analyze a user's emotional state.

[1353] "Emotional data" refers to data that indicates a user's emotional state and is used for feedback and improving business processes.

[1354] A "template format" refers to a template for documents or data created based on a specific structure or format.

[1355] "Trend data" refers to data that shows past trends or patterns in phenomena, and is used for future predictions and planning.

[1356] Modes for carrying out the invention

[1357] This invention is a system that automates everything from business planning and progress management to effectiveness measurement and employee support, and further recognizes user emotions and reflects them in the process. The following describes a specific form for implementing the invention.

[1358] System Configuration

[1359] The system primarily consists of servers, terminals, and users. The server acts as a central management device, handling data collection, processing, analysis, generation, and presentation. Terminals are devices that users use to access the server and input or verify data. Users are the primary operators of the system, generating business plans and providing feedback.

[1360] Hardware and software to be used

[1361] Hardware: Servers (server machines with high-performance CPUs and sufficient memory), terminals (PCs, tablets, smartphones)

[1362] Software: Database management systems (DBMS), generative AI models (NLP algorithms), libraries for data collection and analysis (Pandas, Scikit-learn), sentiment engine (Google AI's Sentiment Analysis API), user interface technologies (HTML / CSS / JavaScript, D3.js)

[1363] Specific processing flow

[1364] The server first collects past project and trend data for the company using APIs and database queries. The collected data undergoes data cleaning and normalization, and is then input into a generative AI model (e.g., an NLP algorithm) to generate new business plans.

[1365] The generated business plan is applied to a template format and then provided to the user through the user interface. The user reviews it and provides feedback. This feedback is sent to the server and used for regeneration and modification.

[1366] The server displays real-time data using technologies such as HTML / CSS / JavaScript and D3.js to dynamically visualize business plans and project progress. Users can view this data on a dashboard and decide on necessary actions.

[1367] Furthermore, the server collects employee performance data and work records, and trains machine learning models based on this data. The trained models are then used to generate work simulation scenarios, enabling more realistic predictions and planning.

[1368] The system also includes a feature to collect project progress and results in real time and automatically generate effectiveness measurement reports. These reports include key metrics such as KPIs and ROI, and users can download the reports to view the details.

[1369] The server also manages each employee's work history and skill set, and recommends resources and training tailored to their needs. Users can submit support requests through chatbots or dedicated forms, and the server provides appropriate resources and training in response.

[1370] The emotion engine recognizes the user's emotional state and collects emotional data during feedback and work. The server has the function to adjust the content of work plans as needed based on the emotional data. This allows for suggestions to reduce the workload when the user is experiencing stress.

[1371] Specific example

[1372] For example, when generating a business plan for a new marketing strategy, the server collects data on successful case studies and market trends from the past year, and then uses an AI model to automatically generate the plan based on that data. When a user reviews this plan and provides feedback, the emotion engine recognizes the user's emotions, and the server analyzes those emotions to identify problems in the plan and makes corrections.

[1373] Example of a prompt

[1374] "Develop a new marketing strategy. Referencing successful case studies and trend data from the past year, analyze user sentiment, and propose the optimal plan."

[1375] This will improve the quality of business planning, streamline project management and effectiveness measurement, and enhance the quality of support for employees, thereby improving overall corporate performance.

[1376] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1377] Program processing flow

[1378] Step 1:

[1379] Data Acquisition and Preprocessing

[1380] The server collects historical project and trend data for companies using APIs and database queries. Input data includes sales performance and market trends for the past year. After collecting this data, the server performs data cleaning (imputing missing values ​​and removing outliers) and normalization (scaling the data). The output is a clean dataset.

[1381] Specific example of operation: The server executes an SQL query like "SELECT FROM ProjectData WHERE Year=2022" to collect data, and then uses the Python Pandas library to perform data cleaning and normalization.

[1382] Step 2:

[1383] Business plan generation

[1384] The server inputs pre-processed data into a generation AI model (such as an NLP algorithm) to automatically generate new business plans. The input is a clean dataset, and the output is a new business plan document.

[1385] Specific example of operation: The server outputs a log message saying "Generating new business plan using NLP model..." and generates a new business plan using an NLP algorithm.

[1386] Step 3:

[1387] Applying a project template

[1388] The server applies the generated business plan to a template format. The input is the generated business plan document, and the output is a plan document that fits the standard format.

[1389] Specific example of operation: The server outputs "Applying business plan to template format..." and applies the new plan to the template.

[1390] Step 4:

[1391] Providing a plan

[1392] The server displays business plans that fit a standard format in the user interface. The input is the plan document after applying the template, and the output is the business plan displayed on the user screen.

[1393] Specific example of operation: The server outputs a log message saying "Displaying business plan on user interface..." and generates and sends HTML content to the user's terminal.

[1394] Step 5:

[1395] Gathering feedback

[1396] The user reviews the displayed business plan and enters feedback. The input is the user's feedback comment, and the output is the feedback data sent to the server.

[1397] Specific example of operation: The user enters "I would like the sales target to be set a little higher" in the feedback field on the screen and presses the submit button.

[1398] Step 6:

[1399] Feedback analysis and regeneration

[1400] The server receives user feedback and uses an emotion engine to analyze the feedback content and emotional state. The input is the feedback data, and the output is the analysis results and a list of items that need correction.

[1401] Specific example of operation: The server outputs a log message saying "Received user feedback. Analyzing for plan adjustment..." and calls a sentiment analysis API to evaluate the feedback content.

[1402] Step 7:

[1403] Regenerate or modify the business plan.

[1404] The server regenerates or modifies the business plan based on the analysis results of the feedback. The input is the analysis results, and the output is the modified or regenerated business plan document.

[1405] Specific example of operation: The server uses the NLP model again and outputs a log message saying "Adjusting business plan based on user feedback..." to regenerate the plan.

[1406] Step 8:

[1407] Visual confirmation

[1408] The server redisplays the regenerated or modified business plan in the user interface. The input is the final business plan document, and the output is the updated business plan displayed on the user screen.

[1409] Specific example of operation: The server regenerates the revised business plan in HTML and displays it on the user's terminal.

[1410] Step 9:

[1411] Visualization of real-time progress

[1412] The server collects and visually displays project progress data in real time. The input is progress data, and the output is real-time graphs and charts displayed on the dashboard.

[1413] Specific example of operation: The server uses a JavaScript library (e.g., D3.js) to generate graphs in real time and display them on the user's dashboard.

[1414] Step 10:

[1415] Business simulation generation

[1416] The server collects employee performance data and work records, and uses this data to train a machine learning model. The input is performance data, and the output is the trained machine learning model.

[1417] Specific example of operation: The server outputs a log message saying "Training machine learning model with performance data..." and trains the model using Spark ML or TensorFlow.

[1418] Step 11:

[1419] Generating Simulation Scenarios

[1420] The server uses a trained model to generate business simulation scenarios. The input is the trained model, and the output is the simulation scenario.

[1421] Specific example of operation: The server outputs a log message saying "Generating business simulation scenarios...", generates a scenario, and provides it to the user.

[1422] Step 12:

[1423] Generating an effectiveness measurement report

[1424] The server automatically generates project results as effectiveness measurement reports. The input is project progress data, and the output is the effectiveness measurement report.

[1425] Specific example of operation: The server outputs a log message saying "Generating performance measurement report..." and generates a report in Excel or PDF format.

