system

Abstract

We provide a system that allows users to easily and efficiently analyze large amounts of data, obtain concrete and practical solutions, and create new business opportunities. [Solution] A system comprising: means for a user to upload business-related data; means for a server to receive and store the uploaded data; means for the server to preprocess the received data, including imputing missing values ​​and formatting the data; means for the server to analyze the preprocessed data and generate multiple AI models; means for the server to visualize the results of the generated AI models in a dashboard format; means for the server to generate optimal business improvement suggestions and new business ideas based on the analysis results; means for the user to confirm the proposed solutions; and means for the server to analyze other user data within the system and match users who can offer each other business opportunities.

Description

Technical Field

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

Background Art

[0002] Patent Document No. 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance; adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot; encoding the prompt; and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Currently, many corporations are seeking data-driven decision-making in business efficiency improvement and new business idea creation. However, it is difficult to appropriately organize and analyze huge amounts of business data and generate practical solutions. Also, existing solutions are insufficient in providing new business opportunities through effective matching among users. There is a need for a system that solves such problems and provides highly accurate data analysis and efficient business improvement proposals.

Means for Solving the Problems

[0005] The present invention is a system that includes means for a user to upload business-related data, means for a server to receive and store the uploaded data, means for the server to preprocess the received data, including imputing missing values ​​and formatting the data, means for the server to analyze the preprocessed data and generate multiple AI models, means for the server to visualize the results of the generated AI models in a dashboard format, means for the server to generate optimal business improvement suggestions and new business ideas based on the analysis results, means for the user to confirm the proposed solutions, and means for the server to analyze other user data within the system and match users who can offer each other business opportunities. As a result, users can easily and efficiently analyze large amounts of data, obtain concrete and practical solutions, and create new business opportunities.

[0006] A "user" is a corporation or individual that uses this system to input and upload business-related data, and to review and utilize the proposed solutions.

[0007] A "server" is a computer system that receives and stores data uploaded by users, performs preprocessing and analysis, generates multiple AI models, and visualizes the results in a dashboard format.

[0008] "Data" refers to all information related to business operations (e.g., sales data, inventory data, customer data) that users upload to the system.

[0009] A "database" is a storage device or storage system where uploaded data is stored.

[0010] "Preprocessing" refers to the process of imputing missing values ​​in uploaded data, correcting outliers, and standardizing data formats.

[0011] An "AI model" is an artificial intelligence algorithm used for data analysis, designed to provide generated analysis results and predictions.

[0012] A "dashboard" is an interface that visually displays analysis results and predictions generated by an AI model.

[0013] A "business improvement proposal" refers to a specific suggestion based on the analysis results of an AI model, aimed at improving the efficiency and performance of the user's work.

[0014] A "business idea" refers to a business plan or business opportunity that may be newly created based on the analysis results of an AI model.

[0015] "Matching" is the process by which a server analyzes other user data within the system and connects users who can offer each other business opportunities based on common challenges and complementary relationships. [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] It 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 to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 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 Example 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.

Mode 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 according 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 consulting service system for corporations that utilizes generative AI. In this system, users upload business-related data, and a server stores, preprocesses, and analyzes that data to generate optimal business improvement suggestions and new business ideas. Furthermore, the system can match users with each other, providing new business opportunities.

[0038] System Program Overview

[0039] User actions

[0040] 1. The user logs in to the web portal or dedicated application. They enter their authentication information here to establish access to the system.

[0041] 2. Users input specific challenges related to their work. For example, they input specific business needs such as "improving the accuracy of sales forecasts" or "optimizing inventory management."

[0042] 3. Users upload the necessary business data. The data formats vary widely, including CSV, Excel, and API. Uploaded data includes sales data, inventory data, customer data, and more.

[0043] Server Processing

[0044] 1. The server receives the data uploaded by the user and stores it in temporary storage. It then moves it to the database.

[0045] 2. The server performs data preprocessing. Specifically, it normalizes the data by imputing missing values, detecting and correcting outliers, and standardizing data formats.

[0046] 3. The server analyzes the pre-processed data. Here, multiple AI models are generated. For example, a sales forecasting model, a customer behavior analysis model, and an inventory optimization model are generated.

[0047] 4. The server visualizes the results of the generated AI model in a dashboard format. This allows users to visually understand the analysis results.

[0048] 5. The server generates optimal business improvement suggestions and new business ideas based on the results of the AI ​​model. Users can also review the proposed solutions.

[0049] 6. The server analyzes other user data within the system and matches users who can offer each other business opportunities.

[0050] Specific example

[0051] Case Study: Sales Data Analysis and Optimization in the Retail Industry

[0052] 1. The user (retail company A) logs into the system and uploads monthly sales data and inventory data.

[0053] 2. The server receives the data and saves it to the database. Simultaneously, it performs data imputation and correction of outliers.

[0054] 3. The server analyzes the pre-processed data and generates a sales forecasting model and an inventory optimization model.

[0055] 4. Based on the model generated by the server, the sales forecast for the next month and inventory status are displayed in a dashboard format.

[0056] 5. The server suggests a list of best-selling products and provides an optimal inventory replenishment plan. It also suggests the use of logistics services.

[0057] 6. The server suggests matching with another retail company (Company B) within the system, providing business opportunities such as conducting joint campaigns or jointly purchasing inventory.

[0058] This invention enables corporations to efficiently process vast amounts of data and implement concrete and effective business improvements. Furthermore, it allows for the creation of new business opportunities through effective matching between users.

[0059] The following describes the processing flow.

[0060] Step 1:

[0061] Users log in to the system using a web portal or a dedicated application. Users enter their authentication information (e.g., username, password) to establish access to the system.

[0062] Step 2:

[0063] Users input their current business challenges and requirements. For example, they provide the system with specific needs such as improving sales forecasting or optimizing inventory management.

[0064] Step 3:

[0065] Users upload business-related data. Upload formats include CSV files, Excel files, and data submitted via API. This data includes monthly sales data, inventory data, and customer data.

[0066] Step 4:

[0067] The server receives data uploaded by the user and stores it in temporary storage. Then, it moves the data to the database.

[0068] Step 5:

[0069] The server begins preprocessing the received data. Specifically, it performs tasks such as imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data.

[0070] Step 6:

[0071] The server performs initial analysis using pre-processed data. It extracts data trends and patterns, performs basic statistical processing, and then generates multiple AI models (e.g., sales forecasting model, customer behavior analysis model, inventory optimization model) based on this data.

[0072] Step 7:

[0073] The server trains the generated AI model and evaluates its accuracy. Training includes iterative processes that use historical data to improve the model's predictive accuracy.

[0074] Step 8:

[0075] The server converts the results of the trained model into a dashboard format. The results are transformed into visual components such as graphs, charts, and heatmaps, making them easy for users to understand.

[0076] Step 9:

[0077] Users access the generated dashboard to view the analysis results. The dashboard allows users to navigate to other pages to obtain more detailed information.

[0078] Step 10:

[0079] The server generates optimal business improvement suggestions and new business ideas based on the dashboard results. These suggestions are organized into a report and notified to the user.

[0080] Step 11:

[0081] The user accesses the proposed solution report and reviews its contents. They then implement the proposed solutions into their work and carry out the improvement measures.

[0082] Step 12:

[0083] The server analyzes other user data within the system and matches users who can offer each other business opportunities based on common challenges and complementary relationships.

[0084] Step 13:

[0085] The server proposes the most suitable business match to the user, providing contact information and specific collaboration proposals. Users can then collaborate with each other and maximize new business opportunities.

[0086] This process allows the system to efficiently analyze the vast amount of business data held by users, providing concrete and practical solutions while also creating new business opportunities.

[0087] (Example 1)

[0088] 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."

[0089] Modern corporations need to efficiently process vast amounts of business data and implement concrete and effective business improvements. Furthermore, creating new business opportunities through effective business matching between different corporations is crucial. Traditional systems struggled to integrate data preprocessing, AI model generation, and user matching, hindering effective business improvement and the creation of business opportunities.

[0090] 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.

[0091] In this invention, the server includes means for users to upload business-related data, means for the server to receive and store the uploaded data, means for the server to preprocess the received data, including imputing missing values ​​and detecting and correcting outliers, means for the server to analyze the preprocessed data and generate multiple machine learning models, means for the server to display the results of the generated machine learning models in a dashboard format using visualization means, means for the server to generate optimal business improvement suggestions and new business ideas based on the analysis results, means for the user to confirm the proposed solutions, and means for the server to analyze other user data within the system and match users who can offer each other business opportunities. This enables corporations to efficiently preprocess data and realize concrete business improvements and business matching based on the analysis results.

[0092] A "user" is the entity that uses this system to upload business data and review the analysis results and suggestions.

[0093] A "server" is an information processing device that receives data uploaded by users, stores it, preprocesses and analyzes it, and provides the user with the results of the generated AI model.

[0094] "Data upload" refers to the act of a user sending work-related data to this system.

[0095] "Preprocessing" is the process of imputing missing values ​​from received data, detecting and correcting outliers, and standardizing the data format.

[0096] A "machine learning model" is an algorithm generated based on data analysis to perform predictions and analyses related to specific tasks.

[0097] "Visualization methods" refer to methods that display the results of a generated machine learning model in a dashboard format, allowing users to understand them intuitively.

[0098] A "business improvement proposal" is a specific suggestion based on analysis results, aimed at improving the efficiency and performance of the user's work.

[0099] "Business matching" is the process of analyzing user data within a system and connecting users who can offer each other business opportunities.

[0100] "Data storage" refers to equipment or devices for temporarily or permanently storing uploaded data.

[0101] A "sales forecasting model" is a machine learning model that predicts future sales based on pre-processed data.

[0102] A "consumer behavior analysis model" is a machine learning model used to analyze customer behavior patterns based on pre-processed data.

[0103] An "inventory management model" is a machine learning model that uses pre-processed data to enable efficient inventory management.

[0104] This invention relates to a consulting service system for corporations that utilizes generative AI. In this system, when a user uploads business-related data, the server receives, stores, preprocesses, and analyzes that data to generate business improvement suggestions and new business ideas. The system can also match users with each other, providing new business opportunities.

[0105] Program processing

[0106] In this system, users upload business-related data through a dedicated web portal or application. After logging in and authenticating, users input specific business tasks and provide data via CSV, Excel files, or API.

[0107] The server is equipped with high-performance data storage, where incoming data is initially stored. It is then moved to the database for further preprocessing. This preprocessing includes imputing missing data values, detecting and correcting outliers, and standardizing data formats. These operations utilize libraries such as Python's Pandas and NumPy.

[0108] The pre-processed data then proceeds to the analysis phase. Here, the server generates multiple machine learning models using TENSORFLOW® and PyTorch. Specifically, these include a sales forecasting model, a consumer behavior analysis model, and an inventory management model.

[0109] The analysis results of the generated model are displayed in a dashboard format using visualization tools such as Tableau and Power BI. This makes it easier for users to visually understand the analysis results. The server also generates business improvement suggestions and new business ideas based on these results. Users can review the suggested solutions through the dashboard.

[0110] Furthermore, this system also includes a user matching function. Using a graph database powered by Neo4j, it matches users who can offer each other business opportunities. For example, it might suggest joint campaigns or joint inventory purchases.

[0111] Specific example

[0112] Case Study: Sales Data Analysis and Optimization in the Retail Industry

[0113] 1. The user (retail company A) logs into the system and uploads monthly sales data and inventory data.

[0114] 2. The server receives the data and saves it to the database. Simultaneously, it performs data imputation and corrects outliers. For example, it uses the Pandas "fillna" method or Z-scores to handle outliers.

[0115] 3. The server analyzes the pre-processed data and generates a sales forecasting model using TensorFlow. It also generates a customer behavior analysis model using PyTorch.

[0116] 4. Based on the generated model, the server displays the next month's sales forecast and inventory status in a dashboard format. Tableau is used to generate the dashboard.

[0117] 5. The server suggests a list of best-selling products and provides an optimal inventory replenishment plan. It also suggests the use of logistics services. Specifically, it inputs prompts such as the following into the AI ​​model: "What are the sales forecasts for the next month? Also, please suggest an inventory replenishment plan."

[0118] 6. The server suggests matching with another retail company (Company B) within the system, providing business opportunities such as conducting joint campaigns or jointly purchasing inventory.

[0119] This invention enables corporations to efficiently preprocess data and achieve business improvements and business matching based on the analysis results.

[0120] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0121] Step 1:

[0122] The user logs in.

[0123] The user opens a dedicated web portal or application and accesses the login screen. The user enters their username and password and clicks the "Login" button. The server receives this authentication information and compares it with the authentication information stored in the database. If authentication is successful, the server starts a session and redirects the user to the dashboard. In this process, the input is the user's authentication information (username and password), and the output is the authentication success or failure status.

[0124] Step 2:

[0125] Users enter business challenges.

[0126] The user clicks the "New Issue" button on the dashboard and enters a specific business issue into the displayed form. For example, they might enter a specific theme such as "Improving the accuracy of sales forecasts" and click the "Submit" button. The server receives the entered issue information and saves it to the database. In this case, the input is text data of the business issue, and the output is the issue information saved in the database.

[0127] Step 3:

[0128] The user uploads data.

[0129] The user clicks the "Data Upload" button, opening an upload window. The user uploads data by selecting a CSV or Excel file, or by specifying an API endpoint. The server receives this data, saves it to temporary storage, and then moves it to the database. The input in this step is the business data file or API endpoint information, and the output is the business data stored in temporary storage and the database.

[0130] Step 4:

[0131] Data preprocessing

[0132] The server reads the data stored in the database and begins preprocessing. Specifically, it performs missing value imputation (using the Pandas "fillna" method), detects and corrects outliers (using Z-scores), and standardizes the data format. The preprocessed data is then saved back to the database. In this case, the input is the stored raw data, and the output is the preprocessed data.

[0133] Step 5:

[0134] Data analysis and machine learning model generation

[0135] The server analyzes the pre-processed data and generates multiple machine learning models. Specifically, it generates a sales forecasting model using TensorFlow and a customer behavior analysis model using PyTorch. Each generated model is stored in a database. The input in this step is the pre-processed data, and the output is the parameters and prediction results of each generated machine learning model.

[0136] Step 6:

[0137] Visualization of Model Results

[0138] The server displays the results of the generated machine learning model in a dashboard format using visualization tools (such as Tableau). Users can visually confirm the analysis results through this dashboard. In this case, the input is the result data of the generated machine learning model, and the output is the visualized dashboard.

[0139] Step 7:

[0140] Generating business improvement proposals

[0141] The server generates optimal business improvement suggestions and new business ideas based on the model results. These might include inventory replenishment plans and marketing strategies to increase sales. Specifically, prompts such as "What are the sales forecasts for the next month? Also, please propose an inventory replenishment plan" are input into the AI ​​model. The input in this step is the analysis results of the machine learning model, and the output is text data of business improvement suggestions.

[0142] Step 8:

[0143] User matching

[0144] The server analyzes other user data within the system and matches users who can offer each other business opportunities. It uses Neo4j to build a graph database and identify highly relevant users. For example, it might propose joint campaigns or joint inventory purchases. In this case, the input is user data within the system, and the output is a notification of the matching results and the proposed solutions.

[0145] Through these processing steps, the system enables corporations to efficiently preprocess data and achieve business improvements and business matching based on the analysis results.

[0146] (Application Example 1)

[0147] 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."

[0148] In factory production environments, vast amounts of data are generated daily, and effectively utilizing this data to improve productivity is a crucial challenge. In particular, predicting equipment maintenance, optimizing inventory, and forecasting production require sophisticated analysis; performing these tasks manually is inefficient and prone to human error. Furthermore, collaboration with other factories is essential for achieving even greater efficiency.

[0149] 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.

[0150] In this invention, the server includes means for users to upload business-related data, means for the server to receive and store the uploaded data, means for the server to preprocess the received data, including imputing missing values ​​and formatting the data, means for the server to analyze the preprocessed data and generate multiple AI models, means for the server to visualize the results of the generated AI models in a dashboard format, means for the server to generate optimal business improvement proposals and new business ideas based on the analysis results, means for the user to confirm the proposed solutions, means for the server to analyze other user data within the system and match users who can offer each other business opportunities, and means for the server to generate production forecasting models, equipment maintenance models, and inventory optimization models based on the preprocessed data, and apply the results of these models to factory production operations. This enables improved productivity and optimization of operations by efficiently analyzing and utilizing a large amount of data from the factory floor.

[0151] A "user" is an individual or organization that accesses the system and uploads business-related data.

[0152] A "server" is a computer device that stores, preprocesses, and analyzes data received from users, and then provides the results.

[0153] "Data preprocessing" refers to a series of processes that involve imputing missing values ​​in uploaded data, formatting the data, and converting it into a format suitable for analysis.

[0154] An "AI model" is an artificial intelligence model built to perform analyses and predictions useful for specific tasks, based on pre-processed data.

[0155] A "dashboard" is an interface used to visually display data analysis results.

[0156] A "business improvement proposal" is a specific suggestion to improve the user's work efficiency based on the analysis results of an AI model.

[0157] A "business idea" refers to the potential business opportunities and strategies that are newly created from the analysis results of an AI model.

[0158] "Matching" refers to the process of analyzing different user data within a system and connecting users who can offer each other business opportunities.

[0159] A "production forecasting model" is an AI model built to predict future production volumes based on pre-processed data.

[0160] A "device maintenance model" is an AI model that analyzes device operating data to predict future maintenance schedules and necessary maintenance tasks.

[0161] An "inventory optimization model" is an AI model that uses inventory data to determine the optimal inventory level and replenishment timing.

[0162] To implement this invention, the following hardware and software are used.

[0163] hardware

[0164] Server: A high-performance computing server is used to receive, store, preprocess, and analyze data.

[0165] Terminal: A device (such as a PC, tablet, or smartphone) used by the user to upload data and view analysis results.

[0166] software

[0167] Database: Use MySQL (registered trademark) to store uploaded data.

[0168] AI model creation framework: Generates AI models using TensorFlow or PyTorch.

[0169] Dashboard tool: Use Tableau to visually display the analysis results.

[0170] Program processing

[0171] The server will execute the following processes:

[0172] 1. Receiving and storing data:

[0173] The server receives business data uploaded by users (e.g., production data, inventory data, equipment operation data, etc.) and stores it in temporary storage. Afterward, this data is moved to a database (MySQL).

[0174] 2. Data preprocessing:

[0175] The server formats the data by imputing missing values, detecting and correcting outliers, and standardizing the data format. This makes the data suitable for analysis.

[0176] 3. Generation and analysis of AI models:

[0177] The server generates multiple AI models—production forecasting models, equipment maintenance models, and inventory optimization models—based on pre-processed data. AI model creation frameworks (TensorFlow, PyTorch) are used for this purpose.

[0178] 4. Visualization of analysis results:

[0179] The server visually displays the results of the generated AI model in a dashboard format. A dashboard tool (Tableau) is used to make it easy for users to understand the results.

[0180] 5. Proposing business improvements and generating business ideas:

[0181] Based on the results of the AI ​​model, the server generates specific business improvement suggestions and new business ideas to optimize the user's work. These suggestions can then be reviewed by the user.

[0182] 6. User matching:

[0183] The server analyzes other users' data within the system and matches users who can offer each other business opportunities. This process creates new business opportunities.

[0184] Specific example

[0185] For example, if a factory manager uploads production data with the goal of "improving machine utilization," this system works as follows:

[0186] 1. The factory manager uploads production data and operational data in CSV format.

[0187] 2. The server receives the data and saves it to the MySQL database.

[0188] 3. The server performs data preprocessing, including imputing outliers and missing values.

[0189] 4. Based on the pre-processed data, the server generates an AI model (e.g., production forecasting model, equipment maintenance model).

[0190] 5. The server displays the results in a dashboard format and provides specific improvement suggestions to the factory manager.

[0191] Example of a prompt

[0192] "To improve current machine utilization, please generate optimal improvement suggestions based on the following data. This data includes production line operating hours, product types, and monthly production volume."

[0193] In this way, this system can effectively support improvements in factory productivity and optimization of operations.

[0194] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0195] Step 1:

[0196] Users upload business-related data to the system using their terminals. Specifically, they upload production data, inventory data, equipment operation data, etc., in CSV or Excel format via a dedicated application or web portal. At this time, users can specify issues such as "improving machine utilization" or "optimizing raw material procurement," which are entered into the system as prompt messages.

[0197] Step 2:

[0198] The server receives data uploaded by the user and stores it in temporary storage. Next, it moves it to the database (MySQL) and saves it. Here, the input is the uploaded business data, and the output is the formatted data stored in the database.

[0199] Step 3:

[0200] The server preprocesses the data stored in the database. Specifically, it imputes missing values, detects and corrects outliers, and standardizes the data format. This preprocessing shapes the data into a clean format suitable for analysis. The input is the unformatted data retrieved from the database, and the output is the preprocessed, normalized data.