[1426] Step 13:

[1427] Report Provision

[1428] Users can view the generated performance measurement reports on the dashboard and download them as needed. The input is the performance measurement report, and the output is the report downloaded to the user's device.

[1429] Specific example of operation: A user clicks a file from the dashboard and downloads a PDF report.

[1430] Step 14:

[1431] Providing CRM-based employee support

[1432] The server manages each employee's work history and skill set, and provides appropriate resources and training based on user requests. Inputs include employee work history, skill set, and request data, while outputs include recommended resources and training plans.

[1433] Specific example of operation: The server outputs a log message saying "Recommending training resources for requested skill..." and provides relevant online courses and materials.

[1434] (Application Example 2)

[1435] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1436] Traditional business planning and project management systems automate tasks such as generating plans and measuring effectiveness based on past data, but they fail to consider the emotional state of users, potentially increasing worker stress and workload. Furthermore, real-time work instructions and dynamic task reallocation required complex settings and human intervention, making them inefficient. Additionally, a lack of individual support for factory workers could result in a decrease in overall productivity.

[1437] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically generating new business plans based on past project data and trend data using generative artificial intelligence; means for providing the generated business plans to the user and receiving user feedback; means for modifying or regenerating the generated business plans based on user feedback; means for dynamically generating a user interface and visually displaying the progress of business plans and projects to the user; means for collecting and analyzing project progress and results in real time; means for automatically generating effectiveness measurement reports based on real-time analysis results; means for training a machine learning model using the collected data and automatically generating business simulations using this model; means for collecting each employee's work history and skill set and recommending resources and training according to their needs; means for recognizing the user's emotional state using an emotion recognition engine and adjusting the content of the business plans based on the results; and means for providing work instructions in real time using a head-mounted display and performing dynamic work reallocation based on emotions. This allows for a reduction in the burden on workers by responding to user emotions, enabling improved work efficiency and increased productivity.

[1438] "Generative artificial intelligence" is an artificial intelligence technology that automatically generates new business plans by utilizing past project data and trend data.

[1439] "Providing to users" refers to the means of showing or presenting the generated business plan to users.

[1440] "Receiving user feedback" refers to the means of collecting opinions and reactions from users.

[1441] "Modifying or regenerating generated business plans" refers to the means of changing existing business plans or generating new ones based on user feedback.

[1442] "Dynamically generating a user interface" refers to a means of providing users with a visual display based on information and data that changes in real time.

[1443] "Collecting and analyzing project progress and results in real time" refers to methods for acquiring and analyzing project progress and results in real time.

[1444] "Automatically generating effectiveness measurement reports" refers to a method of automatically creating effectiveness measurement reports based on the progress and results of a project.

[1445] "Training a machine learning model" refers to the process of training a machine learning algorithm using collected data.

[1446] "Automatically generating business simulations" refers to a method of automatically creating business simulations using trained machine learning models.

[1447] "Recommending resources and training tailored to individual needs" means proposing necessary resources and training based on each employee's work history and skill set.

[1448] An "emotion recognition engine" is a technology used to recognize a user's emotional state.

[1449] "Adjusting the content of the business plan" refers to the means of appropriately changing the content of the business plan based on the perceived emotional state.

[1450] A "head-mounted display" is a display device worn on the head to display work instructions in real time.

[1451] "Dynamic task reallocation" refers to a method of redistributing tasks in response to real-time situations and emotional states.

[1452] This invention relates to a smart factory support system for assisting factory workers. This system enables automatic generation of work plans, optimization of work through emotion recognition, real-time instruction provision, and dynamic work redistribution.

[1453] System Configuration

[1454] This system consists of the following main components:

[1455] server

[1456] Head-mounted display (HMD)

[1457] User (factory worker)

[1458] server

[1459] Business plan generation

[1460] The server collects past project and trend data for companies, and performs data cleaning and normalization. This pre-processed data is then input into generative artificial intelligence (such as natural language generation algorithms) to automatically generate new business plans. The generated plans are based on template formats and trend data and are displayed in the user interface.

[1461] Feedback and Sentiment Recognition

[1462] The server collects feedback from users (workers) and recognizes their emotional state using an emotion recognition engine. Based on this information, it modifies or regenerates the business plan. Emotion recognition is performed by analyzing biometric data such as facial expressions and heart rate.

[1463] Providing real-time instructions

[1464] The server has the capability to provide work instructions in real time via a head-mounted display. If the emotion recognition engine detects the user's stress level, the server dynamically redistributes tasks to reduce the workload.

[1465] Effectiveness measurement

[1466] The server collects project progress and results in real time and automatically generates effectiveness measurement reports. These reports are displayed in the user interface for easy review.

[1467] Head-mounted display

[1468] A head-mounted display (HMD) is a device worn by workers that visually displays real-time work instructions and status reports. This allows workers to check work instructions without using their hands.

[1469] User

[1470] Factory workers wear head-mounted displays to view real-time work instructions provided by a server. Emotions and feedback during work are sent to the server via an emotion recognition engine and a chatbot.

[1471] Specific example

[1472] For example, when introducing a new production line at a factory, the server references data from similar past projects to generate a new work plan. As workers wearing HMDs (Head-Mounted Displays) follow the instructions, the emotion recognition engine detects stress in the workers, and the server automatically redistributes the workload to reduce the burden on the workers. After the work is completed, progress and effectiveness measurement reports are automatically generated.

[1473] Example of a prompt

[1474] "I want to develop an application that recognizes emotions in real time using an emotion recognition model and displays work instructions on a head-mounted display. The emotion recognition model to be used is "emotion_model.h5," which recognizes facial expressions. Work instructions will be obtained from AI_ENDPOINT. For example, if a worker is feeling stressed, the application should issue instructions to reduce their workload."

[1475] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1476] Step 1:

[1477] The server collects historical project data and trend data, and performs data cleaning and normalization. Specifically, it retrieves necessary data using database queries and APIs, and removes incomplete and duplicate data. It also preprocesses the data by converting it to a unified format. It receives project data from databases and external APIs as input and outputs preprocessed data.

[1478] Step 2:

[1479] The server inputs pre-processed data into a generative artificial intelligence (natural language generation algorithm) to automatically generate new business plans. This generation process generates the optimal business plan in natural language format based on the input data. It receives pre-processed data as input and obtains the generated business plan as output.

[1480] Step 3:

[1481] The server provides the generated business plan to the user through a user interface. The user reviews the provided business plan and enters feedback. The server receives the generated business plan data and the user's feedback as input and obtains an updated plan or feedback content as output.

[1482] Step 4:

[1483] The server modifies or regenerates business plans based on user feedback. This process includes analyzing the feedback and re-inputting the analysis results into a generative artificial intelligence to generate new business plans. It receives feedback data as input and obtains modified or regenerated business plans as output.

[1484] Step 5:

[1485] The server recognizes the user's emotional state using an emotion recognition engine. Specifically, it acquires the user's facial image using a camera and inputs it into the emotion recognition model to perform an emotional evaluation. It receives real-time facial image data as input and obtains the user's emotional state as output.

[1486] Step 6:

[1487] The server adjusts the content of the business plan based on the emotion recognition results. Specifically, if the user is experiencing stress, the generative artificial intelligence will make suggestions to reduce the workload. It receives emotion data as input and obtains an adjusted business plan as output.

[1488] Step 7:

[1489] The server provides work instructions in real time via a head-mounted display. It can also dynamically modify work instructions based on emotion recognition results. It receives adjusted work plans and emotion data as input and outputs instruction data for the head-mounted display.

[1490] Step 8:

[1491] The server collects project progress and results in real time and automatically generates effectiveness measurement reports. This process includes collecting and analyzing sensor data and log data, and generating reports. It receives project progress data as input and obtains effectiveness measurement reports as output.

[1492] Step 9:

[1493] The server collects each employee's work history and skill set, and recommends resources and training tailored to their needs. Specifically, it retrieves work history and skill set data from the database and generates appropriate resources and training plans. It takes employee data as input and outputs recommended resources and training plans.

[1494] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1495] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1496] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1497] [Fourth Embodiment]

[1498] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1499] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1500] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1501] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1502] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1503] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1504] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1505] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1506] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1507] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1508] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1509] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1510] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1511] This invention relates to a system that automates the planning, management, and effectiveness measurement of business plans within a company, and further provides support to individual employees. The embodiments of this system are described below.

[1512] System Configuration

[1513] The system mainly consists of the following components:

[1514] server

[1515] terminal

[1516] User

[1517] 1. Generating a business plan

[1518] 1.1 Data Collection and Analysis

[1519] The server collects historical project data and trend data for the company. This collection is performed via database queries and APIs. The collected data undergoes data cleaning and preprocessing before being converted into an analyzable format.

[1520] 1.2 Planning using generative artificial intelligence

[1521] The server automatically generates new business plans using pre-processed data through generative artificial intelligence. This generative AI employs, for example, machine learning models and natural language generation algorithms. At this stage, the generated business plans are based on template formats and trend data.

[1522] 1.3 Providing proposals and feedback

[1523] The server displays the generated business plan on the user interface.

[1524] Users can review the proposed project plan and provide feedback, including additional suggestions and revisions. This feedback is then sent back to the server, which uses it to revise or regenerate the project plan.

[1525] 2. Platform: UX / Reporting

[1526] The server dynamically generates the user interface, allowing users to check business plans and project progress. The displayed dashboards are created using technologies such as HTML / CSS / JavaScript. This allows users to visually view real-time data and make immediate decisions about necessary actions.

[1527] 3. Generating business simulations

[1528] The server trains a machine learning model using collected employee performance data and work records. This model is used to generate simulations of actual work processes. The simulations reproduce work processes in a virtual environment and aim to improve employee skills. The generated simulation games are deployed via web and mobile platforms.

[1529] 4. Measurement of effectiveness

[1530] The server collects project progress data in real time and automatically generates effectiveness measurement reports. These reports include metrics such as project results, KPIs, and ROI after project completion. The generated reports can be downloaded and reviewed by the user.

[1531] 5. CRM-based employee support

[1532] The server manages each employee's work history and skill set. Based on this, users can submit support requests through the user interface or chatbot. The server then suggests the most suitable resources and training based on the request, supporting the employee's work. It also records employee growth data and feedback, which are used to improve future support.

[1533] Specific example

[1534] For example, the server generates a business plan titled "Marketing Strategy for New Product Launch." In doing so, it considers past successes and trends when proposing the plan. The user then reviews this plan and adds feedback, such as "We should strengthen social media advertising to expand the target market." Based on this feedback, the server revises the plan and presents an optimized marketing strategy again.

[1535] In this way, this system improves the quality of business planning and enables efficient project progress management and effectiveness measurement. Furthermore, it provides appropriate support to individual employees, thereby improving the overall performance of the company.

[1536] The following describes the processing flow.

[1537] Business plan generation

[1538] Business plan generation process

[1539] Step 1:

[1540] Server: Collects historical project data and trend data from the company's database. Extracts and preprocesses data using SQL queries.

[1541] Step 2:

[1542] Server: Cleans the collected data, imputing missing values ​​and removing outliers. Normalizes the data and converts it into a format suitable for analysis.

[1543] Step 3:

[1544] Server: Inputs pre-processed data into a generative artificial intelligence (e.g., a natural language generation algorithm) to automatically generate new business plans.

[1545] Step 4:

[1546] Server: Prepares the generated business plan for display in the user interface. This includes generating dynamic web pages using HTML / CSS / JavaScript.

[1547] Step 5:

[1548] User: Log in to the user interface and review the generated business plan. View the specific proposal details and prepare feedback at this stage.

[1549] Step 6:

[1550] User: Enter any corrections or suggestions into the feedback form and submit it to the server.

[1551] Step 7:

[1552] Server: Analyzes user feedback and executes algorithms to revise or regenerate business plans. Generative artificial intelligence is used again in this process.

[1553] UX / Reporting Process

[1554] Step 1:

[1555] Server: Build applications that collect project progress and key metrics. Collect real-time data through APIs and database connections.

[1556] Step 2:

[1557] Server: Processes collected data and generates graphs and charts for dashboards. Uses libraries such as D3.js to visualize the data.

[1558] Step 3:

[1559] Terminal: Users access the dashboard to view project progress and reports. They can view detailed information and historical data by interacting with UI elements.

[1560] Step 4:

[1561] Server: Automatically generates reports based on user-specified time periods and parameters, and outputs them in PDF or Excel format.

[1562] Step 5:

[1563] Terminal: Download the generated report and print or share it as needed.

[1564] Business simulation generation process

[1565] Step 1:

[1566] Server: Collects employee performance data and work records. Data is collected via database queries and APIs.

[1567] Step 2:

[1568] Server: Trains machine learning models using collected data. Uses machine learning libraries such as TensorFlow and PyTorch.

[1569] Step 3:

[1570] Server: Generates business simulation scenarios using a pre-trained model. Designs specific business processes and storylines.

[1571] Step 4:

[1572] Server: Deploys the generated simulation game to a web or mobile platform. Hosts the application using AWS Lambda or Firebase.

[1573] Step 5:

[1574] User: Play simulation games and improve your skills. Collect gameplay logs and send them to the server.

[1575] Step 6:

[1576] Server: Analyzes collected gameplay data to identify areas for improvement in the simulation. Retrains the model as needed and generates improved scenarios.

[1577] Effectiveness measurement process

[1578] Step 1:

[1579] Server: Collects project progress data in real time. Data is automatically retrieved using APIs and webhooks.

[1580] Step 2:

[1581] Server: Analyzes data collected in real time and automatically generates effectiveness measurement reports based on that analysis. Inserts the analysis results into the report template.

[1582] Step 3:

[1583] User: View the generated performance measurement report on the dashboard. Download or print the report as needed.

[1584] CRM-based employee support process

[1585] Step 1:

[1586] Server: Collects each employee's work history and skill data and stores it in a database. Uses an API from the HR system.

[1587] Step 2:

[1588] Terminal: Provides an interface for employees to enter support requests. Requests are collected using chatbots or dedicated forms.

[1589] Step 3:

[1590] Server: Based on collected requests, it recommends the most suitable resources and training. It uses a matching algorithm to make appropriate suggestions.

[1591] Step 4:

[1592] Terminal: Employees use suggested resources to support their work. They refer to training materials and online guides.

[1593] Step 5:

[1594] Server: Records employee growth data and feedback, and uses it to improve future support. Analyzes feedback data to refine future proposals.

[1595] The above are the specific processing steps for carrying out the invention.