[0201] Step 4:

[0202] The server analyzes pre-processed data and generates multiple AI models. For example, it generates production forecasting models, equipment maintenance models, and inventory optimization models. AI model creation frameworks (TensorFlow, PyTorch) are used, and models are built based on the data. The input is pre-processed data, and the output is the generated AI models.

[0203] Step 5:

[0204] The server visualizes the results of the generated AI model in a dashboard format. Using a dashboard tool (Tableau), the results are displayed in a user-friendly, visual format. Specifically, predictive graphs and heatmaps are displayed. The input is the analysis results of the generated AI model, and the output is the visualized results on the dashboard.

[0205] Step 6:

[0206] The server generates optimal business improvement suggestions and new business ideas based on the analysis results of the AI ​​model. For example, it generates specific suggestions such as equipment maintenance schedules, inventory replenishment plans, and cost reduction measures. This allows users to obtain concrete action plans to optimize their operations. The input is the analysis results of the AI ​​model, and the output is business improvement suggestions and business ideas.

[0207] Step 7:

[0208] Users review the proposed solutions through their devices. They use dashboards and dedicated applications to examine the generated business improvement suggestions and ideas in detail and take necessary actions. The input is the suggestions provided by the server, and the output is the user's review and implementation of the suggestions.

[0209] Step 8:

[0210] The server analyzes other user data within the system and matches users who can offer each other business opportunities. This enables cooperation and joint ventures between different factories and companies. Specifically, it searches for suitable users within the database and identifies common business needs and synergies. The input is other user data within the system, and the output is the matched business opportunities.

[0211] 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.

[0212] This invention combines a generative AI-powered consulting service system for corporations with an emotion engine that recognizes user emotions. In this system, users upload business-related data, which is then stored, preprocessed, and analyzed by a server to generate optimal business improvement suggestions and new business ideas. Furthermore, by utilizing the emotion engine, suggestions tailored to the user's emotions become possible, providing more effective solutions.

[0213] System Program Overview

[0214] User actions

[0215] 1. The user logs in to the web portal or dedicated application. They enter their authentication information to establish access to the system.

[0216] 2. The user inputs their current business challenges and requirements. For example, they provide the system with specific needs such as improving sales forecasting or optimizing inventory management.

[0217] 3. Users upload business-related data. Data formats include CSV files, Excel files, and API-based formats, and include monthly sales data, inventory data, customer data, etc.

[0218] Server Processing

[0219] 1. The server receives the data uploaded by the user and stores it in temporary storage. Then, it moves the data to the database.

[0220] 2. The server begins data preprocessing. Specifically, it performs data imputation, detects and corrects outliers, standardizes data formats, and normalizes the data.

[0221] 3. The server performs initial analysis using the pre-processed data. It extracts data trends and patterns and performs basic statistical processing.

[0222] 4. The server generates multiple AI models (sales forecasting model, customer behavior analysis model, inventory optimization model, etc.), trains these models, and evaluates their accuracy.

[0223] 5. The server converts the results of the trained model into a dashboard format, transforming them into visual components such as graphs, charts, and heatmaps.

[0224] Emotional Engine Processing

[0225] 1. The device sends user operation information and input data to the emotion engine.

[0226] 2. The emotion engine (server) analyzes the user's emotions. It identifies the type of emotion (e.g., joy, sadness, stress) and evaluates its intensity.

[0227] 3. The server displays the results of the emotion engine on a dashboard, allowing users to visually check their current emotional state.

[0228] Solution proposal

[0229] 1. The server adjusts the suggested solutions based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, it will suggest a simpler and easier-to-implement solution.

[0230] 2. The server organizes the proposed content into a report format and notifies the user.

[0231] 3. The user accesses the provided solution report, reviews its contents, and implements them.

[0232] Matching proposal

[0233] 1. The server analyzes other user data within the system to identify common issues and complementary relationships.

[0234] 2. The server proposes the most suitable business match to the user, providing contact information and specific collaboration proposals. Users can collaborate with each other and maximize new business opportunities.

[0235] Specific example

[0236] Case Study: Data Analysis and the Use of Emotion Engines in the Retail Industry

[0237] 1. The user (retail company A) logs into the system and uploads the necessary sales data and inventory data.

[0238] 2. The server receives and stores the data, and performs missing value imputation and outlier correction.

[0239] 3. The server uses the pre-processed data to generate a sales forecasting model and an inventory optimization model.

[0240] 4. The server trains the model and displays the results on the dashboard.

[0241] 5. The device sends user operation information to the emotion engine, which analyzes the user's emotions.

[0242] 6. The server proposes and presents solutions that are tailored to the user's emotions.

[0243] 7. The server analyzes the commonalities between retail company A and another retail company B, and proposes a match.

[0244] The system of this invention enables efficient data analysis and customized suggestions based on user sentiment, maximizing the effectiveness of business improvement while creating new business opportunities.

[0245] The following describes the processing flow.

[0246] Step 1:

[0247] The user logs into the system using a web portal or dedicated application. They enter their authentication information (e.g., username, password) to establish access to the system.

[0248] Step 2:

[0249] Users input their current business challenges and requirements. For example, they provide the system with specific needs such as "improving the accuracy of sales forecasts" or "optimizing inventory management."

[0250] Step 3:

[0251] Users upload business-related data. Upload formats include CSV files, Excel files, and API-based formats, and this data includes monthly sales data, inventory data, customer data, and more.

[0252] Step 4:

[0253] The server receives the data uploaded by the user and stores it in temporary storage. It then moves it to the database.

[0254] Step 5:

[0255] The server begins preprocessing the received data. Specifically, it performs tasks such as imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data.

[0256] Step 6:

[0257] The server performs initial analysis using pre-processed data. It extracts data trends and patterns and performs basic statistical processing.

[0258] Step 7:

[0259] The server generates multiple AI models (such as a sales forecasting model, a customer behavior analysis model, and an inventory optimization model), trains these models, and evaluates their accuracy.

[0260] Step 8:

[0261] The server converts the results of the trained model into a dashboard format, transforming them into visual components such as graphs, charts, and heatmaps.

[0262] Step 9:

[0263] Users access the generated dashboard to view the analysis results. The dashboard allows users to navigate to other pages to obtain more detailed information.

[0264] Step 10:

[0265] The device collects user operation information and input data in real time and sends it to the emotion engine. Operation information includes mouse movements, button clicks, and input speed.

[0266] Step 11:

[0267] The emotion engine within the server analyzes collected operation information and input data to identify the user's emotions. For example, it can detect whether the user is stressed or satisfied.

[0268] Step 12:

[0269] The server displays the results of the emotion engine on a dashboard, allowing users to visually check their current emotional state.

[0270] Step 13:

[0271] The server adjusts the suggested solutions based on the user's emotions, as recognized by the emotion engine. For example, if the user is feeling stressed, it will suggest a simpler and easier-to-implement solution.

[0272] Step 14:

[0273] The server organizes the proposed content into a report format and notifies the user.

[0274] Step 15:

[0275] The user accesses the provided solution report, reviews its contents, and implements them.

[0276] Step 16:

[0277] The server analyzes other user data within the system and matches users who can offer each other business opportunities based on common challenges and complementary relationships.

[0278] Step 17:

[0279] The server proposes the most suitable business match to the user, providing contact information and specific collaboration proposals, enabling users to maximize new business opportunities.

[0280] (Example 2)

[0281] 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".

[0282] In a conventional system, a user can upload data related to their work and obtain analysis results, but it is difficult to make proposals considering the user's emotional state. Therefore, in order to maximize the efficiency and effectiveness of the user's work improvement, customized proposals reflecting the emotional state are necessary. In addition, appropriate business matching with other users is also required, but there is a limit to automatically performing this in the current system. To solve such problems, an object of the present invention is to provide a system that analyzes the emotional state of a user and provides business improvement proposals based on the results and effective matching with other users.

[0283] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0284] In this invention, the server includes means for a user to upload information related to their work, means for the server to receive and store the uploaded information, means for the server to preprocess the received information and perform missing value supplementation and information shaping, means for generating a plurality of machine learning models, means for visualizing the results of the machine learning models in a dashboard format, means for generating optimal business improvement proposals and new business ideas based on the analysis results, means for analyzing the emotional state of the user using an emotion analysis engine and displaying the results, means for adjusting the proposed content based on the emotional state of the user, and means for analyzing other user information in the system and matching users who can provide business opportunities for each other. Thereby, it is possible to make proposals reflecting the emotional state of the user, maximize the efficiency and effectiveness of work improvement, and realize appropriate business matching with other users.

[0285] A "user" is an end user who inputs and uploads information related to their work using the system.

[0286] A "server" is a central processing unit that receives information uploaded from a user and performs preprocessing, analysis, generation of a machine learning model, visualization of results, and emotion analysis.

[0287] "Business-related information" refers to various types of data necessary for business improvement and new business proposals, such as monthly sales data, inventory data, and customer data uploaded by users.

[0288] "Preprocessing" refers to the process of filling in missing data values, detecting and correcting outliers, unifying data formats, and normalizing data, which shapes the data into a state suitable for analysis.

[0289] "Machine learning model" refers to a model based on statistical and machine learning algorithms such as sales prediction models, customer behavior analysis models, and inventory optimization models, which are generated using preprocessed data.

[0290] "Dashboard" is a user interface for visually displaying the results of a machine learning model, including graphs, charts, heatmaps, etc.

[0291] "Sentiment analysis engine" is an analysis engine that analyzes user input data and operation information and evaluates the type (such as joy, sadness, stress, etc.) and intensity of emotions.

[0292] "Business improvement proposal" is a proposal beneficial for improving the efficiency of the user's business and formulating new businesses based on the results of data analysis and sentiment analysis.

[0293] "Business matching" is a function that analyzes other user information within the system and automatically matches users who can provide business opportunities to each other.

[0294] The present invention is a system in which a user uploads business-related information, and the server analyzes the information to generate business improvement proposals and new business ideas. This system also incorporates a sentiment analysis engine, enabling customized proposals that reflect the user's emotional state.

[0295] First, users establish access to the system by logging in to a web portal or dedicated application and entering their authentication information. Users then enter their current business challenges and requirements into forms or text fields and upload business-related data files (e.g., CSV, Excel, API, etc.). This data includes monthly sales data, inventory data, customer data, and so on.

[0296] Next, the server receives the information uploaded by the user and stores it in temporary storage. Then, it moves the data to the database. At this point, the server begins data preprocessing, including imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data. This prepares the data for analysis.

[0297] The server performs an initial analysis using pre-processed data, extracting trends and patterns and performing basic statistical processing. It then generates multiple machine learning models, such as sales forecasting models, customer behavior analysis models, and inventory optimization models, and trains these models with training data. Once model training is complete, its accuracy is evaluated, and the highest-performing models are displayed on the dashboard. The dashboard includes visual components such as graphs, charts, and heatmaps.

[0298] Furthermore, the device sends user operation information and input data to the emotion analysis engine. The emotion analysis engine (server) analyzes the user's emotions and evaluates the type and intensity of emotions such as joy, sadness, and stress. The results of the emotion analysis are displayed on the dashboard, allowing the user to visually check their current emotional state.

[0299] The server adjusts its suggestions based on the results of the emotion analysis engine. For example, if the user is feeling stressed, it will suggest simpler and easier-to-implement solutions. These solutions are organized in a report format and communicated to the user. The user can access the presented solution report, review its contents, and implement them.

[0300] In addition, the server analyzes other user information within the system to find common issues and complementary relationships. It proposes the optimal business match to the user and provides contact information and specific collaboration plans. This enables users to cooperate with each other and maximize the utilization of new business opportunities.

[0301] Explanation of operations with specific examples

[0302] For example, when a user (retail company A) logs in to the system and uploads the necessary sales data and inventory data, the server receives and stores these data, performs missing value supplementation and outlier correction. Next, it generates a sales prediction model and an inventory optimization model, and visualizes the training results on the dashboard. Then, the terminal sends the user's operation information to the sentiment analysis engine, and the sentiment analysis engine analyzes the user's sentiment. Finally, the server proposes a solution according to the sentiment and promotes business matching with other retail companies.

[0303] Examples of prompt sentences

[0304] "Please predict the sales amount for the next six months based on the inventory data."

[0305] "Please propose a specific action plan to improve customer satisfaction."

[0306] "Please teach me the optimal method for inventory management."

[0307] The flow of specific processing in Example 2 will be described using FIG. 13.

[0308] Step 1: User authentication and login

[0309] The user logs in to a web portal or dedicated application. The server receives the entered authentication information (user ID and password) and sends it to the authentication server to perform authentication. If authentication is successful, the server redirects the user to their individual dashboard.

[0310] Input: User ID, Password

[0311] Output: Authenticated access session, user-specific dashboard

[0312] Step 2: Enter and upload business data

[0313] Users input business challenges and requirements related to their operations into the system. Next, they upload business-related data files (CSV files, Excel files, APIs, etc.). This data includes monthly sales data, inventory data, customer data, and so on.

[0314] Input: Business issues, data files

[0315] Output: Business issues and data files to send to the server

[0316] Step 3: Data preprocessing and storage

[0317] The server receives data uploaded by users and stores it in temporary storage. Then, the data is moved to the database. Data preprocessing includes imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data.

[0318] Input: Uploaded data file

[0319] Output: Preprocessed data, saved to database

[0320] Step 4: Data Analysis and AI Model Generation

[0321] The server performs initial analysis using pre-processed data. This step involves extracting data trends and patterns and performing basic statistical processing. Next, it generates multiple machine learning models, such as a sales forecasting model, a customer behavior analysis model, and an inventory optimization model. These models are trained on the training data, and their accuracy is evaluated. The results of the completed models are displayed on the dashboard.

[0322] Input: Preprocessed data

[0323] Output: Machine learning model, analysis results displayed on the dashboard

[0324] Step 5: Analyzing the Emotion Engine

[0325] The device sends user operation information and input data to the sentiment analysis engine. The sentiment analysis engine (server) analyzes the user's emotions and evaluates their type and intensity (e.g., joy, sadness, stress). The sentiment analysis results are displayed on the dashboard.

[0326] Input: Operation information, input data

[0327] Output: Sentiment analysis results, displayed on the dashboard.

[0328] Step 6: Proposing the optimal solution

[0329] The server customizes suggestions based on the sentiment analysis results. For example, if the user is feeling stressed, simple and easy-to-implement solutions will be suggested. These suggestions are organized in a report format and notified to the user.

[0330] Input: Sentiment analysis results

[0331] Output: Proposal report, user notification

[0332] Step 7: Propose User Matching

[0333] The server analyzes information from other users within the system to identify common challenges and complementary relationships. It then proposes optimal business matches to users, providing contact information and specific collaboration proposals. This enables users to collaborate and maximize new business opportunities.

[0334] Input: Information from other users, common challenges

[0335] Output: Business matching proposals, contact information, collaboration proposals

[0336] (Application Example 2)

[0337] 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 device 14 will be referred to as the "terminal."

[0338] Traditional factory production management systems commonly utilize data analysis and AI models to optimize production efficiency and quality, but they have not adequately provided solutions that take into account the emotional state of employees. Therefore, it has been difficult to flexibly reallocate tasks and adjust production schedules according to employee motivation and stress levels, creating a need for improved production efficiency and a better working environment for employees.

[0339] 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.

[0340] In this invention, the server includes means for users to upload business-related data, means for the server to receive and store the uploaded data, means for the server to preprocess the received data, including imputing missing values ​​and formatting the data, means for the server to analyze the preprocessed data and generate multiple AI models, means for the server to visualize the results of the generated AI models in a dashboard format, means for the server to generate optimal business improvement suggestions and new business ideas based on the analysis results, means for the user to confirm the proposed solutions, means for the server to analyze other user data within the system and match users who can offer each other business opportunities, means including an emotion engine that analyzes the emotional state of factory employees in real time, and means for proposing optimal production schedules and tasks based on the emotional state. This makes it possible to propose appropriate production schedules that take into account the emotional state of employees and to reallocate tasks to reduce stress.

[0341] "User" refers to an individual or legal entity that uses the system.

[0342] "Business-related data" refers to all data related to the operation of a factory or other business, such as production data, operational data, and quality data.

[0343] "Uploading" refers to the act of a user sending data from their device to a server.

[0344] A "server" refers to a computing system that receives, stores, preprocesses, analyzes, generates AI models, and proposes solutions for data.

[0345] "Preprocessing" refers to the initial processing performed on received data, specifically, imputing missing values, correcting outliers, and formatting the data.

[0346] "Missing value imputation" refers to the process of filling in missing values ​​in a dataset using appropriate methods.

[0347] "Formatting" refers to the process of converting data into a format suitable for analysis and model generation.

[0348] "Analysis" refers to the process of analyzing pre-processed data using statistical methods or machine learning techniques.

[0349] An "AI model" refers to a predictive or analytical model generated using artificial intelligence.

[0350] A "dashboard" refers to an interface used to visually display data and analysis results.

[0351] A "solution" refers to specific suggestions or ideas for improving a user's work.

[0352] "Matching" refers to analyzing data from multiple users within a system and proposing mutually beneficial business relationships.

[0353] The term "emotion engine" refers to technology used to analyze employees' emotional states in real time.

[0354] "Production schedule" refers to the plan for production activities in a factory.

[0355] A "task" refers to an individual job or role within a factory.

[0356] A "business idea" refers to a new proposal or concept aimed at innovating the user's business operations.

[0357] A "business improvement proposal" refers to a specific plan for improvement aimed at increasing the efficiency and quality of business operations.

[0358] The system for realizing this invention is configured to optimize factory production management. The main components of the system and their operation are described below.

[0359] Hardware configuration

[0360] 1. Server: Receives, stores, preprocesses, analyzes, and generates multiple AI models from data.

[0361] 2. Terminal: Sends employee facial expressions and voice data to the emotion engine.

[0362] 3. Sensors: Collect production data within the factory (working hours, product quality, operating rate, etc.).

[0363] 4. Camera: Detects employees' facial expressions and provides data.

[0364] 5. Microphone: Records employee voices and provides data.

[0365] Software Configuration

[0366] 1. Pandas: Load and preprocess the data.

[0367] 2. Scikit-learn: Used to train and evaluate models.

[0368] 3. EmotionEngine: A hypothetical emotion analysis engine that analyzes the emotional state of employees.

[0369] Data processing and analysis

[0370] User actions:

[0371] Users upload work-related data via their terminals. This data includes production and quality data. Users also input current challenges and requirements in production management.

[0372] Server processing:

[0373] The server stores the uploaded data in temporary storage and then moves it to the database. Next, it performs preprocessing such as imputing missing values, correcting outliers, and formatting the data. The preprocessed data is then analyzed to generate multiple AI models, such as production efficiency models and quality prediction models, and trained. The results of the trained models are visualized in a dashboard format.

[0374] Analysis of the emotion engine:

[0375] The terminal transmits the factory worker's facial expressions and voice data to the emotion engine. The emotion engine analyzes the worker's emotional state in real time and sends the results to the server. The server displays the emotion engine's results on a dashboard, allowing users to visually confirm them.

[0376] Proposed solution:

[0377] The server suggests optimal production schedules and tasks based on employee emotions recognized by the emotion engine. For example, if an employee is experiencing high stress levels, the server will suggest assigning them less demanding tasks. These suggestions are provided in dashboard and report formats for user review.

[0378] Specific example

[0379] As a practical example, suppose a factory manager logs into the system and uploads production data. The server preprocesses the data and trains a production efficiency model. Simultaneously, terminals that detect employee facial expressions and voice data analyze them using an emotion engine and send the results to the server. The server integrates this data to assign less demanding tasks to employees experiencing high stress levels and suggests optimizing the production schedule.

[0380] Examples of prompts for a generative AI model include the following:

[0381] "Based on the current stress levels of the employees, please propose an optimal production schedule. The data format is as follows: {employee_id: 123, stress_level: 0.8, task_complexity: high}"

[0382] This enables flexible production management that takes into account the emotional state of employees.

[0383] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0384] Step 1:

[0385] The server receives the user's business data and saves it to temporary storage.

[0386] Input: User-uploaded business data (e.g., production data, quality data).

[0387] Specific operation: The server saves the data as a temporary file and then moves it to the database. The output is the production data stored in the database.

[0388] Step 2:

[0389] The server preprocesses the data it receives.

[0390] Input: Production data moved from temporary storage.

[0391] Specific operation: The server uses the Pandas library to impute missing values ​​with the mean, detect and correct outliers, and normalize the data to a consistent format. The output is pre-processed data.

[0392] Step 3:

[0393] The server analyzes the pre-processed data and generates an AI model.

[0394] Input: Preprocessed data.