[1596] (Example 1)

[1597] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1598] In the current business planning and effectiveness measurement process, improving the quality of plans requires significant time and effort. Furthermore, the lack of centralized collection and analysis of accurate real-time data, and the absence of support tailored to individual employee skill sets, makes management cumbersome. This creates challenges in improving overall company performance.

[1599] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1600] In this invention, the server includes means for automatically generating new business plans based on past project data and trend data using a generation AI model, means for providing the generated business plans to users and receiving user feedback, and means for modifying or regenerating the generated business plans based on user feedback. This enables reduction of time and effort, accurate collection and analysis of real-time data, and centralized support for employees, which were problems in the past.

[1601] A "generative AI model" is an algorithm or program that uses generative artificial intelligence to automatically generate new information or content from given data.

[1602] A "prompt message" is an instruction given to a generative AI model to generate a specific answer or information.

[1603] "Past project data" refers to information and records about projects that a company has undertaken in the past, including, for example, project progress, results, and resources used.

[1604] "Trend data" refers to data that shows current market trends and changes, and includes, for example, social media posts, economic indicators, and industry news.

[1605] "User feedback" refers to suggestions for improvements, opinions, and additional requirements that users provide to the system.

[1606] A "template format" is a model used to format generated content or information into a specific form or structure.

[1607] A "dashboard" is an interface for centrally managing the visual display of project progress and data.

[1608] A "machine learning model" is a computer program that uses large amounts of data to train algorithms and then makes predictions, classifications, and generations based on new data.

[1609] A "virtual environment" is a digital space that simulates the physical environment of the real world, and is a system capable of reproducing various scenarios.

[1610] "Business simulation" is a system that aims to improve employee skills and operational efficiency by reproducing actual business processes in a virtual environment.

[1611] An "effectiveness measurement report" is a report created based on data collected to evaluate the results of a project.

[1612] This invention relates to a system that automates the planning, management, and effectiveness measurement of business plans within a company, and further provides support to individual employees. Specific embodiments of this system are described below.

[1613] System Configuration

[1614] The system mainly consists of the following components:

[1615] server

[1616] terminal

[1617] User

[1618] Data collection and analysis by server

[1619] The server collects historical project and trend data for companies through database queries (e.g., PostgreSQL) and APIs (e.g., Twitter API). The collected data is cleaned and preprocessed using Python scripts or ETL tools (e.g., Apache NiFi) and converted into an analyzable format.

[1620] Server-based generation of business plans

[1621] The server inputs pre-processed data into a machine learning model (e.g., GPT-4) and automatically generates new business plans using a generative AI model. The generated business plans are then formatted according to a template format.

[1622] Providing proposals and processing feedback

[1623] The server displays the generated business plan on a web interface. Users review the plan and provide feedback through the web interface. The server receives the user's feedback and uses the machine learning model again to revise or regenerate the plan.

[1624] User interface and display of real-time data

[1625] The server dynamically generates dashboards using HTML / CSS / JavaScript, visually displaying business plans and project progress to the user. Users can view real-time data on the dashboard.

[1626] Business simulation generation

[1627] The server trains machine learning models (e.g., TensorFlow or PyTorch) using employee performance data and work records, and generates work simulations in a virtual environment. The generated simulations are then provided through web and mobile applications.

[1628] Automatic generation of effectiveness measurements and reports

[1629] The server collects project progress data in real time and automatically generates performance measurement reports that include metrics such as KPIs and ROI. The generated reports are provided in a format that users can download and review.

[1630] Providing CRM-based employee support

[1631] The server manages each employee's work history and skill set, and allows users to submit support requests through an interface or chatbot. The server analyzes the requests and suggests the most suitable resources and training. It also records employee growth data and feedback to improve future support.

[1632] Specific example

[1633] For example, the server generates a business plan titled "Marketing Strategy for New Product Launch." In doing so, it considers past success stories and trend data to propose the plan. The user reviews this proposal and adds feedback such as, "We should strengthen social media advertising to expand the target market." Based on this feedback, the server revises the plan and presents an optimized marketing strategy again.

[1634] Example of a prompt

[1635] As an example of a prompt message to use when using a generative AI model, enter the following:

[1636] "Based on marketing data from the past five years, please generate the optimal marketing strategy for our new product launch."

[1637] In this way, this system can improve the quality of business planning and enable efficient project progress management and effectiveness measurement. Furthermore, it can provide appropriate support to individual employees, thereby improving the overall performance of the company.

[1638] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1639] Step 1: Data Collection

[1640] The server executes database queries (e.g., PostgreSQL) to collect historical project data for a company. It uses SQL queries as input to retrieve historical project data records. The output is the retrieved project data. It also calls APIs (e.g., Twitter API) to collect trend data. It uses API requests as input to retrieve trend data as output.

[1641] Step 2: Data preprocessing and analysis

[1642] The server performs data cleaning and preprocessing on the acquired data using the Python Pandas library. It uses the acquired project data and trend data as input, handling missing values ​​and performing data type conversions. The output is preprocessed, analyzable data.

[1643] Step 3: Automatic generation of business plans

[1644] The server inputs pre-processed data into a machine learning model (e.g., GPT-4) and uses a generative AI model to automatically generate new business plans. Using pre-processed data and prompt statements as input, it obtains the generated business plan as output. Specifically, it formats the generated text based on a template format.

[1645] Step 4: Providing a proposal

[1646] The server displays the generated business plan on a web interface. It uses a formatted business plan as input and displays the business plan on a web page as output. Specifically, it dynamically generates the page using HTML / CSS / JavaScript.

[1647] Step 5: Collecting user feedback

[1648] Users review business plans and input feedback through a web interface. The system receives user feedback as input and outputs feedback data. Specifically, users input information using a feedback form.

[1649] Step 6: Revise or regenerate the plan based on feedback

[1650] The server uses the machine learning model again to revise or regenerate the business plan based on user feedback. It uses user feedback and the previously generated business plan as input, and obtains the revised or regenerated business plan as output. Specifically, it inputs the prompt and feedback again into the machine learning model and formats the generated text.

[1651] Step 7: Real-time display of progress

[1652] The server collects project progress in real time and dynamically generates a dashboard using HTML / CSS / JavaScript. It uses project progress data as input and outputs an updated dashboard display. Specifically, it periodically runs a data collection script to reflect the latest data in the dashboard.

[1653] Step 8: Automatic generation of performance measurement reports

[1654] The server automatically generates effectiveness measurement reports based on the collected progress data. It uses project progress data, KPIs, and ROI metrics as input, and outputs an effectiveness measurement report. Specifically, it executes a report generation script to create the report in PDF or web format.

[1655] Step 9: Generate Business Simulation

[1656] The server trains a machine learning model using employee performance data and work records to generate business simulations in a virtual environment. It uses employee data and work records as input and obtains business simulations as output. Specifically, it inputs data into the virtual environment system and reproduces business processes based on scenarios.

[1657] Step 10: Employee support using CRM functions

[1658] Users enter support requests through an interface or chatbot. The server analyzes the request and suggests the most suitable resources and training. It uses employee work history and skill sets, along with the request content, as input, and outputs suggested resources and training content. Specifically, it analyzes the request and searches the database for appropriate resource information.