[0395] Specific operation: The server uses the Scikit-learn library to generate production efficiency models and quality prediction models from the data, and then trains these models. The output is the trained AI model.

[0396] Step 4:

[0397] The server visualizes the results of the generated AI model in a dashboard format.

[0398] Input: Output result of a trained AI model.

[0399] Specific operation: The server converts the results into visual components such as graphs, charts, and heatmaps, and displays them on the dashboard. The output is the visual analysis results on the dashboard.

[0400] Step 5:

[0401] The terminal transmits the facial expressions and voice data of factory workers to the emotion engine.

[0402] Input: Facial expression data and voice data of employees collected by cameras and microphones.

[0403] Specific operation: The device sends this data to the emotion engine in real time. The output is the data sent to the emotion engine.

[0404] Step 6:

[0405] The emotion engine analyzes the emotional state of employees.

[0406] Input: Facial expression data and audio data sent from the device.

[0407] Specific operation: The emotion engine analyzes the employee's emotions and sends the results to the server. The output is the analyzed emotion data.

[0408] Step 7:

[0409] The server uses the results from the emotion engine to suggest the optimal production schedule and tasks.

[0410] Input: Sentimental data sent from the emotion engine and results from a trained AI model.

[0411] Specific operation: The server assesses employee stress levels and motivation, and proposes optimizations to production schedules and task reallocations. For example, it suggests less demanding tasks to employees with high stress levels. The output is a proposal for the optimal production schedule and tasks.

[0412] Step 8:

[0413] The server provides the suggestions in dashboard and report format.

[0414] Input: Suggestions for optimal production schedules and tasks.

[0415] Specific operation: The server converts the suggested content into a visually easy-to-understand format, displays it on the dashboard, and notifies the user in the form of a report. The output is the suggested content provided on the dashboard and in the report.

[0416] This series of processes makes it possible to optimize factory production management in a way that takes into account the emotional state of employees.

[0417] 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.

[0418] 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.

[0419] 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.

[0420] [Second Embodiment]

[0421] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0422] 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.

[0423] 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).

[0424] 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.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] 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".

[0433] This invention relates to a consulting service system for corporations that utilizes generative AI. In this system, users upload business-related data, and a server stores, preprocesses, and analyzes that data to generate optimal business improvement suggestions and new business ideas. Furthermore, the system can match users with each other, providing new business opportunities.

[0434] System Program Overview

[0435] User actions

[0436] 1. The user logs in to the web portal or dedicated application. They enter their authentication information here to establish access to the system.

[0437] 2. Users input specific challenges related to their work. For example, they input specific business needs such as "improving the accuracy of sales forecasts" or "optimizing inventory management."

[0438] 3. Users upload the necessary business data. The data formats vary widely, including CSV, Excel, and API. Uploaded data includes sales data, inventory data, customer data, and more.

[0439] Server Processing

[0440] 1. The server receives the data uploaded by the user and stores it in temporary storage. It then moves it to the database.

[0441] 2. The server performs data preprocessing. Specifically, it normalizes the data by imputing missing values, detecting and correcting outliers, and standardizing data formats.

[0442] 3. The server analyzes the pre-processed data. Here, multiple AI models are generated. For example, a sales forecasting model, a customer behavior analysis model, and an inventory optimization model are generated.

[0443] 4. The server visualizes the results of the generated AI model in a dashboard format. This allows users to visually understand the analysis results.

[0444] 5. The server generates optimal business improvement suggestions and new business ideas based on the results of the AI ​​model. Users can also review the proposed solutions.

[0445] 6. The server analyzes other user data within the system and matches users who can offer each other business opportunities.

[0446] Specific example

[0447] Case Study: Sales Data Analysis and Optimization in the Retail Industry

[0448] 1. The user (retail company A) logs into the system and uploads monthly sales data and inventory data.

[0449] 2. The server receives the data and saves it to the database. Simultaneously, it performs data imputation and correction of outliers.

[0450] 3. The server analyzes the pre-processed data and generates a sales forecasting model and an inventory optimization model.

[0451] 4. Based on the model generated by the server, the sales forecast for the next month and inventory status are displayed in a dashboard format.

[0452] 5. The server suggests a list of best-selling products and provides an optimal inventory replenishment plan. It also suggests the use of logistics services.

[0453] 6. The server suggests matching with another retail company (Company B) within the system, providing business opportunities such as conducting joint campaigns or jointly purchasing inventory.

[0454] This invention enables corporations to efficiently process vast amounts of data and implement concrete and effective business improvements. Furthermore, it allows for the creation of new business opportunities through effective matching between users.

[0455] The following describes the processing flow.

[0456] Step 1:

[0457] Users log in to the system using a web portal or a dedicated application. Users enter their authentication information (e.g., username, password) to establish access to the system.

[0458] Step 2:

[0459] Users input their current business challenges and requirements. For example, they provide the system with specific needs such as improving sales forecasting or optimizing inventory management.

[0460] Step 3:

[0461] Users upload business-related data. Upload formats include CSV files, Excel files, and data submitted via API. This data includes monthly sales data, inventory data, and customer data.

[0462] Step 4:

[0463] The server receives data uploaded by the user and stores it in temporary storage. Then, it moves the data to the database.

[0464] Step 5:

[0465] The server begins preprocessing the received data. Specifically, it performs tasks such as imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data.

[0466] Step 6:

[0467] The server performs initial analysis using pre-processed data. It extracts data trends and patterns, performs basic statistical processing, and then generates multiple AI models (e.g., sales forecasting model, customer behavior analysis model, inventory optimization model) based on this data.

[0468] Step 7:

[0469] The server trains the generated AI model and evaluates its accuracy. Training includes iterative processes that use historical data to improve the model's predictive accuracy.

[0470] Step 8:

[0471] The server converts the results of the trained model into a dashboard format. The results are transformed into visual components such as graphs, charts, and heatmaps, making them easy for users to understand.

[0472] Step 9:

[0473] Users access the generated dashboard to view the analysis results. The dashboard allows users to navigate to other pages to obtain more detailed information.

[0474] Step 10:

[0475] The server generates optimal business improvement suggestions and new business ideas based on the dashboard results. These suggestions are organized into a report and notified to the user.

[0476] Step 11:

[0477] The user accesses the proposed solution report and reviews its contents. They then implement the proposed solutions into their work and carry out the improvement measures.

[0478] Step 12:

[0479] The server analyzes other user data within the system and matches users who can offer each other business opportunities based on common challenges and complementary relationships.

[0480] Step 13:

[0481] The server proposes the most suitable business match to the user, providing contact information and specific collaboration proposals. Users can then collaborate with each other and maximize new business opportunities.

[0482] This process allows the system to efficiently analyze the vast amount of business data held by users, providing concrete and practical solutions while also creating new business opportunities.

[0483] (Example 1)

[0484] 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".

[0485] Modern corporations need to efficiently process vast amounts of business data and implement concrete and effective business improvements. Furthermore, creating new business opportunities through effective business matching between different corporations is crucial. Traditional systems struggled to integrate data preprocessing, AI model generation, and user matching, hindering effective business improvement and the creation of business opportunities.

[0486] 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.

[0487] In this invention, the server includes means for users to upload business-related data, means for the server to receive and store the uploaded data, means for the server to preprocess the received data, including imputing missing values ​​and detecting and correcting outliers, means for the server to analyze the preprocessed data and generate multiple machine learning models, means for the server to display the results of the generated machine learning models in a dashboard format using visualization means, means for the server to generate optimal business improvement suggestions and new business ideas based on the analysis results, means for the user to confirm the proposed solutions, and means for the server to analyze other user data within the system and match users who can offer each other business opportunities. This enables corporations to efficiently preprocess data and realize concrete business improvements and business matching based on the analysis results.

[0488] A "user" is the entity that uses this system to upload business data and review the analysis results and suggestions.

[0489] A "server" is an information processing device that receives data uploaded by users, stores it, preprocesses and analyzes it, and provides the user with the results of the generated AI model.

[0490] "Data upload" refers to the act of a user sending work-related data to this system.

[0491] "Preprocessing" is the process of imputing missing values ​​from received data, detecting and correcting outliers, and standardizing the data format.

[0492] A "machine learning model" is an algorithm generated based on data analysis to perform predictions and analyses related to specific tasks.

[0493] "Visualization methods" refer to methods that display the results of a generated machine learning model in a dashboard format, allowing users to understand them intuitively.

[0494] A "business improvement proposal" is a specific suggestion based on analysis results, aimed at improving the efficiency and performance of the user's work.

[0495] "Business matching" is the process of analyzing user data within a system and connecting users who can offer each other business opportunities.

[0496] "Data storage" refers to equipment or devices for temporarily or permanently storing uploaded data.

[0497] A "sales forecasting model" is a machine learning model that predicts future sales based on pre-processed data.

[0498] A "consumer behavior analysis model" is a machine learning model used to analyze customer behavior patterns based on pre-processed data.

[0499] An "inventory management model" is a machine learning model that uses pre-processed data to enable efficient inventory management.

[0500] This invention relates to a consulting service system for corporations that utilizes generative AI. In this system, when a user uploads business-related data, the server receives, stores, preprocesses, and analyzes that data to generate business improvement suggestions and new business ideas. The system can also match users with each other, providing new business opportunities.

[0501] Program processing

[0502] In this system, users upload business-related data through a dedicated web portal or application. After logging in and authenticating, users input specific business tasks and provide data via CSV, Excel files, or API.

[0503] The server is equipped with high-performance data storage, where incoming data is initially stored. It is then moved to the database for further preprocessing. This preprocessing includes imputing missing data values, detecting and correcting outliers, and standardizing data formats. These operations utilize libraries such as Python's Pandas and NumPy.

[0504] The preprocessed data then proceeds to the analysis phase. Here, the server generates multiple machine learning models using TensorFlow or PyTorch. Specifically, these include a sales forecasting model, a consumer behavior analysis model, and an inventory management model.

[0505] The analysis results of the generated model are displayed in a dashboard format using visualization tools such as Tableau and Power BI. This makes it easier for users to visually understand the analysis results. The server also generates business improvement suggestions and new business ideas based on these results. Users can review the suggested solutions through the dashboard.

[0506] Furthermore, this system also includes a user matching function. Using a graph database powered by Neo4j, it matches users who can offer each other business opportunities. For example, it might suggest joint campaigns or joint inventory purchases.

[0507] Specific example

[0508] Case Study: Sales Data Analysis and Optimization in the Retail Industry

[0509] 1. The user (retail company A) logs into the system and uploads monthly sales data and inventory data.

[0510] 2. The server receives the data and saves it to the database. Simultaneously, it performs data imputation and corrects outliers. For example, it uses the Pandas "fillna" method or Z-scores to handle outliers.

[0511] 3. The server analyzes the pre-processed data and generates a sales forecasting model using TensorFlow. It also generates a customer behavior analysis model using PyTorch.

[0512] 4. Based on the generated model, the server displays the next month's sales forecast and inventory status in a dashboard format. Tableau is used to generate the dashboard.

[0513] 5. The server suggests a list of best-selling products and provides an optimal inventory replenishment plan. It also suggests the use of logistics services. Specifically, it inputs prompts such as the following into the AI ​​model: "What are the sales forecasts for the next month? Also, please suggest an inventory replenishment plan."

[0514] 6. The server suggests matching with another retail company (Company B) within the system, providing business opportunities such as conducting joint campaigns or jointly purchasing inventory.

[0515] This invention enables corporations to efficiently preprocess data and achieve business improvements and business matching based on the analysis results.

[0516] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0517] Step 1:

[0518] The user logs in.

[0519] The user opens a dedicated web portal or application and accesses the login screen. The user enters their username and password and clicks the "Login" button. The server receives this authentication information and compares it with the authentication information stored in the database. If authentication is successful, the server starts a session and redirects the user to the dashboard. In this process, the input is the user's authentication information (username and password), and the output is the authentication success or failure status.

[0520] Step 2:

[0521] Users enter business challenges.

[0522] The user clicks the "New Issue" button on the dashboard and enters a specific business issue into the displayed form. For example, they might enter a specific theme such as "Improving the accuracy of sales forecasts" and click the "Submit" button. The server receives the entered issue information and saves it to the database. In this case, the input is text data of the business issue, and the output is the issue information saved in the database.

[0523] Step 3:

[0524] The user uploads data.

[0525] The user clicks the "Data Upload" button, opening an upload window. The user uploads data by selecting a CSV or Excel file, or by specifying an API endpoint. The server receives this data, saves it to temporary storage, and then moves it to the database. The input in this step is the business data file or API endpoint information, and the output is the business data stored in temporary storage and the database.

[0526] Step 4:

[0527] Data preprocessing

[0528] The server reads the data stored in the database and begins preprocessing. Specifically, it performs missing value imputation (using the Pandas "fillna" method), detects and corrects outliers (using Z-scores), and standardizes the data format. The preprocessed data is then saved back to the database. In this case, the input is the stored raw data, and the output is the preprocessed data.

[0529] Step 5:

[0530] Data analysis and machine learning model generation

[0531] The server analyzes the pre-processed data and generates multiple machine learning models. Specifically, it generates a sales forecasting model using TensorFlow and a customer behavior analysis model using PyTorch. Each generated model is stored in a database. The input in this step is the pre-processed data, and the output is the parameters and prediction results of each generated machine learning model.

[0532] Step 6:

[0533] Visualization of Model Results

[0534] The server displays the results of the generated machine learning model in a dashboard format using visualization tools (such as Tableau). Users can visually confirm the analysis results through this dashboard. In this case, the input is the result data of the generated machine learning model, and the output is the visualized dashboard.

[0535] Step 7:

[0536] Generating business improvement proposals

[0537] The server generates optimal business improvement suggestions and new business ideas based on the model results. These might include inventory replenishment plans and marketing strategies to increase sales. Specifically, prompts such as "What are the sales forecasts for the next month? Also, please propose an inventory replenishment plan" are input into the AI ​​model. The input in this step is the analysis results of the machine learning model, and the output is text data of business improvement suggestions.

[0538] Step 8:

[0539] User matching

[0540] The server analyzes other user data within the system and matches users who can offer each other business opportunities. It uses Neo4j to build a graph database and identify highly relevant users. For example, it might propose joint campaigns or joint inventory purchases. In this case, the input is user data within the system, and the output is a notification of the matching results and the proposed solutions.

[0541] Through these processing steps, the system enables corporations to efficiently preprocess data and achieve business improvements and business matching based on the analysis results.

[0542] (Application Example 1)

[0543] 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."

[0544] In factory production environments, vast amounts of data are generated daily, and effectively utilizing this data to improve productivity is a crucial challenge. In particular, predicting equipment maintenance, optimizing inventory, and forecasting production require sophisticated analysis; performing these tasks manually is inefficient and prone to human error. Furthermore, collaboration with other factories is essential for achieving even greater efficiency.

[0545] 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.

[0546] In this invention, the server includes means for users to upload business-related data, means for the server to receive and store the uploaded data, means for the server to preprocess the received data, including imputing missing values ​​and formatting the data, means for the server to analyze the preprocessed data and generate multiple AI models, means for the server to visualize the results of the generated AI models in a dashboard format, means for the server to generate optimal business improvement proposals and new business ideas based on the analysis results, means for the user to confirm the proposed solutions, means for the server to analyze other user data within the system and match users who can offer each other business opportunities, and means for the server to generate production forecasting models, equipment maintenance models, and inventory optimization models based on the preprocessed data, and apply the results of these models to factory production operations. This enables improved productivity and optimization of operations by efficiently analyzing and utilizing a large amount of data from the factory floor.

[0547] A "user" is an individual or organization that accesses the system and uploads business-related data.

[0548] A "server" is a computer device that stores, preprocesses, and analyzes data received from users, and then provides the results.

[0549] "Data preprocessing" refers to a series of processes that involve imputing missing values ​​in uploaded data, formatting the data, and converting it into a format suitable for analysis.

[0550] An "AI model" is an artificial intelligence model built to perform analyses and predictions useful for specific tasks, based on pre-processed data.

[0551] A "dashboard" is an interface used to visually display data analysis results.

[0552] A "business improvement proposal" is a specific suggestion to improve the user's work efficiency based on the analysis results of an AI model.

[0553] A "business idea" refers to the potential business opportunities and strategies that are newly created from the analysis results of an AI model.

[0554] "Matching" refers to the process of analyzing different user data within a system and connecting users who can offer each other business opportunities.

[0555] A "production forecasting model" is an AI model built to predict future production volumes based on pre-processed data.

[0556] A "device maintenance model" is an AI model that analyzes device operating data to predict future maintenance schedules and necessary maintenance tasks.

[0557] An "inventory optimization model" is an AI model that uses inventory data to determine the optimal inventory level and replenishment timing.

[0558] To implement this invention, the following hardware and software are used.

[0559] hardware

[0560] Server: A high-performance computing server is used to receive, store, preprocess, and analyze data.

[0561] Terminal: A device (such as a PC, tablet, or smartphone) used by the user to upload data and view analysis results.

[0562] software

[0563] Database: Use MySQL to store uploaded data.

[0564] AI model creation framework: Generates AI models using TensorFlow or PyTorch.

[0565] Dashboard tool: Use Tableau to visually display the analysis results.

[0566] Program processing

[0567] The server will execute the following processes:

[0568] 1. Receiving and storing data:

[0569] The server receives business data uploaded by users (e.g., production data, inventory data, equipment operation data, etc.) and stores it in temporary storage. Afterward, this data is moved to a database (MySQL).

[0570] 2. Data preprocessing:

[0571] The server formats the data by imputing missing values, detecting and correcting outliers, and standardizing the data format. This makes the data suitable for analysis.

[0572] 3. Generation and analysis of AI models:

[0573] The server generates multiple AI models—production forecasting models, equipment maintenance models, and inventory optimization models—based on pre-processed data. AI model creation frameworks (TensorFlow, PyTorch) are used for this purpose.

[0574] 4. Visualization of analysis results:

[0575] The server visually displays the results of the generated AI model in a dashboard format. A dashboard tool (Tableau) is used to make it easy for users to understand the results.

[0576] 5. Proposing business improvements and generating business ideas:

[0577] Based on the results of the AI ​​model, the server generates specific business improvement suggestions and new business ideas to optimize the user's work. These suggestions can then be reviewed by the user.

[0578] 6. User matching:

[0579] The server analyzes other users' data within the system and matches users who can offer each other business opportunities. This process creates new business opportunities.

[0580] Specific example

[0581] For example, if a factory manager uploads production data with the goal of "improving machine utilization," this system works as follows:

[0582] 1. The factory manager uploads production data and operational data in CSV format.

[0583] 2. The server receives the data and saves it to the MySQL database.

[0584] 3. The server performs data preprocessing, including imputing outliers and missing values.

[0585] 4. Based on the pre-processed data, the server generates an AI model (e.g., production forecasting model, equipment maintenance model).

[0586] 5. The server displays the results in a dashboard format and provides specific improvement suggestions to the factory manager.

[0587] Example of a prompt

[0588] "To improve current machine utilization, please generate optimal improvement suggestions based on the following data. This data includes production line operating hours, product types, and monthly production volume."

[0589] In this way, this system can effectively support improvements in factory productivity and optimization of operations.

[0590] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0591] Step 1:

[0592] Users upload business-related data to the system using their terminals. Specifically, they upload production data, inventory data, equipment operation data, etc., in CSV or Excel format via a dedicated application or web portal. At this time, users can specify issues such as "improving machine utilization" or "optimizing raw material procurement," which are entered into the system as prompt messages.

[0593] Step 2:

[0594] The server receives data uploaded by the user and stores it in temporary storage. Next, it moves it to the database (MySQL) and saves it. Here, the input is the uploaded business data, and the output is the formatted data stored in the database.

[0595] Step 3:

[0596] The server preprocesses the data stored in the database. Specifically, it imputes missing values, detects and corrects outliers, and standardizes the data format. This preprocessing shapes the data into a clean format suitable for analysis. The input is the unformatted data retrieved from the database, and the output is the preprocessed, normalized data.

[0597] Step 4:

[0598] The server analyzes pre-processed data and generates multiple AI models. For example, it generates production forecasting models, equipment maintenance models, and inventory optimization models. AI model creation frameworks (TensorFlow, PyTorch) are used, and models are built based on the data. The input is pre-processed data, and the output is the generated AI models.

[0599] Step 5:

[0600] The server visualizes the results of the generated AI model in a dashboard format. Using a dashboard tool (Tableau), the results are displayed in a user-friendly, visual format. Specifically, predictive graphs and heatmaps are displayed. The input is the analysis results of the generated AI model, and the output is the visualized results on the dashboard.

[0601] Step 6:

[0602] The server generates optimal business improvement suggestions and new business ideas based on the analysis results of the AI ​​model. For example, it generates specific suggestions such as equipment maintenance schedules, inventory replenishment plans, and cost reduction measures. This allows users to obtain concrete action plans to optimize their operations. The input is the analysis results of the AI ​​model, and the output is business improvement suggestions and business ideas.