[1659] (Application Example 1)

[1660] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1661] In modern factories, improving production efficiency and developing flexible production plans are crucial challenges. However, traditional systems relied on manual plan generation and modification based on historical data and trends, which required significant time and effort. Furthermore, real-time monitoring of production efficiency and improving the accuracy of production plans through operational simulations were difficult. Additionally, there was a lack of training tailored to each employee's skill set, sometimes resulting in a decline in overall productivity.

[1662] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1663] In this invention, the server includes means for collecting and analyzing data from sensors and IoT devices in production equipment, means for regenerating or improving the manufacturing plan based on the feedback, and means for monitoring production efficiency in real time and generating effectiveness measurement reports. This enables real-time monitoring and analysis of production efficiency, rapid regeneration and improvement of the manufacturing plan based on feedback, and the suggestion of training optimized for each employee.

[1664] "Generative artificial intelligence" is an artificial intelligence technology that automatically generates business plans and other information based on past data and trend data.

[1665] "Methods for automatically generating business plans" refers to the part of a system that automatically generates business plans using generative artificial intelligence based on collected data.

[1666] "Means of receiving feedback" refers to the part of the system that receives and processes opinions and suggestions for revisions from users.

[1667] "Means for modifying or regenerating business plans" refers to the part of the system that modifies existing business plans or generates new ones based on user feedback.

[1668] "Means for dynamically generating and displaying user interfaces" refers to the part of a system that provides dynamically generated interfaces so that users can visually check the progress of business plans and projects.

[1669] "Means for collecting and analyzing project progress and results in real time" refers to the part of a system that collects data in real time as the project progresses and analyzes that data immediately.

[1670] "Method for automatically generating effectiveness measurement reports" refers to the part of the system that measures the effectiveness of a project based on collected real-time analysis results and automatically generates a report on it.

[1671] "Methods for automatically generating business simulations" refers to the part of a system that uses machine learning models to automatically generate simulations that virtually reproduce actual business operations.

[1672] "Means for collecting employees' work history and skill sets and recommending training" refers to the part of the system that records each employee's work history and skill set and then suggests training that is appropriate to their needs based on that information.

[1673] "Means for collecting and analyzing data from sensors and IoT devices" refers to the part of the system that collects data in real time from sensors and IoT devices within a factory and analyzes that data.

[1674] "Means for regenerating or improving manufacturing plans based on feedback" refers to the part of the system that incorporates user feedback to regenerate or improve existing manufacturing plans.

[1675] "A means of monitoring production efficiency in real time and generating effectiveness measurement reports" refers to the part of a system that monitors production efficiency within a factory in real time and automatically generates effectiveness measurement reports that evaluate that efficiency.

[1676] This invention relates to a system aimed at improving production efficiency in factories and automatically generating flexible production plans. The system of this invention consists of a server, terminals, and users, and is implemented using various hardware and software.

[1677] Data collection and analysis

[1678] The server collects data in real time from sensors and IoT devices on production equipment. This data includes production volume, machine operating status, and quality inspection results. The data is preprocessed and analyzed to become foundational data for generating business plans. A database management system (e.g., MySQL) is used to store and manage the data.

[1679] Automatic generation of business plans

[1680] The server automatically generates new business plans based on past project data and trend data using generative artificial intelligence. Machine learning algorithms (e.g., linear regression models) and natural language generation algorithms are used at this stage. The generated business plans are based on template formats and trend data.

[1681] Incorporating user feedback

[1682] The generated business plan is provided to the user via a terminal. The user reviews the proposed plan and provides any necessary feedback. The server then modifies or regenerates the business plan based on this feedback. This process generates an optimal business plan that meets the user's needs.

[1683] Production plan management and display

[1684] The server dynamically generates a user interface, visually displaying business plans and project progress to the user. This interface is created using technologies such as HTML / CSS / JavaScript, enabling real-time data display. The user reviews this information and decides on the next action as needed.

[1685] Effectiveness measurement and report generation

[1686] The server collects and analyzes project progress and results in real time and automatically generates effectiveness measurement reports. These reports include metrics such as KPIs and ROI, which users can review via their terminals.

[1687] Business simulation

[1688] The server trains a machine learning model using the collected data and automatically generates business simulations using this model. The simulations are run in a virtual environment and are intended to improve employee skills. The generated simulations are delivered via web and mobile platforms.

[1689] Employee support

[1690] The server manages each employee's work history and skill set, and based on this, suggests the most suitable resources and training. This ensures that each employee receives personalized support.

[1691] Specific example

[1692] For example, the server generates a business plan titled "Efficient Production Plan for a New Product." In doing so, it considers past production data and trends when proposing the plan. The user reviews this plan and adds feedback such as, "We need to adjust the production line to consider using a new material." Based on this feedback, the server revises the plan and presents a new, optimized production plan.

[1693] Examples of prompts for generative AI models

[1694] "Please generate a new production plan based on production data from the past three years. The feedback from management states that 'new materials should also be considered.' Please also generate a production plan that reflects this feedback."

[1695] By providing the entire system as an integrated service, the factory's production efficiency and flexibility are significantly improved. Furthermore, it contributes to improving employee skills and enhances overall performance.

[1696] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1697] Step 1:

[1698] The server collects data from sensors and IoT devices in the production equipment. This collected data includes production volume, machine operating status, and quality inspection results. This data is stored in a database (e.g., MySQL) and then cleaned and pre-processed. As a result, analyzable, formatted data can be obtained.

[1699] Step 2:

[1700] The server analyzes the formatted data and generates new business plans based on past project data and trend data. This process utilizes generative artificial intelligence technologies (e.g., machine learning algorithms and natural language generation algorithms). The business plans generated from the input data and the model are output.

[1701] Step 3:

[1702] The generated business plan is provided to the user via a terminal. The user reviews the provided business plan and enters any necessary feedback. This feedback includes specific revisions and additional requests. The user's input is sent to the server as feedback.

[1703] Step 4:

[1704] The server modifies or regenerates the business plan based on the feedback received. This process again utilizes generative artificial intelligence technology to automatically generate a new business plan that reflects the feedback. The output is the modified business plan.

[1705] Step 5:

[1706] The revised business plan is dynamically displayed on the user interface. The server generates a visually verifiable dashboard using technologies such as HTML / CSS / JavaScript. This user interface allows users to check the progress of business plans and projects in real time.

[1707] Step 6:

[1708] The server collects and analyzes project progress and results in real time. This process involves monitoring data from various sensors in real time to evaluate progress and performance. Performance metrics (e.g., KPIs and ROI) are used to assess the extent to which progress has been achieved. The evaluation results are provided as output.

[1709] Step 7:

[1710] The server automatically generates effectiveness measurement reports based on real-time analysis results. The reporting tool then uses the analysis results to generate reports based on metrics such as project completion outcomes, KPIs, and ROI. The generated reports are provided to the user to help them determine the necessary next actions.

[1711] Step 8:

[1712] The collected data is used to train a machine learning model, which is then used to automatically generate business simulations. These simulations replicate business processes in a virtual environment, aiming to improve employee skills. The generated business simulations are provided in a deployable format via web and mobile platforms.

[1713] Step 9:

[1714] The server collects each employee's work history and skill set, and recommends resources and training tailored to their needs. Based on the collected work history and skill set, it utilizes a matching algorithm to suggest the optimal training program. As a result, users are provided with individually optimized training plans.

[1715] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1716] This invention relates to a system that automates everything from business planning and progress management to effectiveness measurement and employee support, and further recognizes user emotions and incorporates them into the process. The following describes specific embodiments of this system.