[0603] Step 7:

[0604] Users review the proposed solutions through their devices. They use dashboards and dedicated applications to examine the generated business improvement suggestions and ideas in detail and take necessary actions. The input is the suggestions provided by the server, and the output is the user's review and implementation of the suggestions.

[0605] Step 8:

[0606] The server analyzes other user data within the system and matches users who can offer each other business opportunities. This enables cooperation and joint ventures between different factories and companies. Specifically, it searches for suitable users within the database and identifies common business needs and synergies. The input is other user data within the system, and the output is the matched business opportunities.

[0607] 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.

[0608] This invention combines a generative AI-powered consulting service system for corporations with an emotion engine that recognizes user emotions. In this system, users upload business-related data, which is then stored, preprocessed, and analyzed by a server to generate optimal business improvement suggestions and new business ideas. Furthermore, by utilizing the emotion engine, suggestions tailored to the user's emotions become possible, providing more effective solutions.

[0609] System Program Overview

[0610] User actions

[0611] 1. The user logs in to the web portal or dedicated application. They enter their authentication information to establish access to the system.

[0612] 2. The user inputs their current business challenges and requirements. For example, they provide the system with specific needs such as improving sales forecasting or optimizing inventory management.

[0613] 3. Users upload business-related data. Data formats include CSV files, Excel files, and API-based formats, and include monthly sales data, inventory data, customer data, etc.

[0614] Server Processing

[0615] 1. The server receives the data uploaded by the user and stores it in temporary storage. Then, it moves the data to the database.

[0616] 2. The server begins data preprocessing. Specifically, it performs data imputation, detects and corrects outliers, standardizes data formats, and normalizes the data.

[0617] 3. The server performs initial analysis using the pre-processed data. It extracts data trends and patterns and performs basic statistical processing.

[0618] 4. The server generates multiple AI models (sales forecasting model, customer behavior analysis model, inventory optimization model, etc.), trains these models, and evaluates their accuracy.

[0619] 5. The server converts the results of the trained model into a dashboard format, transforming them into visual components such as graphs, charts, and heatmaps.

[0620] Emotional Engine Processing

[0621] 1. The device sends user operation information and input data to the emotion engine.

[0622] 2. The emotion engine (server) analyzes the user's emotions. It identifies the type of emotion (e.g., joy, sadness, stress) and evaluates its intensity.

[0623] 3. The server displays the results of the emotion engine on a dashboard, allowing users to visually check their current emotional state.

[0624] Solution proposal

[0625] 1. The server adjusts the suggested solutions based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, it will suggest a simpler and easier-to-implement solution.

[0626] 2. The server organizes the proposed content into a report format and notifies the user.

[0627] 3. The user accesses the provided solution report, reviews its contents, and implements them.

[0628] Matching proposal

[0629] 1. The server analyzes other user data within the system to identify common issues and complementary relationships.

[0630] 2. The server proposes the most suitable business match to the user, providing contact information and specific collaboration proposals. Users can collaborate with each other and maximize new business opportunities.

[0631] Specific example

[0632] Case Study: Data Analysis and the Use of Emotion Engines in the Retail Industry

[0633] 1. The user (retail company A) logs into the system and uploads the necessary sales data and inventory data.

[0634] 2. The server receives and stores the data, and performs missing value imputation and outlier correction.

[0635] 3. The server uses the pre-processed data to generate a sales forecasting model and an inventory optimization model.

[0636] 4. The server trains the model and displays the results on the dashboard.

[0637] 5. The device sends user operation information to the emotion engine, which analyzes the user's emotions.

[0638] 6. The server proposes and presents solutions that are tailored to the user's emotions.

[0639] 7. The server analyzes the commonalities between retail company A and another retail company B, and proposes a match.

[0640] The system of this invention enables efficient data analysis and customized suggestions based on user sentiment, maximizing the effectiveness of business improvement while creating new business opportunities.

[0641] The following describes the processing flow.

[0642] Step 1:

[0643] The user logs into the system using a web portal or dedicated application. They enter their authentication information (e.g., username, password) to establish access to the system.

[0644] Step 2:

[0645] Users input their current business challenges and requirements. For example, they provide the system with specific needs such as "improving the accuracy of sales forecasts" or "optimizing inventory management."

[0646] Step 3:

[0647] Users upload business-related data. Upload formats include CSV files, Excel files, and API-based formats, and this data includes monthly sales data, inventory data, customer data, and more.

[0648] Step 4:

[0649] The server receives the data uploaded by the user and stores it in temporary storage. It then moves it to the database.

[0650] Step 5:

[0651] The server begins preprocessing the received data. Specifically, it performs tasks such as imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data.

[0652] Step 6:

[0653] The server performs initial analysis using pre-processed data. It extracts data trends and patterns and performs basic statistical processing.

[0654] Step 7:

[0655] The server generates multiple AI models (such as a sales forecasting model, a customer behavior analysis model, and an inventory optimization model), trains these models, and evaluates their accuracy.

[0656] Step 8:

[0657] The server converts the results of the trained model into a dashboard format, transforming them into visual components such as graphs, charts, and heatmaps.

[0658] Step 9:

[0659] Users access the generated dashboard to view the analysis results. The dashboard allows users to navigate to other pages to obtain more detailed information.

[0660] Step 10:

[0661] The device collects user operation information and input data in real time and sends it to the emotion engine. Operation information includes mouse movements, button clicks, and input speed.

[0662] Step 11:

[0663] The emotion engine within the server analyzes collected operation information and input data to identify the user's emotions. For example, it can detect whether the user is stressed or satisfied.

[0664] Step 12:

[0665] The server displays the results of the emotion engine on a dashboard, allowing users to visually check their current emotional state.

[0666] Step 13:

[0667] The server adjusts the suggested solutions based on the user's emotions, as recognized by the emotion engine. For example, if the user is feeling stressed, it will suggest a simpler and easier-to-implement solution.

[0668] Step 14:

[0669] The server organizes the proposed content into a report format and notifies the user.

[0670] Step 15:

[0671] The user accesses the provided solution report, reviews its contents, and implements them.

[0672] Step 16:

[0673] The server analyzes other user data within the system and matches users who can offer each other business opportunities based on common challenges and complementary relationships.

[0674] Step 17:

[0675] The server proposes the most suitable business match to the user, providing contact information and specific collaboration proposals, enabling users to maximize new business opportunities.

[0676] (Example 2)

[0677] 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".

[0678] Conventional systems allow users to upload business-related data and obtain analysis results, but they struggle to provide suggestions that take into account the user's emotional state. Therefore, to maximize the efficiency and effectiveness of user business improvement, customized suggestions that reflect the user's emotional state are necessary. Appropriate business matching with other users is also required, but current systems have limitations in automating this process. To address these challenges, the present invention aims to provide a system that analyzes the user's emotional state and provides business improvement suggestions and effective matching with other users based on the results.

[0679] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0680] In this invention, the server includes means for users to upload information related to their work, means for the server to receive and store the uploaded information, means for the server to preprocess the received information, including imputing missing values ​​and formatting the information, means for generating multiple machine learning models, means for visualizing the results of the machine learning models in a dashboard format, means for generating optimal business improvement proposals and new business ideas based on the analysis results, means for analyzing the user's emotional state using an emotion analysis engine and displaying the results, means for adjusting the proposal content based on the user's emotional state, and means for analyzing information on other users in the system and matching users who can offer each other business opportunities. This makes it possible to make proposals that reflect the user's emotional state, maximizing the efficiency and effectiveness of business improvement while achieving appropriate business matching with other users.

[0681] A "user" is an end-user who uses the system to input and upload information related to their work.

[0682] A "server" is a central processing unit that receives information uploaded by users and performs preprocessing, analysis, machine learning model generation, result visualization, and sentiment analysis.

[0683] "Business-related information" refers to various types of data uploaded by users, such as monthly sales data, inventory data, and customer data, which are necessary for business improvement and new business proposals.

[0684] "Preprocessing" refers to processes that prepare data for analysis, including imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing data.

[0685] A "machine learning model" is a model based on statistical and machine learning algorithms, such as sales forecasting models, customer behavior analysis models, and inventory optimization models, which are generated using pre-processed data.

[0686] A "dashboard" is a user interface for visually displaying the results of a machine learning model, and includes graphs, charts, heatmaps, and other elements.

[0687] An "emotion analysis engine" is an analysis engine that analyzes user input data and operation information to evaluate the type of emotion (joy, sadness, stress, etc.) and its intensity.

[0688] A "business improvement proposal" is a suggestion that is useful for improving the efficiency of the user's work or for planning new businesses, based on the results of data analysis and sentiment analysis.

[0689] "Business matching" is a function that analyzes other users' information within the system and automatically matches users who can offer each other business opportunities.

[0690] This invention is a system in which users upload information related to their work, and a server analyzes that information to generate suggestions for business improvement and new business ideas. This system also incorporates an emotion analysis engine, enabling customized suggestions that reflect the user's emotional state.

[0691] First, users establish access to the system by logging in to a web portal or dedicated application and entering their authentication information. Users then enter their current business challenges and requirements into forms or text fields and upload business-related data files (e.g., CSV, Excel, API, etc.). This data includes monthly sales data, inventory data, customer data, and so on.

[0692] Next, the server receives the information uploaded by the user and stores it in temporary storage. Then, it moves the data to the database. At this point, the server begins data preprocessing, including imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data. This prepares the data for analysis.

[0693] The server performs an initial analysis using pre-processed data, extracting trends and patterns and performing basic statistical processing. It then generates multiple machine learning models, such as sales forecasting models, customer behavior analysis models, and inventory optimization models, and trains these models with training data. Once model training is complete, its accuracy is evaluated, and the highest-performing models are displayed on the dashboard. The dashboard includes visual components such as graphs, charts, and heatmaps.

[0694] Furthermore, the device sends user operation information and input data to the emotion analysis engine. The emotion analysis engine (server) analyzes the user's emotions and evaluates the type and intensity of emotions such as joy, sadness, and stress. The results of the emotion analysis are displayed on the dashboard, allowing the user to visually check their current emotional state.

[0695] The server adjusts its suggestions based on the results of the emotion analysis engine. For example, if the user is feeling stressed, it will suggest simpler and easier-to-implement solutions. These solutions are organized in a report format and communicated to the user. The user can access the presented solution report, review its contents, and implement them.

[0696] Furthermore, the server analyzes information from other users within the system to identify common challenges and complementary relationships. It then proposes optimal business matches to users, providing contact information and specific collaboration proposals. This enables users to collaborate and maximize new business opportunities.

[0697] Explanation of actions with specific examples

[0698] For example, when a user (retail company A) logs into the system and uploads the necessary sales and inventory data, the server receives and stores this data, performs missing value imputation and corrects outliers. Next, it generates a sales forecasting model and an inventory optimization model, and visualizes the training results on a dashboard. Subsequently, the terminal sends user interaction information to the sentiment analysis engine, which analyzes the user's emotions. Finally, the server proposes emotionally appropriate solutions and facilitates business matching with other retail companies.

[0699] Example of a prompt

[0700] "Please create a sales forecast for the next six months based on inventory data."

[0701] "Please propose a concrete action plan to improve customer satisfaction."

[0702] "Please tell me how to optimize inventory management."

[0703] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0704] Step 1: User Authentication and Login

[0705] The user logs in to a web portal or dedicated application. The server receives the entered authentication information (user ID and password) and sends it to the authentication server to perform authentication. If authentication is successful, the server redirects the user to their individual dashboard.

[0706] Input: User ID, Password

[0707] Output: Authenticated access session, user-specific dashboard

[0708] Step 2: Enter and upload business data

[0709] Users input business challenges and requirements related to their operations into the system. Next, they upload business-related data files (CSV files, Excel files, APIs, etc.). This data includes monthly sales data, inventory data, customer data, and so on.

[0710] Input: Business issues, data files

[0711] Output: Business issues and data files to send to the server

[0712] Step 3: Data preprocessing and storage

[0713] The server receives data uploaded by users and stores it in temporary storage. Then, the data is moved to the database. Data preprocessing includes imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data.

[0714] Input: Uploaded data file

[0715] Output: Preprocessed data, saved to database

[0716] Step 4: Data Analysis and AI Model Generation

[0717] The server performs initial analysis using pre-processed data. This step involves extracting data trends and patterns and performing basic statistical processing. Next, it generates multiple machine learning models, such as a sales forecasting model, a customer behavior analysis model, and an inventory optimization model. These models are trained on the training data, and their accuracy is evaluated. The results of the completed models are displayed on the dashboard.

[0718] Input: Preprocessed data

[0719] Output: Machine learning model, analysis results displayed on the dashboard

[0720] Step 5: Analyzing the Emotion Engine

[0721] The device sends user operation information and input data to the sentiment analysis engine. The sentiment analysis engine (server) analyzes the user's emotions and evaluates their type and intensity (e.g., joy, sadness, stress). The sentiment analysis results are displayed on the dashboard.

[0722] Input: Operation information, input data

[0723] Output: Sentiment analysis results, displayed on the dashboard.

[0724] Step 6: Proposing the optimal solution

[0725] The server customizes suggestions based on the sentiment analysis results. For example, if the user is feeling stressed, simple and easy-to-implement solutions will be suggested. These suggestions are organized in a report format and notified to the user.

[0726] Input: Sentiment analysis results

[0727] Output: Proposal report, user notification

[0728] Step 7: Propose User Matching

[0729] The server analyzes information from other users within the system to identify common challenges and complementary relationships. It then proposes optimal business matches to users, providing contact information and specific collaboration proposals. This enables users to collaborate and maximize new business opportunities.

[0730] Input: Information from other users, common challenges

[0731] Output: Business matching proposals, contact information, collaboration proposals

[0732] (Application Example 2)

[0733] 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."

[0734] Traditional factory production management systems commonly utilize data analysis and AI models to optimize production efficiency and quality, but they have not adequately provided solutions that take into account the emotional state of employees. Therefore, it has been difficult to flexibly reallocate tasks and adjust production schedules according to employee motivation and stress levels, creating a need for improved production efficiency and a better working environment for employees.

[0735] 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.

[0736] In this invention, the server includes means for users to upload business-related data, means for the server to receive and store the uploaded data, means for the server to preprocess the received data, including imputing missing values ​​and formatting the data, means for the server to analyze the preprocessed data and generate multiple AI models, means for the server to visualize the results of the generated AI models in a dashboard format, means for the server to generate optimal business improvement suggestions and new business ideas based on the analysis results, means for the user to confirm the proposed solutions, means for the server to analyze other user data within the system and match users who can offer each other business opportunities, means including an emotion engine that analyzes the emotional state of factory employees in real time, and means for proposing optimal production schedules and tasks based on the emotional state. This makes it possible to propose appropriate production schedules that take into account the emotional state of employees and to reallocate tasks to reduce stress.

[0737] "User" refers to an individual or legal entity that uses the system.

[0738] "Business-related data" refers to all data related to the operation of a factory or other business, such as production data, operational data, and quality data.

[0739] "Uploading" refers to the act of a user sending data from their device to a server.

[0740] A "server" refers to a computing system that receives, stores, preprocesses, analyzes, generates AI models, and proposes solutions for data.

[0741] "Preprocessing" refers to the initial processing performed on received data, specifically, imputing missing values, correcting outliers, and formatting the data.

[0742] "Missing value imputation" refers to the process of filling in missing values ​​in a dataset using appropriate methods.

[0743] "Formatting" refers to the process of converting data into a format suitable for analysis and model generation.

[0744] "Analysis" refers to the process of analyzing pre-processed data using statistical methods or machine learning techniques.

[0745] An "AI model" refers to a predictive or analytical model generated using artificial intelligence.

[0746] A "dashboard" refers to an interface used to visually display data and analysis results.

[0747] A "solution" refers to specific suggestions or ideas for improving a user's work.

[0748] "Matching" refers to analyzing data from multiple users within a system and proposing mutually beneficial business relationships.

[0749] The term "emotion engine" refers to technology used to analyze employees' emotional states in real time.

[0750] "Production schedule" refers to the plan for production activities in a factory.

[0751] A "task" refers to an individual job or role within a factory.

[0752] A "business idea" refers to a new proposal or concept aimed at innovating the user's business operations.

[0753] A "business improvement proposal" refers to a specific plan for improvement aimed at increasing the efficiency and quality of business operations.

[0754] The system for realizing this invention is configured to optimize factory production management. The main components of the system and their operation are described below.

[0755] Hardware configuration

[0756] 1. Server: Receives, stores, preprocesses, analyzes, and generates multiple AI models from data.

[0757] 2. Terminal: Sends employee facial expressions and voice data to the emotion engine.

[0758] 3. Sensors: Collect production data within the factory (working hours, product quality, operating rate, etc.).

[0759] 4. Camera: Detects employees' facial expressions and provides data.

[0760] 5. Microphone: Records employee voices and provides data.

[0761] Software Configuration

[0762] 1. Pandas: Load and preprocess the data.

[0763] 2. Scikit-learn: Used to train and evaluate models.

[0764] 3. EmotionEngine: A hypothetical emotion analysis engine that analyzes the emotional state of employees.

[0765] Data processing and analysis

[0766] User actions:

[0767] Users upload work-related data via their terminals. This data includes production and quality data. Users also input current challenges and requirements in production management.

[0768] Server processing:

[0769] The server stores the uploaded data in temporary storage and then moves it to the database. Next, it performs preprocessing such as imputing missing values, correcting outliers, and formatting the data. The preprocessed data is then analyzed to generate multiple AI models, such as production efficiency models and quality prediction models, and trained. The results of the trained models are visualized in a dashboard format.

[0770] Analysis of the emotion engine:

[0771] The terminal transmits the factory worker's facial expressions and voice data to the emotion engine. The emotion engine analyzes the worker's emotional state in real time and sends the results to the server. The server displays the emotion engine's results on a dashboard, allowing users to visually confirm them.

[0772] Proposed solution:

[0773] The server suggests optimal production schedules and tasks based on employee emotions recognized by the emotion engine. For example, if an employee is experiencing high stress levels, the server will suggest assigning them less demanding tasks. These suggestions are provided in dashboard and report formats for user review.

[0774] Specific example

[0775] As a practical example, suppose a factory manager logs into the system and uploads production data. The server preprocesses the data and trains a production efficiency model. Simultaneously, terminals that detect employee facial expressions and voice data analyze them using an emotion engine and send the results to the server. The server integrates this data to assign less demanding tasks to employees experiencing high stress levels and suggests optimizing the production schedule.

[0776] Examples of prompts for a generative AI model include the following:

[0777] "Based on the current stress levels of the employees, please propose an optimal production schedule. The data format is as follows: {employee_id: 123, stress_level: 0.8, task_complexity: high}"

[0778] This enables flexible production management that takes into account the emotional state of employees.

[0779] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0780] Step 1:

[0781] The server receives the user's business data and saves it to temporary storage.

[0782] Input: User-uploaded business data (e.g., production data, quality data).

[0783] Specific operation: The server saves the data as a temporary file and then moves it to the database. The output is the production data stored in the database.

[0784] Step 2:

[0785] The server preprocesses the data it receives.

[0786] Input: Production data moved from temporary storage.

[0787] Specific operation: The server uses the Pandas library to impute missing values ​​with the mean, detect and correct outliers, and normalize the data to a consistent format. The output is pre-processed data.

[0788] Step 3:

[0789] The server analyzes the pre-processed data and generates an AI model.

[0790] Input: Preprocessed data.

[0791] Specific operation: The server uses the Scikit-learn library to generate production efficiency models and quality prediction models from the data, and then trains these models. The output is the trained AI model.

[0792] Step 4:

[0793] The server visualizes the results of the generated AI model in a dashboard format.

[0794] Input: Output result of a trained AI model.

[0795] Specific operation: The server converts the results into visual components such as graphs, charts, and heatmaps, and displays them on the dashboard. The output is the visual analysis results on the dashboard.

[0796] Step 5:

[0797] The terminal transmits the facial expressions and voice data of factory workers to the emotion engine.

[0798] Input: Facial expression data and voice data of employees collected by cameras and microphones.

[0799] Specific operation: The device sends this data to the emotion engine in real time. The output is the data sent to the emotion engine.

[0800] Step 6:

[0801] The emotion engine analyzes the emotional state of employees.

[0802] Input: Facial expression data and audio data sent from the device.

[0803] Specific operation: The emotion engine analyzes the employee's emotions and sends the results to the server. The output is the analyzed emotion data.

[0804] Step 7:

[0805] The server uses the results from the emotion engine to suggest the optimal production schedule and tasks.

[0806] Input: Sentimental data sent from the emotion engine and results from a trained AI model.