[1717] System Configuration

[1718] The system mainly consists of the following components:

[1719] server

[1720] terminal

[1721] User

[1722] 1. Generating a business plan

[1723] 1.1 Data Collection and Analysis

[1724] The server collects historical project data and trend data for the company. This data is retrieved via database queries and APIs, and then preprocessed through data cleaning and normalization.

[1725] 1.2 Planning using generative artificial intelligence

[1726] The server inputs pre-processed data into a generative artificial intelligence (e.g., a natural language generation algorithm) to automatically generate new business plans. The generated plans are based on template formats and trend data.

[1727] 1.3 Providing proposals and feedback

[1728] The server displays the generated business plan in the user interface. The user reviews the plan and provides feedback. This feedback is sent to the server and used for regeneration or modification.

[1729] 2. Platform: UX / Reporting

[1730] The server dynamically generates the user interface, allowing users to visually check business plans and project progress. Technologies such as HTML / CSS / JavaScript are used to visualize real-time data. Users view the data on the dashboard and decide on necessary actions.

[1731] 3. Business simulation generation

[1732] The server collects employee performance data and work records, and trains a machine learning model based on this data. This model is then used to generate work simulation scenarios. These simulations become available on web and mobile platforms.

[1733] 4. Measurement of effectiveness

[1734] The server collects project progress data in real time and automatically generates effectiveness measurement reports. These reports include project outcomes, KPIs, ROI, and more. Users can download and review the generated reports.

[1735] 5. CRM-based employee support

[1736] The server manages each employee's work history and skill set. Users can submit support requests through chatbots or dedicated forms. Based on the request, the server recommends appropriate resources and training. Employee growth data and feedback are also recorded and used to improve future support.

[1737] 6. Integrating an emotion engine

[1738] 6.1 Emotion recognition

[1739] The server uses an emotion engine to recognize user emotions and understand the user's emotional state. This allows for the collection of user emotional data during feedback sessions and work activities.

[1740] 6.2 Adjusting business plans based on emotions

[1741] The server adjusts the content of the work plan as needed based on the user's emotional state recognized by the emotion engine. For example, if the user is feeling stressed, it will make suggestions to reduce the workload.

[1742] 6.3 Improving the quality of feedback through sentiment analysis

[1743] The server analyzes the emotions expressed by users during feedback and uses the results to revise or regenerate business plans. This results in the creation of business plans that are more user-satisfying.

[1744] 6.4 Emotion-based support and suggestions

[1745] The user interface provides appropriate support and suggestions based on the user's emotions. For example, if the user is tired, it might suggest taking a break, responding in a way that matches their feelings.

[1746] Specific example

[1747] For example, when generating a business plan for a new marketing strategy, the server generates the plan by referencing past success stories. When a user reviews this plan and provides feedback, the emotion engine recognizes the user's emotions and determines whether the user is satisfied or dissatisfied. If dissatisfaction is detected, the server analyzes the reason and improves the plan. In this process, the burden on the user is reduced and an optimized plan is created.

[1748] Thus, this system improves the quality of business planning and enables efficient project progress management and effectiveness measurement. Furthermore, by providing appropriate support to individual employees and responding in a way that is sensitive to user emotions, it aims to improve the overall performance of the company.

[1749] The following describes the processing flow.

[1750] Business plan generation

[1751] Business plan generation process

[1752] Step 1:

[1753] Server: Collects historical project data and trend data from the company's database. Extracts necessary data using SQL queries and preprocesses the data.

[1754] Step 2:

[1755] Server: Cleans the collected data, imputing missing values ​​and removing outliers. Performs normalization and feature extraction, and converts the data into an analyzable format.

[1756] Step 3:

[1757] Server: Pre-processed data is input into a generative artificial intelligence (natural language generation algorithm) to automatically generate new business plans. The generated business plans are based on a template format.

[1758] Proposal of plans and feedback

[1759] Step 4:

[1760] Server: Formats the generated business plan into a format that can be displayed in the user interface. Generates dynamic web pages using HTML / CSS / JavaScript.

[1761] Step 5:

[1762] User: Log in to the user interface and review the generated business plan. View the specific details and prepare feedback.

[1763] Step 6:

[1764] User: Enter any corrections or suggestions in the feedback form and submit it.

[1765] Step 7:

[1766] Server: Receives feedback submitted by users and uses generative artificial intelligence to revise or regenerate the plan.

[1767] Platform: UX / Reporting Process

[1768] Step 1:

[1769] Server: Build APIs and database connections to collect project progress and key metrics, and obtain real-time data.

[1770] Step 2:

[1771] Server: Processes collected data and generates dashboards for visualization. Uses libraries such as D3.js to display real-time data as graphs and charts.

[1772] Step 3:

[1773] Terminal: Users access the dashboard to view project progress and reports. They interact with UI elements to view detailed information and historical data.

[1774] Step 4:

[1775] Server: Automatically generates reports based on user-specified time periods and parameters, and outputs them in PDF or Excel format.

[1776] Step 5:

[1777] Terminal: Download the generated report and print or share it as needed.

[1778] Embedding an emotion engine

[1779] Emotion recognition process

[1780] Step 1:

[1781] Server: Activates the emotion engine to recognize user emotions. It extracts emotions from text or audio data using NLP techniques and machine learning models.

[1782] Step 2:

[1783] Device: When a user enters feedback or communication, that data is sent to the emotion engine.

[1784] Step 3:

[1785] Server: Analyzes the data received by the emotion engine to determine the user's emotional state. This information is recorded in the database.

[1786] Adjusting business plans based on emotions

[1787] Step 4:

[1788] Server: Reflects user emotion data, identified by the emotion engine, into business planning. For example, if a user is experiencing stress, it automatically adds suggestions to reduce their workload.

[1789] Analysis and reflection of feedback

[1790] Step 5:

[1791] Server: Analyzes the emotional state of users when they provide feedback to identify the quality of the feedback and areas for improvement. Based on these analysis results, the business plan is revised or regenerated.

[1792] Emotion-based support and suggestions

[1793] Step 6:

[1794] Terminal: Displays support and suggestions tailored to the user's emotions on the user interface. For example, if the user is tired, it suggests taking appropriate rest.

[1795] Step 7:

[1796] Server: Based on user growth data and emotional feedback, improve future business planning and support suggestions. This data will be used for future training and support.

[1797] Business simulation generation process

[1798] Step 1:

[1799] Server: Collects employee performance data and work records. Retrieves data via databases and APIs.

[1800] Step 2:

[1801] Server: Trains machine learning models using collected data. Uses libraries such as TensorFlow and PyTorch.

[1802] Step 3:

[1803] Server: Generates business simulation scenarios using a pre-trained model. Incorporates specific business processes and storylines into the scenarios.

[1804] Step 4:

[1805] Server: Deploys the generated simulation game to a web or mobile platform. Deployment is performed using AWS or Firebase.

[1806] Step 5:

[1807] User: Play simulation games and improve your skills. Collect gameplay logs and send them to the server.

[1808] Step 6:

[1809] Server: Analyzes collected gameplay data to identify areas for improvement in the simulation. Retrains the model to generate improved scenarios.

[1810] Effectiveness measurement process

[1811] Step 1:

[1812] Server: Collects project progress data in real time. Retrieves data via APIs and webhooks.