[0807] Specific operation: The server assesses employee stress levels and motivation, and proposes optimizations to production schedules and task reallocations. For example, it suggests less demanding tasks to employees with high stress levels. The output is a proposal for the optimal production schedule and tasks.

[0808] Step 8:

[0809] The server provides the suggestions in dashboard and report format.

[0810] Input: Suggestions for optimal production schedules and tasks.

[0811] Specific operation: The server converts the suggested content into a visually easy-to-understand format, displays it on the dashboard, and notifies the user in the form of a report. The output is the suggested content provided on the dashboard and in the report.

[0812] This series of processes makes it possible to optimize factory production management in a way that takes into account the emotional state of employees.

[0813] 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.

[0814] 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.

[0815] 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.

[0816] [Third Embodiment]

[0817] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0818] 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.

[0819] 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).

[0820] 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.

[0821] 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.

[0822] 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).

[0823] 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.

[0824] 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.

[0825] 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.

[0826] 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.

[0827] 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.

[0828] 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".

[0829] This invention relates to a consulting service system for corporations that utilizes generative AI. In this system, users upload business-related data, and a server stores, preprocesses, and analyzes that data to generate optimal business improvement suggestions and new business ideas. Furthermore, the system can match users with each other, providing new business opportunities.

[0830] System Program Overview

[0831] User actions

[0832] 1. The user logs in to the web portal or dedicated application. They enter their authentication information here to establish access to the system.

[0833] 2. Users input specific challenges related to their work. For example, they input specific business needs such as "improving the accuracy of sales forecasts" or "optimizing inventory management."

[0834] 3. Users upload the necessary business data. The data formats vary widely, including CSV, Excel, and API. Uploaded data includes sales data, inventory data, customer data, and more.

[0835] Server Processing

[0836] 1. The server receives the data uploaded by the user and stores it in temporary storage. It then moves it to the database.

[0837] 2. The server performs data preprocessing. Specifically, it normalizes the data by imputing missing values, detecting and correcting outliers, and standardizing data formats.

[0838] 3. The server analyzes the pre-processed data. Here, multiple AI models are generated. For example, a sales forecasting model, a customer behavior analysis model, and an inventory optimization model are generated.

[0839] 4. The server visualizes the results of the generated AI model in a dashboard format. This allows users to visually understand the analysis results.

[0840] 5. The server generates optimal business improvement suggestions and new business ideas based on the results of the AI ​​model. Users can also review the proposed solutions.

[0841] 6. The server analyzes other user data within the system and matches users who can offer each other business opportunities.

[0842] Specific example

[0843] Case Study: Sales Data Analysis and Optimization in the Retail Industry

[0844] 1. The user (retail company A) logs into the system and uploads monthly sales data and inventory data.

[0845] 2. The server receives the data and saves it to the database. Simultaneously, it performs data imputation and correction of outliers.

[0846] 3. The server analyzes the pre-processed data and generates a sales forecasting model and an inventory optimization model.

[0847] 4. Based on the model generated by the server, the sales forecast for the next month and inventory status are displayed in a dashboard format.

[0848] 5. The server suggests a list of best-selling products and provides an optimal inventory replenishment plan. It also suggests the use of logistics services.

[0849] 6. The server suggests matching with another retail company (Company B) within the system, providing business opportunities such as conducting joint campaigns or jointly purchasing inventory.

[0850] This invention enables corporations to efficiently process vast amounts of data and implement concrete and effective business improvements. Furthermore, it allows for the creation of new business opportunities through effective matching between users.

[0851] The following describes the processing flow.

[0852] Step 1:

[0853] Users log in to the system using a web portal or a dedicated application. Users enter their authentication information (e.g., username, password) to establish access to the system.

[0854] Step 2:

[0855] Users input their current business challenges and requirements. For example, they provide the system with specific needs such as improving sales forecasting or optimizing inventory management.

[0856] Step 3:

[0857] Users upload business-related data. Upload formats include CSV files, Excel files, and data submitted via API. This data includes monthly sales data, inventory data, and customer data.

[0858] Step 4:

[0859] The server receives data uploaded by the user and stores it in temporary storage. Then, it moves the data to the database.

[0860] Step 5:

[0861] The server begins preprocessing the received data. Specifically, it performs tasks such as imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data.

[0862] Step 6:

[0863] The server performs initial analysis using pre-processed data. It extracts data trends and patterns, performs basic statistical processing, and then generates multiple AI models (e.g., sales forecasting model, customer behavior analysis model, inventory optimization model) based on this data.

[0864] Step 7:

[0865] The server trains the generated AI model and evaluates its accuracy. Training includes iterative processes that use historical data to improve the model's predictive accuracy.

[0866] Step 8:

[0867] The server converts the results of the trained model into a dashboard format. The results are transformed into visual components such as graphs, charts, and heatmaps, making them easy for users to understand.

[0868] Step 9:

[0869] Users access the generated dashboard to view the analysis results. The dashboard allows users to navigate to other pages to obtain more detailed information.

[0870] Step 10:

[0871] The server generates optimal business improvement suggestions and new business ideas based on the dashboard results. These suggestions are organized into a report and notified to the user.

[0872] Step 11:

[0873] The user accesses the proposed solution report and reviews its contents. They then implement the proposed solutions into their work and carry out the improvement measures.

[0874] Step 12:

[0875] The server analyzes other user data within the system and matches users who can offer each other business opportunities based on common challenges and complementary relationships.

[0876] Step 13:

[0877] The server proposes the most suitable business match to the user, providing contact information and specific collaboration proposals. Users can then collaborate with each other and maximize new business opportunities.

[0878] This process allows the system to efficiently analyze the vast amount of business data held by users, providing concrete and practical solutions while also creating new business opportunities.

[0879] (Example 1)

[0880] 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."

[0881] Modern corporations need to efficiently process vast amounts of business data and implement concrete and effective business improvements. Furthermore, creating new business opportunities through effective business matching between different corporations is crucial. Traditional systems struggled to integrate data preprocessing, AI model generation, and user matching, hindering effective business improvement and the creation of business opportunities.

[0882] 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.

[0883] In this invention, the server includes means for users to upload business-related data, means for the server to receive and store the uploaded data, means for the server to preprocess the received data, including imputing missing values ​​and detecting and correcting outliers, means for the server to analyze the preprocessed data and generate multiple machine learning models, means for the server to display the results of the generated machine learning models in a dashboard format using visualization means, means for the server to generate optimal business improvement suggestions and new business ideas based on the analysis results, means for the user to confirm the proposed solutions, and means for the server to analyze other user data within the system and match users who can offer each other business opportunities. This enables corporations to efficiently preprocess data and realize concrete business improvements and business matching based on the analysis results.

[0884] A "user" is the entity that uses this system to upload business data and review the analysis results and suggestions.

[0885] A "server" is an information processing device that receives data uploaded by users, stores it, preprocesses and analyzes it, and provides the user with the results of the generated AI model.

[0886] "Data upload" refers to the act of a user sending work-related data to this system.

[0887] "Preprocessing" is the process of imputing missing values ​​from received data, detecting and correcting outliers, and standardizing the data format.

[0888] A "machine learning model" is an algorithm generated based on data analysis to perform predictions and analyses related to specific tasks.

[0889] "Visualization methods" refer to methods that display the results of a generated machine learning model in a dashboard format, allowing users to understand them intuitively.

[0890] A "business improvement proposal" is a specific suggestion based on analysis results, aimed at improving the efficiency and performance of the user's work.

[0891] "Business matching" is the process of analyzing user data within a system and connecting users who can offer each other business opportunities.

[0892] "Data storage" refers to equipment or devices for temporarily or permanently storing uploaded data.

[0893] A "sales forecasting model" is a machine learning model that predicts future sales based on pre-processed data.

[0894] A "consumer behavior analysis model" is a machine learning model used to analyze customer behavior patterns based on pre-processed data.

[0895] An "inventory management model" is a machine learning model that uses pre-processed data to enable efficient inventory management.

[0896] This invention relates to a consulting service system for corporations that utilizes generative AI. In this system, when a user uploads business-related data, the server receives, stores, preprocesses, and analyzes that data to generate business improvement suggestions and new business ideas. The system can also match users with each other, providing new business opportunities.

[0897] Program processing

[0898] In this system, users upload business-related data through a dedicated web portal or application. After logging in and authenticating, users input specific business tasks and provide data via CSV, Excel files, or API.

[0899] The server is equipped with high-performance data storage, where incoming data is initially stored. It is then moved to the database for further preprocessing. This preprocessing includes imputing missing data values, detecting and correcting outliers, and standardizing data formats. These operations utilize libraries such as Python's Pandas and NumPy.

[0900] The preprocessed data then proceeds to the analysis phase. Here, the server generates multiple machine learning models using TensorFlow or PyTorch. Specifically, these include a sales forecasting model, a consumer behavior analysis model, and an inventory management model.

[0901] The analysis results of the generated model are displayed in a dashboard format using visualization tools such as Tableau and Power BI. This makes it easier for users to visually understand the analysis results. The server also generates business improvement suggestions and new business ideas based on these results. Users can review the suggested solutions through the dashboard.

[0902] Furthermore, this system also includes a user matching function. Using a graph database powered by Neo4j, it matches users who can offer each other business opportunities. For example, it might suggest joint campaigns or joint inventory purchases.

[0903] Specific example

[0904] Case Study: Sales Data Analysis and Optimization in the Retail Industry

[0905] 1. The user (retail company A) logs into the system and uploads monthly sales data and inventory data.

[0906] 2. The server receives the data and saves it to the database. Simultaneously, it performs data imputation and corrects outliers. For example, it uses the Pandas "fillna" method or Z-scores to handle outliers.

[0907] 3. The server analyzes the pre-processed data and generates a sales forecasting model using TensorFlow. It also generates a customer behavior analysis model using PyTorch.

[0908] 4. Based on the generated model, the server displays the next month's sales forecast and inventory status in a dashboard format. Tableau is used to generate the dashboard.

[0909] 5. The server suggests a list of best-selling products and provides an optimal inventory replenishment plan. It also suggests the use of logistics services. Specifically, it inputs prompts such as the following into the AI ​​model: "What are the sales forecasts for the next month? Also, please suggest an inventory replenishment plan."

[0910] 6. The server suggests matching with another retail company (Company B) within the system, providing business opportunities such as conducting joint campaigns or jointly purchasing inventory.

[0911] This invention enables corporations to efficiently preprocess data and achieve business improvements and business matching based on the analysis results.

[0912] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0913] Step 1:

[0914] The user logs in.

[0915] The user opens a dedicated web portal or application and accesses the login screen. The user enters their username and password and clicks the "Login" button. The server receives this authentication information and compares it with the authentication information stored in the database. If authentication is successful, the server starts a session and redirects the user to the dashboard. In this process, the input is the user's authentication information (username and password), and the output is the authentication success or failure status.

[0916] Step 2:

[0917] Users enter business challenges.

[0918] The user clicks the "New Issue" button on the dashboard and enters a specific business issue into the displayed form. For example, they might enter a specific theme such as "Improving the accuracy of sales forecasts" and click the "Submit" button. The server receives the entered issue information and saves it to the database. In this case, the input is text data of the business issue, and the output is the issue information saved in the database.

[0919] Step 3:

[0920] The user uploads data.

[0921] The user clicks the "Data Upload" button, opening an upload window. The user uploads data by selecting a CSV or Excel file, or by specifying an API endpoint. The server receives this data, saves it to temporary storage, and then moves it to the database. The input in this step is the business data file or API endpoint information, and the output is the business data stored in temporary storage and the database.

[0922] Step 4:

[0923] Data preprocessing

[0924] The server reads the data stored in the database and begins preprocessing. Specifically, it performs missing value imputation (using the Pandas "fillna" method), detects and corrects outliers (using Z-scores), and standardizes the data format. The preprocessed data is then saved back to the database. In this case, the input is the stored raw data, and the output is the preprocessed data.

[0925] Step 5:

[0926] Data analysis and machine learning model generation

[0927] The server analyzes the pre-processed data and generates multiple machine learning models. Specifically, it generates a sales forecasting model using TensorFlow and a customer behavior analysis model using PyTorch. Each generated model is stored in a database. The input in this step is the pre-processed data, and the output is the parameters and prediction results of each generated machine learning model.

[0928] Step 6:

[0929] Visualization of Model Results

[0930] The server displays the results of the generated machine learning model in a dashboard format using visualization tools (such as Tableau). Users can visually confirm the analysis results through this dashboard. In this case, the input is the result data of the generated machine learning model, and the output is the visualized dashboard.

[0931] Step 7:

[0932] Generating business improvement proposals

[0933] The server generates optimal business improvement suggestions and new business ideas based on the model results. These might include inventory replenishment plans and marketing strategies to increase sales. Specifically, prompts such as "What are the sales forecasts for the next month? Also, please propose an inventory replenishment plan" are input into the AI ​​model. The input in this step is the analysis results of the machine learning model, and the output is text data of business improvement suggestions.

[0934] Step 8:

[0935] User matching

[0936] The server analyzes other user data within the system and matches users who can offer each other business opportunities. It uses Neo4j to build a graph database and identify highly relevant users. For example, it might propose joint campaigns or joint inventory purchases. In this case, the input is user data within the system, and the output is a notification of the matching results and the proposed solutions.

[0937] Through these processing steps, the system enables corporations to efficiently preprocess data and achieve business improvements and business matching based on the analysis results.

[0938] (Application Example 1)

[0939] 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."

[0940] In factory production environments, vast amounts of data are generated daily, and effectively utilizing this data to improve productivity is a crucial challenge. In particular, predicting equipment maintenance, optimizing inventory, and forecasting production require sophisticated analysis; performing these tasks manually is inefficient and prone to human error. Furthermore, collaboration with other factories is essential for achieving even greater efficiency.

[0941] 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.

[0942] In this invention, the server includes means for users to upload business-related data, means for the server to receive and store the uploaded data, means for the server to preprocess the received data, including imputing missing values ​​and formatting the data, means for the server to analyze the preprocessed data and generate multiple AI models, means for the server to visualize the results of the generated AI models in a dashboard format, means for the server to generate optimal business improvement proposals and new business ideas based on the analysis results, means for the user to confirm the proposed solutions, means for the server to analyze other user data within the system and match users who can offer each other business opportunities, and means for the server to generate production forecasting models, equipment maintenance models, and inventory optimization models based on the preprocessed data, and apply the results of these models to factory production operations. This enables improved productivity and optimization of operations by efficiently analyzing and utilizing a large amount of data from the factory floor.

[0943] A "user" is an individual or organization that accesses the system and uploads business-related data.

[0944] A "server" is a computer device that stores, preprocesses, and analyzes data received from users, and then provides the results.

[0945] "Data preprocessing" refers to a series of processes that involve imputing missing values ​​in uploaded data, formatting the data, and converting it into a format suitable for analysis.

[0946] An "AI model" is an artificial intelligence model built to perform analyses and predictions useful for specific tasks, based on pre-processed data.

[0947] A "dashboard" is an interface used to visually display data analysis results.

[0948] A "business improvement proposal" is a specific suggestion to improve the user's work efficiency based on the analysis results of an AI model.

[0949] A "business idea" refers to the potential business opportunities and strategies that are newly created from the analysis results of an AI model.

[0950] "Matching" refers to the process of analyzing different user data within a system and connecting users who can offer each other business opportunities.

[0951] A "production forecasting model" is an AI model built to predict future production volumes based on pre-processed data.

[0952] A "device maintenance model" is an AI model that analyzes device operating data to predict future maintenance schedules and necessary maintenance tasks.

[0953] An "inventory optimization model" is an AI model that uses inventory data to determine the optimal inventory level and replenishment timing.

[0954] To implement this invention, the following hardware and software are used.

[0955] hardware

[0956] Server: A high-performance computing server is used to receive, store, preprocess, and analyze data.

[0957] Terminal: A device (such as a PC, tablet, or smartphone) used by the user to upload data and view analysis results.

[0958] software

[0959] Database: Use MySQL to store uploaded data.

[0960] AI model creation framework: Generates AI models using TensorFlow or PyTorch.

[0961] Dashboard tool: Use Tableau to visually display the analysis results.

[0962] Program processing

[0963] The server will execute the following processes:

[0964] 1. Receiving and storing data:

[0965] The server receives business data uploaded by users (e.g., production data, inventory data, equipment operation data, etc.) and stores it in temporary storage. Afterward, this data is moved to a database (MySQL).

[0966] 2. Data preprocessing:

[0967] The server formats the data by imputing missing values, detecting and correcting outliers, and standardizing the data format. This makes the data suitable for analysis.

[0968] 3. Generation and analysis of AI models:

[0969] The server generates multiple AI models—production forecasting models, equipment maintenance models, and inventory optimization models—based on pre-processed data. AI model creation frameworks (TensorFlow, PyTorch) are used for this purpose.

[0970] 4. Visualization of analysis results:

[0971] The server visually displays the results of the generated AI model in a dashboard format. A dashboard tool (Tableau) is used to make it easy for users to understand the results.

[0972] 5. Proposing business improvements and generating business ideas:

[0973] Based on the results of the AI ​​model, the server generates specific business improvement suggestions and new business ideas to optimize the user's work. These suggestions can then be reviewed by the user.

[0974] 6. User matching:

[0975] The server analyzes other users' data within the system and matches users who can offer each other business opportunities. This process creates new business opportunities.

[0976] Specific example

[0977] For example, if a factory manager uploads production data with the goal of "improving machine utilization," this system works as follows:

[0978] 1. The factory manager uploads production data and operational data in CSV format.

[0979] 2. The server receives the data and saves it to the MySQL database.

[0980] 3. The server performs data preprocessing, including imputing outliers and missing values.

[0981] 4. Based on the pre-processed data, the server generates an AI model (e.g., production forecasting model, equipment maintenance model).

[0982] 5. The server displays the results in a dashboard format and provides specific improvement suggestions to the factory manager.

[0983] Example of a prompt

[0984] "To improve current machine utilization, please generate optimal improvement suggestions based on the following data. This data includes production line operating hours, product types, and monthly production volume."

[0985] In this way, this system can effectively support improvements in factory productivity and optimization of operations.

[0986] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0987] Step 1:

[0988] Users upload business-related data to the system using their terminals. Specifically, they upload production data, inventory data, equipment operation data, etc., in CSV or Excel format via a dedicated application or web portal. At this time, users can specify issues such as "improving machine utilization" or "optimizing raw material procurement," which are entered into the system as prompt messages.

[0989] Step 2:

[0990] The server receives data uploaded by the user and stores it in temporary storage. Next, it moves it to the database (MySQL) and saves it. Here, the input is the uploaded business data, and the output is the formatted data stored in the database.

[0991] Step 3:

[0992] The server preprocesses the data stored in the database. Specifically, it imputes missing values, detects and corrects outliers, and standardizes the data format. This preprocessing shapes the data into a clean format suitable for analysis. The input is the unformatted data retrieved from the database, and the output is the preprocessed, normalized data.

[0993] Step 4:

[0994] The server analyzes pre-processed data and generates multiple AI models. For example, it generates production forecasting models, equipment maintenance models, and inventory optimization models. AI model creation frameworks (TensorFlow, PyTorch) are used, and models are built based on the data. The input is pre-processed data, and the output is the generated AI models.

[0995] Step 5:

[0996] The server visualizes the results of the generated AI model in a dashboard format. Using a dashboard tool (Tableau), the results are displayed in a user-friendly, visual format. Specifically, predictive graphs and heatmaps are displayed. The input is the analysis results of the generated AI model, and the output is the visualized results on the dashboard.

[0997] Step 6:

[0998] The server generates optimal business improvement suggestions and new business ideas based on the analysis results of the AI ​​model. For example, it generates specific suggestions such as equipment maintenance schedules, inventory replenishment plans, and cost reduction measures. This allows users to obtain concrete action plans to optimize their operations. The input is the analysis results of the AI ​​model, and the output is business improvement suggestions and business ideas.

[0999] Step 7:

[1000] Users review the proposed solutions through their devices. They use dashboards and dedicated applications to examine the generated business improvement suggestions and ideas in detail and take necessary actions. The input is the suggestions provided by the server, and the output is the user's review and implementation of the suggestions.

[1001] Step 8:

[1002] The server analyzes other user data within the system and matches users who can offer each other business opportunities. This enables cooperation and joint ventures between different factories and companies. Specifically, it searches for suitable users within the database and identifies common business needs and synergies. The input is other user data within the system, and the output is the matched business opportunities.

[1003] 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.

[1004] This invention combines a generative AI-powered consulting service system for corporations with an emotion engine that recognizes user emotions. In this system, users upload business-related data, which is then stored, preprocessed, and analyzed by a server to generate optimal business improvement suggestions and new business ideas. Furthermore, by utilizing the emotion engine, suggestions tailored to the user's emotions become possible, providing more effective solutions.

[1005] System Program Overview

[1006] User actions

[1007] 1. The user logs in to the web portal or dedicated application. They enter their authentication information to establish access to the system.

[1008] 2. The user inputs their current business challenges and requirements. For example, they provide the system with specific needs such as improving sales forecasting or optimizing inventory management.

[1009] 3. Users upload business-related data. Data formats include CSV files, Excel files, and API-based formats, and include monthly sales data, inventory data, customer data, etc.

[1010] Server Processing

[1011] 1. The server receives the data uploaded by the user and stores it in temporary storage. Then, it moves the data to the database.

[1012] 2. The server begins data preprocessing. Specifically, it performs data imputation, detects and corrects outliers, standardizes data formats, and normalizes the data.

[1013] 3. The server performs initial analysis using the pre-processed data. It extracts data trends and patterns and performs basic statistical processing.

[1014] 4. The server generates multiple AI models (sales forecasting model, customer behavior analysis model, inventory optimization model, etc.), trains these models, and evaluates their accuracy.

[1015] 5. The server converts the results of the trained model into a dashboard format, transforming them into visual components such as graphs, charts, and heatmaps.

[1016] Emotional Engine Processing

[1017] 1. The device sends user operation information and input data to the emotion engine.

[1018] 2. The emotion engine (server) analyzes the user's emotions. It identifies the type of emotion (e.g., joy, sadness, stress) and evaluates its intensity.

[1019] 3. The server displays the results of the emotion engine on a dashboard, allowing users to visually check their current emotional state.

[1020] Solution proposal

[1021] 1. The server adjusts the suggested solutions based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, it will suggest a simpler and easier-to-implement solution.

[1022] 2. The server organizes the proposed content into a report format and notifies the user.

[1023] 3. The user accesses the provided solution report, reviews its contents, and implements them.

[1024] Matching proposal

[1025] 1. The server analyzes other user data within the system to identify common issues and complementary relationships.

[1026] 2. The server proposes the most suitable business match to the user, providing contact information and specific collaboration proposals. Users can collaborate with each other and maximize new business opportunities.

[1027] Specific example

[1028] Case Study: Data Analysis and the Use of Emotion Engines in the Retail Industry

[1029] 1. The user (retail company A) logs into the system and uploads the necessary sales data and inventory data.

[1030] 2. The server receives and stores the data, and performs missing value imputation and outlier correction.

[1031] 3. The server uses the pre-processed data to generate a sales forecasting model and an inventory optimization model.

[1032] 4. The server trains the model and displays the results on the dashboard.

[1033] 5. The device sends user operation information to the emotion engine, which analyzes the user's emotions.

[1034] 6. The server proposes and presents solutions that are tailored to the user's emotions.

[1035] 7. The server analyzes the commonalities between retail company A and another retail company B, and proposes a match.

[1036] The system of this invention enables efficient data analysis and customized suggestions based on user sentiment, maximizing the effectiveness of business improvement while creating new business opportunities.

[1037] The following describes the processing flow.

[1038] Step 1:

[1039] The user logs into the system using a web portal or dedicated application. They enter their authentication information (e.g., username, password) to establish access to the system.

[1040] Step 2:

[1041] Users input their current business challenges and requirements. For example, they provide the system with specific needs such as "improving the accuracy of sales forecasts" or "optimizing inventory management."

[1042] Step 3:

[1043] Users upload business-related data. Upload formats include CSV files, Excel files, and API-based formats, and this data includes monthly sales data, inventory data, customer data, and more.

[1044] Step 4:

[1045] The server receives the data uploaded by the user and stores it in temporary storage. It then moves it to the database.

[1046] Step 5:

[1047] The server begins preprocessing the received data. Specifically, it performs tasks such as imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data.

[1048] Step 6:

[1049] The server performs initial analysis using pre-processed data. It extracts data trends and patterns and performs basic statistical processing.

[1050] Step 7:

[1051] The server generates multiple AI models (such as a sales forecasting model, a customer behavior analysis model, and an inventory optimization model), trains these models, and evaluates their accuracy.

[1052] Step 8:

[1053] The server converts the results of the trained model into a dashboard format, transforming them into visual components such as graphs, charts, and heatmaps.

[1054] Step 9:

[1055] Users access the generated dashboard to view the analysis results. The dashboard allows users to navigate to other pages to obtain more detailed information.

[1056] Step 10:

[1057] The device collects user operation information and input data in real time and sends it to the emotion engine. Operation information includes mouse movements, button clicks, and input speed.

[1058] Step 11:

[1059] The emotion engine within the server analyzes collected operation information and input data to identify the user's emotions. For example, it can detect whether the user is stressed or satisfied.

[1060] Step 12:

[1061] The server displays the results of the emotion engine on a dashboard, allowing users to visually check their current emotional state.

[1062] Step 13:

[1063] The server adjusts the suggested solutions based on the user's emotions, as recognized by the emotion engine. For example, if the user is feeling stressed, it will suggest a simpler and easier-to-implement solution.

[1064] Step 14:

[1065] The server organizes the proposed content into a report format and notifies the user.

[1066] Step 15:

[1067] The user accesses the provided solution report, reviews its contents, and implements them.

[1068] Step 16:

[1069] The server analyzes other user data within the system and matches users who can offer each other business opportunities based on common challenges and complementary relationships.

[1070] Step 17:

[1071] The server proposes the most suitable business match to the user, providing contact information and specific collaboration proposals, enabling users to maximize new business opportunities.

[1072] (Example 2)

[1073] 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."

[1074] Conventional systems allow users to upload business-related data and obtain analysis results, but they struggle to provide suggestions that take into account the user's emotional state. Therefore, to maximize the efficiency and effectiveness of user business improvement, customized suggestions that reflect the user's emotional state are necessary. Appropriate business matching with other users is also required, but current systems have limitations in automating this process. To address these challenges, the present invention aims to provide a system that analyzes the user's emotional state and provides business improvement suggestions and effective matching with other users based on the results.

[1075] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1076] In this invention, the server includes means for users to upload information related to their work, means for the server to receive and store the uploaded information, means for the server to preprocess the received information, including imputing missing values ​​and formatting the information, means for generating multiple machine learning models, means for visualizing the results of the machine learning models in a dashboard format, means for generating optimal business improvement proposals and new business ideas based on the analysis results, means for analyzing the user's emotional state using an emotion analysis engine and displaying the results, means for adjusting the proposal content based on the user's emotional state, and means for analyzing information on other users in the system and matching users who can offer each other business opportunities. This makes it possible to make proposals that reflect the user's emotional state, maximizing the efficiency and effectiveness of business improvement while achieving appropriate business matching with other users.

[1077] A "user" is an end-user who uses the system to input and upload information related to their work.

[1078] A "server" is a central processing unit that receives information uploaded by users and performs preprocessing, analysis, machine learning model generation, result visualization, and sentiment analysis.

[1079] "Business-related information" refers to various types of data uploaded by users, such as monthly sales data, inventory data, and customer data, which are necessary for business improvement and new business proposals.

[1080] "Preprocessing" refers to processes that prepare data for analysis, including imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing data.

[1081] A "machine learning model" is a model based on statistical and machine learning algorithms, such as sales forecasting models, customer behavior analysis models, and inventory optimization models, which are generated using pre-processed data.

[1082] A "dashboard" is a user interface for visually displaying the results of a machine learning model, and includes graphs, charts, heatmaps, and other elements.

[1083] An "emotion analysis engine" is an analysis engine that analyzes user input data and operation information to evaluate the type of emotion (joy, sadness, stress, etc.) and its intensity.

[1084] A "business improvement proposal" is a suggestion that is useful for improving the efficiency of the user's work or for planning new businesses, based on the results of data analysis and sentiment analysis.

[1085] "Business matching" is a function that analyzes other users' information within the system and automatically matches users who can offer each other business opportunities.

[1086] This invention is a system in which users upload information related to their work, and a server analyzes that information to generate suggestions for business improvement and new business ideas. This system also incorporates an emotion analysis engine, enabling customized suggestions that reflect the user's emotional state.

[1087] First, users establish access to the system by logging in to a web portal or dedicated application and entering their authentication information. Users then enter their current business challenges and requirements into forms or text fields and upload business-related data files (e.g., CSV, Excel, API, etc.). This data includes monthly sales data, inventory data, customer data, and so on.

[1088] Next, the server receives the information uploaded by the user and stores it in temporary storage. Then, it moves the data to the database. At this point, the server begins data preprocessing, including imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data. This prepares the data for analysis.

[1089] The server performs an initial analysis using pre-processed data, extracting trends and patterns and performing basic statistical processing. It then generates multiple machine learning models, such as sales forecasting models, customer behavior analysis models, and inventory optimization models, and trains these models with training data. Once model training is complete, its accuracy is evaluated, and the highest-performing models are displayed on the dashboard. The dashboard includes visual components such as graphs, charts, and heatmaps.

[1090] Furthermore, the device sends user operation information and input data to the emotion analysis engine. The emotion analysis engine (server) analyzes the user's emotions and evaluates the type and intensity of emotions such as joy, sadness, and stress. The results of the emotion analysis are displayed on the dashboard, allowing the user to visually check their current emotional state.

[1091] The server adjusts its suggestions based on the results of the emotion analysis engine. For example, if the user is feeling stressed, it will suggest simpler and easier-to-implement solutions. These solutions are organized in a report format and communicated to the user. The user can access the presented solution report, review its contents, and implement them.

[1092] Furthermore, the server analyzes information from other users within the system to identify common challenges and complementary relationships. It then proposes optimal business matches to users, providing contact information and specific collaboration proposals. This enables users to collaborate and maximize new business opportunities.

[1093] Explanation of actions with specific examples

[1094] For example, when a user (retail company A) logs into the system and uploads the necessary sales and inventory data, the server receives and stores this data, performs missing value imputation and corrects outliers. Next, it generates a sales forecasting model and an inventory optimization model, and visualizes the training results on a dashboard. Subsequently, the terminal sends user interaction information to the sentiment analysis engine, which analyzes the user's emotions. Finally, the server proposes emotionally appropriate solutions and facilitates business matching with other retail companies.

[1095] Example of a prompt

[1096] "Please create a sales forecast for the next six months based on inventory data."

[1097] "Please propose a concrete action plan to improve customer satisfaction."

[1098] "Please tell me how to optimize inventory management."

[1099] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1100] Step 1: User Authentication and Login

[1101] The user logs in to a web portal or dedicated application. The server receives the entered authentication information (user ID and password) and sends it to the authentication server to perform authentication. If authentication is successful, the server redirects the user to their individual dashboard.

[1102] Input: User ID, Password

[1103] Output: Authenticated access session, user-specific dashboard

[1104] Step 2: Enter and upload business data

[1105] Users input business challenges and requirements related to their operations into the system. Next, they upload business-related data files (CSV files, Excel files, APIs, etc.). This data includes monthly sales data, inventory data, customer data, and so on.

[1106] Input: Business issues, data files

[1107] Output: Business issues and data files to send to the server

[1108] Step 3: Data preprocessing and storage

[1109] The server receives data uploaded by users and stores it in temporary storage. Then, the data is moved to the database. Data preprocessing includes imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data.

[1110] Input: Uploaded data file

[1111] Output: Preprocessed data, saved to database

[1112] Step 4: Data Analysis and AI Model Generation

[1113] The server performs initial analysis using pre-processed data. This step involves extracting data trends and patterns and performing basic statistical processing. Next, it generates multiple machine learning models, such as a sales forecasting model, a customer behavior analysis model, and an inventory optimization model. These models are trained on the training data, and their accuracy is evaluated. The results of the completed models are displayed on the dashboard.

[1114] Input: Preprocessed data

[1115] Output: Machine learning model, analysis results displayed on the dashboard

[1116] Step 5: Analyzing the Emotion Engine

[1117] The device sends user operation information and input data to the sentiment analysis engine. The sentiment analysis engine (server) analyzes the user's emotions and evaluates their type and intensity (e.g., joy, sadness, stress). The sentiment analysis results are displayed on the dashboard.

[1118] Input: Operation information, input data

[1119] Output: Sentiment analysis results, displayed on the dashboard.

[1120] Step 6: Proposing the optimal solution

[1121] The server customizes suggestions based on the sentiment analysis results. For example, if the user is feeling stressed, simple and easy-to-implement solutions will be suggested. These suggestions are organized in a report format and notified to the user.

[1122] Input: Sentiment analysis results

[1123] Output: Proposal report, user notification

[1124] Step 7: Propose User Matching

[1125] The server analyzes information from other users within the system to identify common challenges and complementary relationships. It then proposes optimal business matches to users, providing contact information and specific collaboration proposals. This enables users to collaborate and maximize new business opportunities.

[1126] Input: Information from other users, common challenges

[1127] Output: Business matching proposals, contact information, collaboration proposals

[1128] (Application Example 2)

[1129] 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."

[1130] Traditional factory production management systems commonly utilize data analysis and AI models to optimize production efficiency and quality, but they have not adequately provided solutions that take into account the emotional state of employees. Therefore, it has been difficult to flexibly reallocate tasks and adjust production schedules according to employee motivation and stress levels, creating a need for improved production efficiency and a better working environment for employees.

[1131] 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.

[1132] In this invention, the server includes means for users to upload business-related data, means for the server to receive and store the uploaded data, means for the server to preprocess the received data, including imputing missing values ​​and formatting the data, means for the server to analyze the preprocessed data and generate multiple AI models, means for the server to visualize the results of the generated AI models in a dashboard format, means for the server to generate optimal business improvement suggestions and new business ideas based on the analysis results, means for the user to confirm the proposed solutions, means for the server to analyze other user data within the system and match users who can offer each other business opportunities, means including an emotion engine that analyzes the emotional state of factory employees in real time, and means for proposing optimal production schedules and tasks based on the emotional state. This makes it possible to propose appropriate production schedules that take into account the emotional state of employees and to reallocate tasks to reduce stress.

[1133] "User" refers to an individual or legal entity that uses the system.

[1134] "Business-related data" refers to all data related to the operation of a factory or other business, such as production data, operational data, and quality data.

[1135] "Uploading" refers to the act of a user sending data from their device to a server.

[1136] A "server" refers to a computing system that receives, stores, preprocesses, analyzes, generates AI models, and proposes solutions for data.

[1137] "Preprocessing" refers to the initial processing performed on received data, specifically, imputing missing values, correcting outliers, and formatting the data.

[1138] "Missing value imputation" refers to the process of filling in missing values ​​in a dataset using appropriate methods.

[1139] "Formatting" refers to the process of converting data into a format suitable for analysis and model generation.

[1140] "Analysis" refers to the process of analyzing pre-processed data using statistical methods or machine learning techniques.

[1141] An "AI model" refers to a predictive or analytical model generated using artificial intelligence.

[1142] A "dashboard" refers to an interface used to visually display data and analysis results.

[1143] A "solution" refers to specific suggestions or ideas for improving a user's work.

[1144] "Matching" refers to analyzing data from multiple users within a system and proposing mutually beneficial business relationships.

[1145] The term "emotion engine" refers to technology used to analyze employees' emotional states in real time.

[1146] "Production schedule" refers to the plan for production activities in a factory.

[1147] A "task" refers to an individual job or role within a factory.

[1148] A "business idea" refers to a new proposal or concept aimed at innovating the user's business operations.

[1149] A "business improvement proposal" refers to a specific plan for improvement aimed at increasing the efficiency and quality of business operations.

[1150] The system for realizing this invention is configured to optimize factory production management. The main components of the system and their operation are described below.

[1151] Hardware configuration

[1152] 1. Server: Receives, stores, preprocesses, analyzes, and generates multiple AI models from data.

[1153] 2. Terminal: Sends employee facial expressions and voice data to the emotion engine.

[1154] 3. Sensors: Collect production data within the factory (working hours, product quality, operating rate, etc.).

[1155] 4. Camera: Detects employees' facial expressions and provides data.

[1156] 5. Microphone: Records employee voices and provides data.

[1157] Software Configuration

[1158] 1. Pandas: Load and preprocess the data.

[1159] 2. Scikit-learn: Used to train and evaluate models.

[1160] 3. EmotionEngine: A hypothetical emotion analysis engine that analyzes the emotional state of employees.

[1161] Data processing and analysis

[1162] User actions:

[1163] Users upload work-related data via their terminals. This data includes production and quality data. Users also input current challenges and requirements in production management.

[1164] Server processing:

[1165] The server stores the uploaded data in temporary storage and then moves it to the database. Next, it performs preprocessing such as imputing missing values, correcting outliers, and formatting the data. The preprocessed data is then analyzed to generate multiple AI models, such as production efficiency models and quality prediction models, and trained. The results of the trained models are visualized in a dashboard format.

[1166] Analysis of the emotion engine:

[1167] The terminal transmits the factory worker's facial expressions and voice data to the emotion engine. The emotion engine analyzes the worker's emotional state in real time and sends the results to the server. The server displays the emotion engine's results on a dashboard, allowing users to visually confirm them.

[1168] Proposed solution:

[1169] The server suggests optimal production schedules and tasks based on employee emotions recognized by the emotion engine. For example, if an employee is experiencing high stress levels, the server will suggest assigning them less demanding tasks. These suggestions are provided in dashboard and report formats for user review.

[1170] Specific example

[1171] As a practical example, suppose a factory manager logs into the system and uploads production data. The server preprocesses the data and trains a production efficiency model. Simultaneously, terminals that detect employee facial expressions and voice data analyze them using an emotion engine and send the results to the server. The server integrates this data to assign less demanding tasks to employees experiencing high stress levels and suggests optimizing the production schedule.

[1172] Examples of prompts for a generative AI model include the following:

[1173] "Based on the current stress levels of the employees, please propose an optimal production schedule. The data format is as follows: {employee_id: 123, stress_level: 0.8, task_complexity: high}"

[1174] This enables flexible production management that takes into account the emotional state of employees.

[1175] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1176] Step 1:

[1177] The server receives the user's business data and saves it to temporary storage.

[1178] Input: User-uploaded business data (e.g., production data, quality data).

[1179] Specific operation: The server saves the data as a temporary file and then moves it to the database. The output is the production data stored in the database.

[1180] Step 2:

[1181] The server preprocesses the data it receives.

[1182] Input: Production data moved from temporary storage.

[1183] Specific operation: The server uses the Pandas library to impute missing values ​​with the mean, detect and correct outliers, and normalize the data to a consistent format. The output is pre-processed data.

[1184] Step 3:

[1185] The server analyzes the pre-processed data and generates an AI model.

[1186] Input: Preprocessed data.

[1187] Specific operation: The server uses the Scikit-learn library to generate production efficiency models and quality prediction models from the data, and then trains these models. The output is the trained AI model.

[1188] Step 4:

[1189] The server visualizes the results of the generated AI model in a dashboard format.

[1190] Input: Output result of a trained AI model.

[1191] Specific operation: The server converts the results into visual components such as graphs, charts, and heatmaps, and displays them on the dashboard. The output is the visual analysis results on the dashboard.

[1192] Step 5:

[1193] The terminal transmits the facial expressions and voice data of factory workers to the emotion engine.

[1194] Input: Facial expression data and voice data of employees collected by cameras and microphones.

[1195] Specific operation: The device sends this data to the emotion engine in real time. The output is the data sent to the emotion engine.

[1196] Step 6:

[1197] The emotion engine analyzes the emotional state of employees.

[1198] Input: Facial expression data and audio data sent from the device.

[1199] Specific operation: The emotion engine analyzes the employee's emotions and sends the results to the server. The output is the analyzed emotion data.

[1200] Step 7:

[1201] The server uses the results from the emotion engine to suggest the optimal production schedule and tasks.

[1202] Input: Sentimental data sent from the emotion engine and results from a trained AI model.

[1203] Specific operation: The server assesses employee stress levels and motivation, and proposes optimizations to production schedules and task reallocations. For example, it suggests less demanding tasks to employees with high stress levels. The output is a proposal for the optimal production schedule and tasks.

[1204] Step 8:

[1205] The server provides the suggestions in dashboard and report format.

[1206] Input: Suggestions for optimal production schedules and tasks.

[1207] Specific operation: The server converts the suggested content into a visually easy-to-understand format, displays it on the dashboard, and notifies the user in the form of a report. The output is the suggested content provided on the dashboard and in the report.

[1208] This series of processes makes it possible to optimize factory production management in a way that takes into account the emotional state of employees.

[1209] 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.

[1210] 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.

[1211] 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.

[1212] [Fourth Embodiment]

[1213] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1214] 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.

[1215] 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).

[1216] 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.

[1217] 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.

[1218] 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).

[1219] 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.

[1220] 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.

[1221] 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.

[1222] 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.

[1223] 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.

[1224] 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.

[1225] 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".