[1813] Step 2:

[1814] Server: Analyzes collected data in real time and automatically generates effectiveness measurement reports. Inserts data into report templates.

[1815] Step 3:

[1816] User: View the generated performance measurement report on the dashboard. Download and print the report as needed.

[1817] Employee support using CRM

[1818] Step 1:

[1819] Server: Collects each employee's work history and skill data and stores it in a database. Retrieves data from the HR system via API.

[1820] Step 2:

[1821] Terminal: Provides an interface for employees to enter support requests. Requests are collected using chatbots or dedicated forms.

[1822] Step 3:

[1823] Server: Recommends the most suitable resources and training based on the request. Uses a matching algorithm to make appropriate suggestions.

[1824] Step 4:

[1825] Terminal: Employees use suggested resources to support their work. They refer to training materials and online guides.

[1826] Step 5:

[1827] Server: Records employee growth data and feedback, and uses it to improve future support. Analyzes feedback data to refine future proposals.

[1828] The above are the specific processing steps for carrying out the invention.

[1829] (Example 2)

[1830] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1831] Traditional business management systems have struggled to comprehensively automate everything from business planning and progress management to performance measurement and employee support, and have been particularly poor at providing feedback and adjusting plans to reflect user sentiment. Furthermore, while efficiency and flexibility are required for real-time project management and providing individual employee support, no system adequately met these needs.

[1832] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for automatically generating new business plans based on past project data and trend data using generative artificial intelligence; means for providing the generated business plans to the user and receiving user feedback; means for modifying or regenerating the business plans based on user feedback; means for dynamically generating a user interface and visually displaying the progress of business plans and projects to the user; means for collecting and analyzing project progress and results in real time; means for automatically generating effectiveness measurement reports based on real-time analysis results; means for training a machine learning model using the collected data and automatically generating business simulations using this model; means for collecting each employee's work history and skill set and recommending resources and training according to their needs; means for collecting user emotional data during feedback and work using an emotion engine that recognizes the user's emotional state; and means for appropriately adjusting the content of the business plans based on the user's emotional state. This enables the streamlining and optimization of the entire business process, as well as flexible, high-quality feedback and planning adjustments that reflect user sentiment.

[1833] "Generative artificial intelligence" is a general term for artificial intelligence technologies that automatically generate new information and plans based on past data and trend information.

[1834] "Business planning" refers to the planning of projects and tasks that a company or organization will carry out, and its contents include objectives, means, schedules, and resource allocation.

[1835] "Feedback" refers to opinions and evaluations provided by users, which are useful information for improving services and projects.

[1836] "User interface" is a general term for the screens and operating methods that users use to operate a system and input or retrieve information.

[1837] "Real-time" refers to the process where data and information are processed instantly, and the results are reflected immediately.

[1838] An "effectiveness measurement report" is an automatically generated report used to evaluate the progress and results of a project or task, and includes metrics such as KPIs and ROI.

[1839] A "machine learning model" refers to an algorithm or computer program that analyzes large amounts of data and learns patterns and rules from it.

[1840] "Business simulation" refers to scenarios or simulators that reproduce actual business environments and situations, allowing users to virtually try them out.

[1841] "Work history" refers to records of an employee's past work and projects, and is used to analyze performance and trends.

[1842] A "skill set" refers to the collection of abilities and skills that each employee possesses, and its contents include specialized knowledge and experience.

[1843] "Resources" refer to management resources such as personnel, time, funds, and equipment, and how these are allocated and utilized is crucial.

[1844] An "emotion engine" refers to artificial intelligence technology or systems used to recognize and analyze a user's emotional state.

[1845] "Emotional data" refers to data that indicates a user's emotional state and is used for feedback and improving business processes.

[1846] A "template format" refers to a template for documents or data created based on a specific structure or format.

[1847] "Trend data" refers to data that shows past trends or patterns in phenomena, and is used for future predictions and planning.

[1848] Modes for carrying out the invention

[1849] This invention is a system that automates everything from business planning and progress management to effectiveness measurement and employee support, and further recognizes user emotions and reflects them in the process. The following describes a specific form for implementing the invention.

[1850] System Configuration

[1851] The system primarily consists of servers, terminals, and users. The server acts as a central management device, handling data collection, processing, analysis, generation, and presentation. Terminals are devices that users use to access the server and input or verify data. Users are the primary operators of the system, generating business plans and providing feedback.

[1852] Hardware and software to be used

[1853] Hardware: Servers (server machines with high-performance CPUs and sufficient memory), terminals (PCs, tablets, smartphones)

[1854] Software: Database management systems (DBMS), generative AI models (NLP algorithms), libraries for data collection and analysis (Pandas, Scikit-learn), sentiment engine (Google AI's Sentiment Analysis API), user interface technologies (HTML / CSS / JavaScript, D3.js)

[1855] Specific processing flow

[1856] The server first collects past project and trend data for the company using APIs and database queries. The collected data undergoes data cleaning and normalization, and is then input into a generative AI model (e.g., an NLP algorithm) to generate new business plans.

[1857] The generated business plan is applied to a template format and then provided to the user through the user interface. The user reviews it and provides feedback. This feedback is sent to the server and used for regeneration and modification.

[1858] The server displays real-time data using technologies such as HTML / CSS / JavaScript and D3.js to dynamically visualize business plans and project progress. Users can view this data on a dashboard and decide on necessary actions.

[1859] Furthermore, the server collects employee performance data and work records, and trains machine learning models based on this data. The trained models are then used to generate work simulation scenarios, enabling more realistic predictions and planning.

[1860] The system also includes a feature to collect project progress and results in real time and automatically generate effectiveness measurement reports. These reports include key metrics such as KPIs and ROI, and users can download the reports to view the details.

[1861] The server also manages each employee's work history and skill set, and recommends resources and training tailored to their needs. Users can submit support requests through chatbots or dedicated forms, and the server provides appropriate resources and training in response.

[1862] The emotion engine recognizes the user's emotional state and collects emotional data during feedback and work. The server has the function to adjust the content of work plans as needed based on the emotional data. This allows for suggestions to reduce the workload when the user is experiencing stress.

[1863] Specific example

[1864] For example, when generating a business plan for a new marketing strategy, the server collects data on successful case studies and market trends from the past year, and then uses an AI model to automatically generate the plan based on that data. When a user reviews this plan and provides feedback, the emotion engine recognizes the user's emotions, and the server analyzes those emotions to identify problems in the plan and makes corrections.

[1865] Example of a prompt

[1866] "Develop a new marketing strategy. Referencing successful case studies and trend data from the past year, analyze user sentiment, and propose the optimal plan."

[1867] This will improve the quality of business planning, streamline project management and effectiveness measurement, and enhance the quality of support for employees, thereby improving overall corporate performance.

[1868] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1869] Program processing flow

[1870] Step 1:

[1871] Data Acquisition and Preprocessing

[1872] The server collects historical project and trend data for companies using APIs and database queries. Input data includes sales performance and market trends for the past year. After collecting this data, the server performs data cleaning (imputing missing values ​​and removing outliers) and normalization (scaling the data). The output is a clean dataset.

[1873] Specific example of operation: The server executes an SQL query like "SELECT FROM ProjectData WHERE Year=2022" to collect data, and then uses the Python Pandas library to perform data cleaning and normalization.