[1226] This invention relates to a consulting service system for corporations that utilizes generative AI. In this system, users upload business-related data, and a server stores, preprocesses, and analyzes that data to generate optimal business improvement suggestions and new business ideas. Furthermore, the system can match users with each other, providing new business opportunities.

[1227] System Program Overview

[1228] User actions

[1229] 1. The user logs in to the web portal or dedicated application. They enter their authentication information here to establish access to the system.

[1230] 2. Users input specific challenges related to their work. For example, they input specific business needs such as "improving the accuracy of sales forecasts" or "optimizing inventory management."

[1231] 3. Users upload the necessary business data. The data formats vary widely, including CSV, Excel, and API. Uploaded data includes sales data, inventory data, customer data, and more.

[1232] Server Processing

[1233] 1. The server receives the data uploaded by the user and stores it in temporary storage. It then moves it to the database.

[1234] 2. The server performs data preprocessing. Specifically, it normalizes the data by imputing missing values, detecting and correcting outliers, and standardizing data formats.

[1235] 3. The server analyzes the pre-processed data. Here, multiple AI models are generated. For example, a sales forecasting model, a customer behavior analysis model, and an inventory optimization model are generated.

[1236] 4. The server visualizes the results of the generated AI model in a dashboard format. This allows users to visually understand the analysis results.

[1237] 5. The server generates optimal business improvement suggestions and new business ideas based on the results of the AI ​​model. Users can also review the proposed solutions.

[1238] 6. The server analyzes other user data within the system and matches users who can offer each other business opportunities.

[1239] Specific example

[1240] Case Study: Sales Data Analysis and Optimization in the Retail Industry

[1241] 1. The user (retail company A) logs into the system and uploads monthly sales data and inventory data.

[1242] 2. The server receives the data and saves it to the database. Simultaneously, it performs data imputation and correction of outliers.

[1243] 3. The server analyzes the pre-processed data and generates a sales forecasting model and an inventory optimization model.

[1244] 4. Based on the model generated by the server, the sales forecast for the next month and inventory status are displayed in a dashboard format.

[1245] 5. The server suggests a list of best-selling products and provides an optimal inventory replenishment plan. It also suggests the use of logistics services.

[1246] 6. The server suggests matching with another retail company (Company B) within the system, providing business opportunities such as conducting joint campaigns or jointly purchasing inventory.

[1247] This invention enables corporations to efficiently process vast amounts of data and implement concrete and effective business improvements. Furthermore, it allows for the creation of new business opportunities through effective matching between users.

[1248] The following describes the processing flow.

[1249] Step 1:

[1250] Users log in to the system using a web portal or a dedicated application. Users enter their authentication information (e.g., username, password) to establish access to the system.

[1251] Step 2:

[1252] Users input their current business challenges and requirements. For example, they provide the system with specific needs such as improving sales forecasting or optimizing inventory management.

[1253] Step 3:

[1254] Users upload business-related data. Upload formats include CSV files, Excel files, and data submitted via API. This data includes monthly sales data, inventory data, and customer data.

[1255] Step 4:

[1256] The server receives data uploaded by the user and stores it in temporary storage. Then, it moves the data to the database.

[1257] Step 5:

[1258] The server begins preprocessing the received data. Specifically, it performs tasks such as imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data.

[1259] Step 6:

[1260] The server performs initial analysis using pre-processed data. It extracts data trends and patterns, performs basic statistical processing, and then generates multiple AI models (e.g., sales forecasting model, customer behavior analysis model, inventory optimization model) based on this data.

[1261] Step 7:

[1262] The server trains the generated AI model and evaluates its accuracy. Training includes iterative processes that use historical data to improve the model's predictive accuracy.

[1263] Step 8:

[1264] The server converts the results of the trained model into a dashboard format. The results are transformed into visual components such as graphs, charts, and heatmaps, making them easy for users to understand.

[1265] Step 9:

[1266] Users access the generated dashboard to view the analysis results. The dashboard allows users to navigate to other pages to obtain more detailed information.

[1267] Step 10:

[1268] The server generates optimal business improvement suggestions and new business ideas based on the dashboard results. These suggestions are organized into a report and notified to the user.

[1269] Step 11:

[1270] The user accesses the proposed solution report and reviews its contents. They then implement the proposed solutions into their work and carry out the improvement measures.

[1271] Step 12:

[1272] The server analyzes other user data within the system and matches users who can offer each other business opportunities based on common challenges and complementary relationships.

[1273] Step 13:

[1274] The server proposes the most suitable business match to the user, providing contact information and specific collaboration proposals. Users can then collaborate with each other and maximize new business opportunities.

[1275] This process allows the system to efficiently analyze the vast amount of business data held by users, providing concrete and practical solutions while also creating new business opportunities.

[1276] (Example 1)

[1277] 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".

[1278] Modern corporations need to efficiently process vast amounts of business data and implement concrete and effective business improvements. Furthermore, creating new business opportunities through effective business matching between different corporations is crucial. Traditional systems struggled to integrate data preprocessing, AI model generation, and user matching, hindering effective business improvement and the creation of business opportunities.

[1279] 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.

[1280] In this invention, the server includes means for users to upload business-related data, means for the server to receive and store the uploaded data, means for the server to preprocess the received data, including imputing missing values ​​and detecting and correcting outliers, means for the server to analyze the preprocessed data and generate multiple machine learning models, means for the server to display the results of the generated machine learning models in a dashboard format using visualization means, means for the server to generate optimal business improvement suggestions and new business ideas based on the analysis results, means for the user to confirm the proposed solutions, and means for the server to analyze other user data within the system and match users who can offer each other business opportunities. This enables corporations to efficiently preprocess data and realize concrete business improvements and business matching based on the analysis results.

[1281] A "user" is the entity that uses this system to upload business data and review the analysis results and suggestions.

[1282] A "server" is an information processing device that receives data uploaded by users, stores it, preprocesses and analyzes it, and provides the user with the results of the generated AI model.

[1283] "Data upload" refers to the act of a user sending work-related data to this system.

[1284] "Preprocessing" is the process of imputing missing values ​​from received data, detecting and correcting outliers, and standardizing the data format.

[1285] A "machine learning model" is an algorithm generated based on data analysis to perform predictions and analyses related to specific tasks.

[1286] "Visualization methods" refer to methods that display the results of a generated machine learning model in a dashboard format, allowing users to understand them intuitively.

[1287] A "business improvement proposal" is a specific suggestion based on analysis results, aimed at improving the efficiency and performance of the user's work.

[1288] "Business matching" is the process of analyzing user data within a system and connecting users who can offer each other business opportunities.

[1289] "Data storage" refers to equipment or devices for temporarily or permanently storing uploaded data.

[1290] A "sales forecasting model" is a machine learning model that predicts future sales based on pre-processed data.

[1291] A "consumer behavior analysis model" is a machine learning model used to analyze customer behavior patterns based on pre-processed data.

[1292] An "inventory management model" is a machine learning model that uses pre-processed data to enable efficient inventory management.

[1293] This invention relates to a consulting service system for corporations that utilizes generative AI. In this system, when a user uploads business-related data, the server receives, stores, preprocesses, and analyzes that data to generate business improvement suggestions and new business ideas. The system can also match users with each other, providing new business opportunities.

[1294] Program processing

[1295] In this system, users upload business-related data through a dedicated web portal or application. After logging in and authenticating, users input specific business tasks and provide data via CSV, Excel files, or API.

[1296] The server is equipped with high-performance data storage, where incoming data is initially stored. It is then moved to the database for further preprocessing. This preprocessing includes imputing missing data values, detecting and correcting outliers, and standardizing data formats. These operations utilize libraries such as Python's Pandas and NumPy.

[1297] The preprocessed data then proceeds to the analysis phase. Here, the server generates multiple machine learning models using TensorFlow or PyTorch. Specifically, these include a sales forecasting model, a consumer behavior analysis model, and an inventory management model.

[1298] The analysis results of the generated model are displayed in a dashboard format using visualization tools such as Tableau and Power BI. This makes it easier for users to visually understand the analysis results. The server also generates business improvement suggestions and new business ideas based on these results. Users can review the suggested solutions through the dashboard.

[1299] Furthermore, this system also includes a user matching function. Using a graph database powered by Neo4j, it matches users who can offer each other business opportunities. For example, it might suggest joint campaigns or joint inventory purchases.

[1300] Specific example

[1301] Case Study: Sales Data Analysis and Optimization in the Retail Industry

[1302] 1. The user (retail company A) logs into the system and uploads monthly sales data and inventory data.

[1303] 2. The server receives the data and saves it to the database. Simultaneously, it performs data imputation and corrects outliers. For example, it uses the Pandas "fillna" method or Z-scores to handle outliers.

[1304] 3. The server analyzes the pre-processed data and generates a sales forecasting model using TensorFlow. It also generates a customer behavior analysis model using PyTorch.

[1305] 4. Based on the generated model, the server displays the next month's sales forecast and inventory status in a dashboard format. Tableau is used to generate the dashboard.

[1306] 5. The server suggests a list of best-selling products and provides an optimal inventory replenishment plan. It also suggests the use of logistics services. Specifically, it inputs prompts such as the following into the AI ​​model: "What are the sales forecasts for the next month? Also, please suggest an inventory replenishment plan."

[1307] 6. The server suggests matching with another retail company (Company B) within the system, providing business opportunities such as conducting joint campaigns or jointly purchasing inventory.

[1308] This invention enables corporations to efficiently preprocess data and achieve business improvements and business matching based on the analysis results.

[1309] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1310] Step 1:

[1311] The user logs in.

[1312] The user opens a dedicated web portal or application and accesses the login screen. The user enters their username and password and clicks the "Login" button. The server receives this authentication information and compares it with the authentication information stored in the database. If authentication is successful, the server starts a session and redirects the user to the dashboard. In this process, the input is the user's authentication information (username and password), and the output is the authentication success or failure status.

[1313] Step 2:

[1314] Users enter business challenges.

[1315] The user clicks the "New Issue" button on the dashboard and enters a specific business issue into the displayed form. For example, they might enter a specific theme such as "Improving the accuracy of sales forecasts" and click the "Submit" button. The server receives the entered issue information and saves it to the database. In this case, the input is text data of the business issue, and the output is the issue information saved in the database.

[1316] Step 3:

[1317] The user uploads data.

[1318] The user clicks the "Data Upload" button, opening an upload window. The user uploads data by selecting a CSV or Excel file, or by specifying an API endpoint. The server receives this data, saves it to temporary storage, and then moves it to the database. The input in this step is the business data file or API endpoint information, and the output is the business data stored in temporary storage and the database.

[1319] Step 4:

[1320] Data preprocessing

[1321] The server reads the data stored in the database and begins preprocessing. Specifically, it performs missing value imputation (using the Pandas "fillna" method), detects and corrects outliers (using Z-scores), and standardizes the data format. The preprocessed data is then saved back to the database. In this case, the input is the stored raw data, and the output is the preprocessed data.

[1322] Step 5:

[1323] Data analysis and machine learning model generation

[1324] The server analyzes the pre-processed data and generates multiple machine learning models. Specifically, it generates a sales forecasting model using TensorFlow and a customer behavior analysis model using PyTorch. Each generated model is stored in a database. The input in this step is the pre-processed data, and the output is the parameters and prediction results of each generated machine learning model.

[1325] Step 6:

[1326] Visualization of Model Results

[1327] The server displays the results of the generated machine learning model in a dashboard format using visualization tools (such as Tableau). Users can visually confirm the analysis results through this dashboard. In this case, the input is the result data of the generated machine learning model, and the output is the visualized dashboard.

[1328] Step 7:

[1329] Generating business improvement proposals

[1330] The server generates optimal business improvement suggestions and new business ideas based on the model results. These might include inventory replenishment plans and marketing strategies to increase sales. Specifically, prompts such as "What are the sales forecasts for the next month? Also, please propose an inventory replenishment plan" are input into the AI ​​model. The input in this step is the analysis results of the machine learning model, and the output is text data of business improvement suggestions.

[1331] Step 8:

[1332] User matching

[1333] The server analyzes other user data within the system and matches users who can offer each other business opportunities. It uses Neo4j to build a graph database and identify highly relevant users. For example, it might propose joint campaigns or joint inventory purchases. In this case, the input is user data within the system, and the output is a notification of the matching results and the proposed solutions.

[1334] Through these processing steps, the system enables corporations to efficiently preprocess data and achieve business improvements and business matching based on the analysis results.

[1335] (Application Example 1)

[1336] 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".

[1337] In factory production environments, vast amounts of data are generated daily, and effectively utilizing this data to improve productivity is a crucial challenge. In particular, predicting equipment maintenance, optimizing inventory, and forecasting production require sophisticated analysis; performing these tasks manually is inefficient and prone to human error. Furthermore, collaboration with other factories is essential for achieving even greater efficiency.

[1338] 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.

[1339] In this invention, the server includes means for users to upload business-related data, means for the server to receive and store the uploaded data, means for the server to preprocess the received data, including imputing missing values ​​and formatting the data, means for the server to analyze the preprocessed data and generate multiple AI models, means for the server to visualize the results of the generated AI models in a dashboard format, means for the server to generate optimal business improvement proposals and new business ideas based on the analysis results, means for the user to confirm the proposed solutions, means for the server to analyze other user data within the system and match users who can offer each other business opportunities, and means for the server to generate production forecasting models, equipment maintenance models, and inventory optimization models based on the preprocessed data, and apply the results of these models to factory production operations. This enables improved productivity and optimization of operations by efficiently analyzing and utilizing a large amount of data from the factory floor.

[1340] A "user" is an individual or organization that accesses the system and uploads business-related data.

[1341] A "server" is a computer device that stores, preprocesses, and analyzes data received from users, and then provides the results.

[1342] "Data preprocessing" refers to a series of processes that involve imputing missing values ​​in uploaded data, formatting the data, and converting it into a format suitable for analysis.

[1343] An "AI model" is an artificial intelligence model built to perform analyses and predictions useful for specific tasks, based on pre-processed data.

[1344] A "dashboard" is an interface used to visually display data analysis results.

[1345] A "business improvement proposal" is a specific suggestion to improve the user's work efficiency based on the analysis results of an AI model.

[1346] A "business idea" refers to the potential business opportunities and strategies that are newly created from the analysis results of an AI model.

[1347] "Matching" refers to the process of analyzing different user data within a system and connecting users who can offer each other business opportunities.

[1348] A "production forecasting model" is an AI model built to predict future production volumes based on pre-processed data.

[1349] A "device maintenance model" is an AI model that analyzes device operating data to predict future maintenance schedules and necessary maintenance tasks.

[1350] An "inventory optimization model" is an AI model that uses inventory data to determine the optimal inventory level and replenishment timing.

[1351] To implement this invention, the following hardware and software are used.

[1352] hardware

[1353] Server: A high-performance computing server is used to receive, store, preprocess, and analyze data.

[1354] Terminal: A device (such as a PC, tablet, or smartphone) used by the user to upload data and view analysis results.

[1355] software

[1356] Database: Use MySQL to store uploaded data.

[1357] AI model creation framework: Generates AI models using TensorFlow or PyTorch.

[1358] Dashboard tool: Use Tableau to visually display the analysis results.

[1359] Program processing

[1360] The server will execute the following processes:

[1361] 1. Receiving and storing data:

[1362] The server receives business data uploaded by users (e.g., production data, inventory data, equipment operation data, etc.) and stores it in temporary storage. Afterward, this data is moved to a database (MySQL).

[1363] 2. Data preprocessing:

[1364] The server formats the data by imputing missing values, detecting and correcting outliers, and standardizing the data format. This makes the data suitable for analysis.

[1365] 3. Generation and analysis of AI models:

[1366] The server generates multiple AI models—production forecasting models, equipment maintenance models, and inventory optimization models—based on pre-processed data. AI model creation frameworks (TensorFlow, PyTorch) are used for this purpose.

[1367] 4. Visualization of analysis results:

[1368] The server visually displays the results of the generated AI model in a dashboard format. A dashboard tool (Tableau) is used to make it easy for users to understand the results.

[1369] 5. Proposing business improvements and generating business ideas:

[1370] Based on the results of the AI ​​model, the server generates specific business improvement suggestions and new business ideas to optimize the user's work. These suggestions can then be reviewed by the user.

[1371] 6. User matching:

[1372] The server analyzes other users' data within the system and matches users who can offer each other business opportunities. This process creates new business opportunities.

[1373] Specific example

[1374] For example, if a factory manager uploads production data with the goal of "improving machine utilization," this system works as follows:

[1375] 1. The factory manager uploads production data and operational data in CSV format.

[1376] 2. The server receives the data and saves it to the MySQL database.

[1377] 3. The server performs data preprocessing, including imputing outliers and missing values.

[1378] 4. Based on the pre-processed data, the server generates an AI model (e.g., production forecasting model, equipment maintenance model).

[1379] 5. The server displays the results in a dashboard format and provides specific improvement suggestions to the factory manager.

[1380] Example of a prompt

[1381] "To improve current machine utilization, please generate optimal improvement suggestions based on the following data. This data includes production line operating hours, product types, and monthly production volume."

[1382] In this way, this system can effectively support improvements in factory productivity and optimization of operations.

[1383] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1384] Step 1:

[1385] Users upload business-related data to the system using their terminals. Specifically, they upload production data, inventory data, equipment operation data, etc., in CSV or Excel format via a dedicated application or web portal. At this time, users can specify issues such as "improving machine utilization" or "optimizing raw material procurement," which are entered into the system as prompt messages.

[1386] Step 2:

[1387] The server receives data uploaded by the user and stores it in temporary storage. Next, it moves it to the database (MySQL) and saves it. Here, the input is the uploaded business data, and the output is the formatted data stored in the database.

[1388] Step 3:

[1389] The server preprocesses the data stored in the database. Specifically, it imputes missing values, detects and corrects outliers, and standardizes the data format. This preprocessing shapes the data into a clean format suitable for analysis. The input is the unformatted data retrieved from the database, and the output is the preprocessed, normalized data.

[1390] Step 4:

[1391] The server analyzes pre-processed data and generates multiple AI models. For example, it generates production forecasting models, equipment maintenance models, and inventory optimization models. AI model creation frameworks (TensorFlow, PyTorch) are used, and models are built based on the data. The input is pre-processed data, and the output is the generated AI models.

[1392] Step 5:

[1393] The server visualizes the results of the generated AI model in a dashboard format. Using a dashboard tool (Tableau), the results are displayed in a user-friendly, visual format. Specifically, predictive graphs and heatmaps are displayed. The input is the analysis results of the generated AI model, and the output is the visualized results on the dashboard.

[1394] Step 6:

[1395] The server generates optimal business improvement suggestions and new business ideas based on the analysis results of the AI ​​model. For example, it generates specific suggestions such as equipment maintenance schedules, inventory replenishment plans, and cost reduction measures. This allows users to obtain concrete action plans to optimize their operations. The input is the analysis results of the AI ​​model, and the output is business improvement suggestions and business ideas.

[1396] Step 7:

[1397] Users review the proposed solutions through their devices. They use dashboards and dedicated applications to examine the generated business improvement suggestions and ideas in detail and take necessary actions. The input is the suggestions provided by the server, and the output is the user's review and implementation of the suggestions.

[1398] Step 8:

[1399] The server analyzes other user data within the system and matches users who can offer each other business opportunities. This enables cooperation and joint ventures between different factories and companies. Specifically, it searches for suitable users within the database and identifies common business needs and synergies. The input is other user data within the system, and the output is the matched business opportunities.

[1400] 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.

[1401] This invention combines a generative AI-powered consulting service system for corporations with an emotion engine that recognizes user emotions. In this system, users upload business-related data, which is then stored, preprocessed, and analyzed by a server to generate optimal business improvement suggestions and new business ideas. Furthermore, by utilizing the emotion engine, suggestions tailored to the user's emotions become possible, providing more effective solutions.

[1402] System Program Overview

[1403] User actions

[1404] 1. The user logs in to the web portal or dedicated application. They enter their authentication information to establish access to the system.

[1405] 2. The user inputs their current business challenges and requirements. For example, they provide the system with specific needs such as improving sales forecasting or optimizing inventory management.

[1406] 3. Users upload business-related data. Data formats include CSV files, Excel files, and API-based formats, and include monthly sales data, inventory data, customer data, etc.

[1407] Server Processing

[1408] 1. The server receives the data uploaded by the user and stores it in temporary storage. Then, it moves the data to the database.

[1409] 2. The server begins data preprocessing. Specifically, it performs data imputation, detects and corrects outliers, standardizes data formats, and normalizes the data.

[1410] 3. The server performs initial analysis using the pre-processed data. It extracts data trends and patterns and performs basic statistical processing.

[1411] 4. The server generates multiple AI models (sales forecasting model, customer behavior analysis model, inventory optimization model, etc.), trains these models, and evaluates their accuracy.