[1874] Step 2:

[1875] Business plan generation

[1876] The server inputs pre-processed data into a generation AI model (such as an NLP algorithm) to automatically generate new business plans. The input is a clean dataset, and the output is a new business plan document.

[1877] Specific example of operation: The server outputs a log message saying "Generating new business plan using NLP model..." and generates a new business plan using an NLP algorithm.

[1878] Step 3:

[1879] Applying a project template

[1880] The server applies the generated business plan to a template format. The input is the generated business plan document, and the output is a plan document that fits the standard format.

[1881] Specific example of operation: The server outputs "Applying business plan to template format..." and applies the new plan to the template.

[1882] Step 4:

[1883] Providing a plan

[1884] The server displays business plans that fit a standard format in the user interface. The input is the plan document after applying the template, and the output is the business plan displayed on the user screen.

[1885] Specific example of operation: The server outputs a log message saying "Displaying business plan on user interface..." and generates and sends HTML content to the user's terminal.

[1886] Step 5:

[1887] Gathering feedback

[1888] The user reviews the displayed business plan and enters feedback. The input is the user's feedback comment, and the output is the feedback data sent to the server.

[1889] Specific example of operation: The user enters "I would like the sales target to be set a little higher" in the feedback field on the screen and presses the submit button.

[1890] Step 6:

[1891] Feedback analysis and regeneration

[1892] The server receives user feedback and uses an emotion engine to analyze the feedback content and emotional state. The input is the feedback data, and the output is the analysis results and a list of items that need correction.

[1893] Specific example of operation: The server outputs a log message saying "Received user feedback. Analyzing for plan adjustment..." and calls a sentiment analysis API to evaluate the feedback content.

[1894] Step 7:

[1895] Regenerate or modify the business plan.

[1896] The server regenerates or modifies the business plan based on the analysis results of the feedback. The input is the analysis results, and the output is the modified or regenerated business plan document.

[1897] Specific example of operation: The server uses the NLP model again and outputs a log message saying "Adjusting business plan based on user feedback..." to regenerate the plan.

[1898] Step 8:

[1899] Visual confirmation

[1900] The server redisplays the regenerated or modified business plan in the user interface. The input is the final business plan document, and the output is the updated business plan displayed on the user screen.

[1901] Specific example of operation: The server regenerates the revised business plan in HTML and displays it on the user's terminal.

[1902] Step 9:

[1903] Visualization of real-time progress

[1904] The server collects and visually displays project progress data in real time. The input is progress data, and the output is real-time graphs and charts displayed on the dashboard.

[1905] Specific example of operation: The server uses a JavaScript library (e.g., D3.js) to generate graphs in real time and display them on the user's dashboard.

[1906] Step 10:

[1907] Business simulation generation

[1908] The server collects employee performance data and work records, and uses this data to train a machine learning model. The input is performance data, and the output is the trained machine learning model.

[1909] Specific example of operation: The server outputs a log message saying "Training machine learning model with performance data..." and trains the model using Spark ML or TensorFlow.

[1910] Step 11:

[1911] Generating Simulation Scenarios

[1912] The server uses a trained model to generate business simulation scenarios. The input is the trained model, and the output is the simulation scenario.

[1913] Specific example of operation: The server outputs a log message saying "Generating business simulation scenarios...", generates a scenario, and provides it to the user.

[1914] Step 12:

[1915] Generating an effectiveness measurement report

[1916] The server automatically generates project results as effectiveness measurement reports. The input is project progress data, and the output is the effectiveness measurement report.

[1917] Specific example of operation: The server outputs a log message saying "Generating performance measurement report..." and generates a report in Excel or PDF format.

[1918] Step 13:

[1919] Report Provision

[1920] Users can view the generated performance measurement reports on the dashboard and download them as needed. The input is the performance measurement report, and the output is the report downloaded to the user's device.

[1921] Specific example of operation: A user clicks a file from the dashboard and downloads a PDF report.

[1922] Step 14:

[1923] Providing CRM-based employee support

[1924] The server manages each employee's work history and skill set, and provides appropriate resources and training based on user requests. Inputs include employee work history, skill set, and request data, while outputs include recommended resources and training plans.

[1925] Specific example of operation: The server outputs a log message saying "Recommending training resources for requested skill..." and provides relevant online courses and materials.

[1926] (Application Example 2)

[1927] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1928] Traditional business planning and project management systems automate tasks such as generating plans and measuring effectiveness based on past data, but they fail to consider the emotional state of users, potentially increasing worker stress and workload. Furthermore, real-time work instructions and dynamic task reallocation required complex settings and human intervention, making them inefficient. Additionally, a lack of individual support for factory workers could result in a decrease in overall productivity.

[1929] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically generating new business plans based on past project data and trend data using generative artificial intelligence; means for providing the generated business plans to the user and receiving user feedback; means for modifying or regenerating the generated business plans based on user feedback; means for dynamically generating a user interface and visually displaying the progress of business plans and projects to the user; means for collecting and analyzing project progress and results in real time; means for automatically generating effectiveness measurement reports based on real-time analysis results; means for training a machine learning model using the collected data and automatically generating business simulations using this model; means for collecting each employee's work history and skill set and recommending resources and training according to their needs; means for recognizing the user's emotional state using an emotion recognition engine and adjusting the content of the business plans based on the results; and means for providing work instructions in real time using a head-mounted display and performing dynamic work reallocation based on emotions. This allows for a reduction in the burden on workers by responding to user emotions, enabling improved work efficiency and increased productivity.

[1930] "Generative artificial intelligence" is an artificial intelligence technology that automatically generates new business plans by utilizing past project data and trend data.

[1931] "Providing to users" refers to the means of showing or presenting the generated business plan to users.

[1932] "Receiving user feedback" refers to the means of collecting opinions and reactions from users.

[1933] "Modifying or regenerating generated business plans" refers to the means of changing existing business plans or generating new ones based on user feedback.

[1934] "Dynamically generating a user interface" refers to a means of providing users with a visual display based on information and data that changes in real time.

[1935] "Collecting and analyzing project progress and results in real time" refers to methods for acquiring and analyzing project progress and results in real time.

[1936] "Automatically generating effectiveness measurement reports" refers to a method of automatically creating effectiveness measurement reports based on the progress and results of a project.

[1937] "Training a machine learning model" refers to the process of training a machine learning algorithm using collected data.

[1938] "Automatically generating business simulations" refers to a method of automatically creating business simulations using trained machine learning models.

[1939] "Recommending resources and training tailored to individual needs" means proposing necessary resources and training based on each employee's work history and skill set.

[1940] ...

Claims

1. A method for automatically generating new business plans based on past project data and trend data using generative artificial intelligence, A means of providing the generated business plan to the user and receiving user feedback, A means of modifying or regenerating business plans generated based on user feedback, A means of dynamically generating a user interface and visually displaying business plans and project progress to the user, A means of collecting and analyzing project progress and results in real time, A means for automatically generating effectiveness measurement reports based on real-time analysis results, A method for training a machine learning model using collected data and automatically generating business simulations using this model, A means of collecting each employee's work history and skill set, and recommending resources and training tailored to their needs, A system that includes this.

2. The system according to claim 1, further comprising means for the user to check the progress of the project and performance measurement reports through a user interface, and to decide on corrections or next actions as necessary.

3. The system according to claim 1, further comprising means for automatically generating individualized learning plans based on each employee's skill set and work history.

Images