[1412] 5. The server converts the results of the trained model into a dashboard format, transforming them into visual components such as graphs, charts, and heatmaps.

[1413] Emotional Engine Processing

[1414] 1. The device sends user operation information and input data to the emotion engine.

[1415] 2. The emotion engine (server) analyzes the user's emotions. It identifies the type of emotion (e.g., joy, sadness, stress) and evaluates its intensity.

[1416] 3. The server displays the results of the emotion engine on a dashboard, allowing users to visually check their current emotional state.

[1417] Solution proposal

[1418] 1. The server adjusts the suggested solutions based on the user's emotions recognized by the emotion engine. For example, if the user is feeling stressed, it will suggest a simpler and easier-to-implement solution.

[1419] 2. The server organizes the proposed content into a report format and notifies the user.

[1420] 3. The user accesses the provided solution report, reviews its contents, and implements them.

[1421] Matching proposal

[1422] 1. The server analyzes other user data within the system to identify common issues and complementary relationships.

[1423] 2. The server proposes the most suitable business match to the user, providing contact information and specific collaboration proposals. Users can collaborate with each other and maximize new business opportunities.

[1424] Specific example

[1425] Case Study: Data Analysis and the Use of Emotion Engines in the Retail Industry

[1426] 1. The user (retail company A) logs into the system and uploads the necessary sales data and inventory data.

[1427] 2. The server receives and stores the data, and performs missing value imputation and outlier correction.

[1428] 3. The server uses the pre-processed data to generate a sales forecasting model and an inventory optimization model.

[1429] 4. The server trains the model and displays the results on the dashboard.

[1430] 5. The device sends user operation information to the emotion engine, which analyzes the user's emotions.

[1431] 6. The server proposes and presents solutions that are tailored to the user's emotions.

[1432] 7. The server analyzes the commonalities between retail company A and another retail company B, and proposes a match.

[1433] The system of this invention enables efficient data analysis and customized suggestions based on user sentiment, maximizing the effectiveness of business improvement while creating new business opportunities.

[1434] The following describes the processing flow.

[1435] Step 1:

[1436] The user logs into the system using a web portal or dedicated application. They enter their authentication information (e.g., username, password) to establish access to the system.

[1437] Step 2:

[1438] Users input their current business challenges and requirements. For example, they provide the system with specific needs such as "improving the accuracy of sales forecasts" or "optimizing inventory management."

[1439] Step 3:

[1440] Users upload business-related data. Upload formats include CSV files, Excel files, and API-based formats, and this data includes monthly sales data, inventory data, customer data, and more.

[1441] Step 4:

[1442] The server receives the data uploaded by the user and stores it in temporary storage. It then moves it to the database.

[1443] Step 5:

[1444] The server begins preprocessing the received data. Specifically, it performs tasks such as imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data.

[1445] Step 6:

[1446] The server performs initial analysis using pre-processed data. It extracts data trends and patterns and performs basic statistical processing.

[1447] Step 7:

[1448] The server generates multiple AI models (such as a sales forecasting model, a customer behavior analysis model, and an inventory optimization model), trains these models, and evaluates their accuracy.

[1449] Step 8:

[1450] The server converts the results of the trained model into a dashboard format, transforming them into visual components such as graphs, charts, and heatmaps.

[1451] Step 9:

[1452] Users access the generated dashboard to view the analysis results. The dashboard allows users to navigate to other pages to obtain more detailed information.

[1453] Step 10:

[1454] The device collects user operation information and input data in real time and sends it to the emotion engine. Operation information includes mouse movements, button clicks, and input speed.

[1455] Step 11:

[1456] The emotion engine within the server analyzes collected operation information and input data to identify the user's emotions. For example, it can detect whether the user is stressed or satisfied.

[1457] Step 12:

[1458] The server displays the results of the emotion engine on a dashboard, allowing users to visually check their current emotional state.

[1459] Step 13:

[1460] The server adjusts the suggested solutions based on the user's emotions, as recognized by the emotion engine. For example, if the user is feeling stressed, it will suggest a simpler and easier-to-implement solution.

[1461] Step 14:

[1462] The server organizes the proposed content into a report format and notifies the user.

[1463] Step 15:

[1464] The user accesses the provided solution report, reviews its contents, and implements them.

[1465] Step 16:

[1466] The server analyzes other user data within the system and matches users who can offer each other business opportunities based on common challenges and complementary relationships.

[1467] Step 17:

[1468] The server proposes the most suitable business match to the user, providing contact information and specific collaboration proposals, enabling users to maximize new business opportunities.

[1469] (Example 2)

[1470] 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".

[1471] Conventional systems allow users to upload business-related data and obtain analysis results, but they struggle to provide suggestions that take into account the user's emotional state. Therefore, to maximize the efficiency and effectiveness of user business improvement, customized suggestions that reflect the user's emotional state are necessary. Appropriate business matching with other users is also required, but current systems have limitations in automating this process. To address these challenges, the present invention aims to provide a system that analyzes the user's emotional state and provides business improvement suggestions and effective matching with other users based on the results.

[1472] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1473] In this invention, the server includes means for users to upload information related to their work, means for the server to receive and store the uploaded information, means for the server to preprocess the received information, including imputing missing values ​​and formatting the information, means for generating multiple machine learning models, means for visualizing the results of the machine learning models in a dashboard format, means for generating optimal business improvement proposals and new business ideas based on the analysis results, means for analyzing the user's emotional state using an emotion analysis engine and displaying the results, means for adjusting the proposal content based on the user's emotional state, and means for analyzing information on other users in the system and matching users who can offer each other business opportunities. This makes it possible to make proposals that reflect the user's emotional state, maximizing the efficiency and effectiveness of business improvement while achieving appropriate business matching with other users.

[1474] A "user" is an end-user who uses the system to input and upload information related to their work.

[1475] A "server" is a central processing unit that receives information uploaded by users and performs preprocessing, analysis, machine learning model generation, result visualization, and sentiment analysis.

[1476] "Business-related information" refers to various types of data uploaded by users, such as monthly sales data, inventory data, and customer data, which are necessary for business improvement and new business proposals.

[1477] "Preprocessing" refers to processes that prepare data for analysis, including imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing data.

[1478] A "machine learning model" is a model based on statistical and machine learning algorithms, such as sales forecasting models, customer behavior analysis models, and inventory optimization models, which are generated using pre-processed data.

[1479] A "dashboard" is a user interface for visually displaying the results of a machine learning model, and includes graphs, charts, heatmaps, and other elements.

[1480] An "emotion analysis engine" is an analysis engine that analyzes user input data and operation information to evaluate the type of emotion (joy, sadness, stress, etc.) and its intensity.

[1481] A "business improvement proposal" is a suggestion that is useful for improving the efficiency of the user's work or for planning new businesses, based on the results of data analysis and sentiment analysis.

[1482] "Business matching" is a function that analyzes other users' information within the system and automatically matches users who can offer each other business opportunities.

[1483] This invention is a system in which users upload information related to their work, and a server analyzes that information to generate suggestions for business improvement and new business ideas. This system also incorporates an emotion analysis engine, enabling customized suggestions that reflect the user's emotional state.

[1484] First, users establish access to the system by logging in to a web portal or dedicated application and entering their authentication information. Users then enter their current business challenges and requirements into forms or text fields and upload business-related data files (e.g., CSV, Excel, API, etc.). This data includes monthly sales data, inventory data, customer data, and so on.

[1485] Next, the server receives the information uploaded by the user and stores it in temporary storage. Then, it moves the data to the database. At this point, the server begins data preprocessing, including imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data. This prepares the data for analysis.

[1486] The server performs an initial analysis using pre-processed data, extracting trends and patterns and performing basic statistical processing. It then generates multiple machine learning models, such as sales forecasting models, customer behavior analysis models, and inventory optimization models, and trains these models with training data. Once model training is complete, its accuracy is evaluated, and the highest-performing models are displayed on the dashboard. The dashboard includes visual components such as graphs, charts, and heatmaps.

[1487] Furthermore, the device sends user operation information and input data to the emotion analysis engine. The emotion analysis engine (server) analyzes the user's emotions and evaluates the type and intensity of emotions such as joy, sadness, and stress. The results of the emotion analysis are displayed on the dashboard, allowing the user to visually check their current emotional state.

[1488] The server adjusts its suggestions based on the results of the emotion analysis engine. For example, if the user is feeling stressed, it will suggest simpler and easier-to-implement solutions. These solutions are organized in a report format and communicated to the user. The user can access the presented solution report, review its contents, and implement them.

[1489] Furthermore, the server analyzes information from other users within the system to identify common challenges and complementary relationships. It then proposes optimal business matches to users, providing contact information and specific collaboration proposals. This enables users to collaborate and maximize new business opportunities.

[1490] Explanation of actions with specific examples

[1491] For example, when a user (retail company A) logs into the system and uploads the necessary sales and inventory data, the server receives and stores this data, performs missing value imputation and corrects outliers. Next, it generates a sales forecasting model and an inventory optimization model, and visualizes the training results on a dashboard. Subsequently, the terminal sends user interaction information to the sentiment analysis engine, which analyzes the user's emotions. Finally, the server proposes emotionally appropriate solutions and facilitates business matching with other retail companies.

[1492] Example of a prompt

[1493] "Please create a sales forecast for the next six months based on inventory data."

[1494] "Please propose a concrete action plan to improve customer satisfaction."

[1495] "Please tell me how to optimize inventory management."

[1496] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1497] Step 1: User Authentication and Login

[1498] The user logs in to a web portal or dedicated application. The server receives the entered authentication information (user ID and password) and sends it to the authentication server to perform authentication. If authentication is successful, the server redirects the user to their individual dashboard.

[1499] Input: User ID, Password

[1500] Output: Authenticated access session, user-specific dashboard

[1501] Step 2: Enter and upload business data

[1502] Users input business challenges and requirements related to their operations into the system. Next, they upload business-related data files (CSV files, Excel files, APIs, etc.). This data includes monthly sales data, inventory data, customer data, and so on.

[1503] Input: Business issues, data files

[1504] Output: Business issues and data files to send to the server

[1505] Step 3: Data preprocessing and storage

[1506] The server receives data uploaded by users and stores it in temporary storage. Then, the data is moved to the database. Data preprocessing includes imputing missing values, detecting and correcting outliers, standardizing data formats, and normalizing the data.

[1507] Input: Uploaded data file

[1508] Output: Preprocessed data, saved to database

[1509] Step 4: Data Analysis and AI Model Generation

[1510] The server performs initial analysis using pre-processed data. This step involves extracting data trends and patterns and performing basic statistical processing. Next, it generates multiple machine learning models, such as a sales forecasting model, a customer behavior analysis model, and an inventory optimization model. These models are trained on the training data, and their accuracy is evaluated. The results of the completed models are displayed on the dashboard.

[1511] Input: Preprocessed data

[1512] Output: Machine learning model, analysis results displayed on the dashboard

[1513] Step 5: Analyzing the Emotion Engine

[1514] The device sends user operation information and input data to the sentiment analysis engine. The sentiment analysis engine (server) analyzes the user's emotions and evaluates their type and intensity (e.g., joy, sadness, stress). The sentiment analysis results are displayed on the dashboard.

[1515] Input: Operation information, input data

[1516] Output: Sentiment analysis results, displayed on the dashboard.

[1517] Step 6: Proposing the optimal solution

[1518] The server customizes suggestions based on the sentiment analysis results. For example, if the user is feeling stressed, simple and easy-to-implement solutions will be suggested. These suggestions are organized in a report format and notified to the user.

[1519] Input: Sentiment analysis results

[1520] Output: Proposal report, user notification

[1521] Step 7: Propose User Matching

[1522] The server analyzes information from other users within the system to identify common challenges and complementary relationships. It then proposes optimal business matches to users, providing contact information and specific collaboration proposals. This enables users to collaborate and maximize new business opportunities.

[1523] Input: Information from other users, common challenges

[1524] Output: Business matching proposals, contact information, collaboration proposals

[1525] (Application Example 2)

[1526] 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".

[1527] Traditional factory production management systems commonly utilize data analysis and AI models to optimize production efficiency and quality, but they have not adequately provided solutions that take into account the emotional state of employees. Therefore, it has been difficult to flexibly reallocate tasks and adjust production schedules according to employee motivation and stress levels, creating a need for improved production efficiency and a better working environment for employees.

[1528] 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.

[1529] In this invention, the server includes means for users to upload business-related data, means for the server to receive and store the uploaded data, means for the server to preprocess the received data, including imputing missing values ​​and formatting the data, means for the server to analyze the preprocessed data and generate multiple AI models, means for the server to visualize the results of the generated AI models in a dashboard format, means for the server to generate optimal business improvement suggestions and new business ideas based on the analysis results, means for the user to confirm the proposed solutions, means for the server to analyze other user data within the system and match users who can offer each other business opportunities, means including an emotion engine that analyzes the emotional state of factory employees in real time, and means for proposing optimal production schedules and tasks based on the emotional state. This makes it possible to propose appropriate production schedules that take into account the emotional state of employees and to reallocate tasks to reduce stress.

[1530] "User" refers to an individual or legal entity that uses the system.

[1531] "Business-related data" refers to all data related to the operation of a factory or other business, such as production data, operational data, and quality data.

[1532] "Uploading" refers to the act of a user sending data from their device to a server.

[1533] A "server" refers to a computing system that receives, stores, preprocesses, analyzes, generates AI models, and proposes solutions for data.

[1534] "Preprocessing" refers to the initial processing performed on received data, specifically, imputing missing values, correcting outliers, and formatting the data.

[1535] "Missing value imputation" refers to the process of filling in missing values ​​in a dataset using appropriate methods.

[1536] "Formatting" refers to the process of converting data into a format suitable for analysis and model generation.

[1537] "Analysis" refers to the process of analyzing pre-processed data using statistical methods or machine learning techniques.

[1538] An "AI model" refers to a predictive or analytical model generated using artificial intelligence.

[1539] A "dashboard" refers to an interface used to visually display data and analysis results.

[1540] A "solution" refers to specific suggestions or ideas for improving a user's work.

[1541] "Matching" refers to analyzing data from multiple users within a system and proposing mutually beneficial business relationships.

[1542] The term "emotion engine" refers to technology used to analyze employees' emotional states in real time.

[1543] "Production schedule" refers to the plan for production activities in a factory.

[1544] A "task" refers to an individual job or role within a factory.

[1545] A "business idea" refers to a new proposal or concept aimed at innovating the user's business operations.

[1546] A "business improvement proposal" refers to a specific plan for improvement aimed at increasing the efficiency and quality of business operations.

[1547] The system for realizing this invention is configured to optimize factory production management. The main components of the system and their operation are described below.

[1548] Hardware configuration

[1549] 1. Server: Receives, stores, preprocesses, analyzes, and generates multiple AI models from data.

[1550] 2. Terminal: Sends employee facial expressions and voice data to the emotion engine.

[1551] 3. Sensors: Collect production data within the factory (working hours, product quality, operating rate, etc.).

[1552] 4. Camera: Detects employees' facial expressions and provides data.

[1553] 5. Microphone: Records employee voices and provides data.

[1554] Software Configuration

[1555] 1. Pandas: Load and preprocess the data.

[1556] 2. Scikit-learn: Used to train and evaluate models.

[1557] 3. EmotionEngine: A hypothetical emotion analysis engine that analyzes the emotional state of employees.

[1558] Data processing and analysis

[1559] User actions:

[1560] Users upload work-related data via their terminals. This data includes production and quality data. Users also input current challenges and requirements in production management.

[1561] Server processing:

[1562] The server stores the uploaded data in temporary storage and then moves it to the database. Next, it performs preprocessing such as imputing missing values, correcting outliers, and formatting the data. The preprocessed data is then analyzed to generate multiple AI models, such as production efficiency models and quality prediction models, and trained. The results of the trained models are visualized in a dashboard format.

[1563] Analysis of the emotion engine:

[1564] The terminal transmits the factory worker's facial expressions and voice data to the emotion engine. The emotion engine analyzes the worker's emotional state in real time and sends the results to the server. The server displays the emotion engine's results on a dashboard, allowing users to visually confirm them.

[1565] Proposed solution:

[1566] The server suggests optimal production schedules and tasks based on employee emotions recognized by the emotion engine. For example, if an employee is experiencing high stress levels, the server will suggest assigning them less demanding tasks. These suggestions are provided in dashboard and report formats for user review.

[1567] Specific example

[1568] As a practical example, suppose a factory manager logs into the system and uploads production data. The server preprocesses the data and trains a production efficiency model. Simultaneously, terminals that detect employee facial expressions and voice data analyze them using an emotion engine and send the results to the server. The server integrates this data to assign less demanding tasks to employees experiencing high stress levels and suggests optimizing the production schedule.

[1569] Examples of prompts for a generative AI model include the following:

[1570] "Based on the current stress levels of the employees, please propose an optimal production schedule. The data format is as follows: {employee_id: 123, stress_level: 0.8, task_complexity: high}"

[1571] This enables flexible production management that takes into account the emotional state of employees.

[1572] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1573] Step 1:

[1574] The server receives the user's business data and saves it to temporary storage.

[1575] Input: User-uploaded business data (e.g., production data, quality data).

[1576] Specific operation: The server saves the data as a temporary file and then moves it to the database. The output is the production data stored in the database.

[1577] Step 2:

[1578] The server preprocesses the data it receives.

[1579] Input: Production data moved from temporary storage.

[1580] Specific operation: The server uses the Pandas library to impute missing values ​​with the mean, detect and correct outliers, and normalize the data to a consistent format. The output is pre-processed data.

[1581] Step 3:

[1582] The server analyzes the pre-processed data and generates an AI model.

[1583] Input: Preprocessed data.

[1584] Specific operation: The server uses the Scikit-learn library to generate production efficiency models and quality prediction models from the data, and then trains these models. The output is the trained AI model.

[1585] Step 4:

[1586] The server visualizes the results of the generated AI model in a dashboard format.

[1587] Input: Output result of a trained AI model.

[1588] Specific operation: The server converts the results into visual components such as graphs, charts, and heatmaps, and displays them on the dashboard. The output is the visual analysis results on the dashboard.

[1589] Step 5:

[1590] The terminal transmits the facial expressions and voice data of factory workers to the emotion engine.

[1591] Input: Facial expression data and voice data of employees collected by cameras and microphones.

[1592] Specific operation: The device sends this data to the emotion engine in real time. The output is the data sent to the emotion engine.

[1593] Step 6:

[1594] The emotion engine analyzes the emotional state of employees.

[1595] Input: Facial expression data and audio data sent from the device.

[1596] Specific operation: The emotion engine analyzes the employee's emotions and sends the results to the server. The output is the analyzed emotion data.

[1597] Step 7:

[1598] The server uses the results from the emotion engine to suggest the optimal production schedule and tasks.

[1599] Input: Sentimental data sent from the emotion engine and results from a trained AI model.

[1600] Specific operation: The server assesses employee stress levels and motivation, and proposes optimizations to production schedules and task reallocations. For example, it suggests less demanding tasks to employees with high stress levels. The output is a proposal for the optimal production schedule and tasks.

[1601] Step 8:

[1602] The server provides the suggestions in dashboard and report format.

[1603] Input: Suggestions for optimal production schedules and tasks.

[1604] Specific operation: The server converts the suggested content into a visually easy-to-understand format, displays it on the dashboard, and notifies the user in the form of a report. The output is the suggested content provided on the dashboard and in the report.

[1605] This series of processes makes it possible to optimize factory production management in a way that takes into account the emotional state of employees.

[1606] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1607] 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.

[1608] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1609] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1610] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1611] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1612] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1613] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1614] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1615] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1616] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1617] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1618] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1619] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1620] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1621] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1622] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1623] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1624] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1625] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1626] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1627] The following is further disclosed regarding the embodiments described above.

[1628] (Claim 1)

[1629] A means for users to upload business-related data,

[1630] A means for the server to receive and store uploaded data,

[1631] The server has means for preprocessing the received data, including imputing missing values ​​and formatting the data.

[1632] A server analyzes pre-processed data and generates multiple AI models,

[1633] A means of visualizing the results of the AI ​​model generated by the server in a dashboard format,

[1634] The server provides a means to generate optimal business improvement suggestions and new business ideas based on the analysis results.

[1635] A means for the user to verify the proposed solution,

[1636] A server analyzes other user data within the system and matches users who can offer each other business opportunities.

[1637] A system that includes this.

[1638] (Claim 2)

[1639] The system according to claim 1, which uses a database as a storage location for uploaded data.

[1640] (Claim 3)

[1641] The system according to claim 1, which generates at least one of a sales forecasting model, a customer behavior analysis model, or an inventory optimization model based on preprocessed data.

[1642] "Example 1"

[1643] (Claim 1)

[1644] A means for users to upload business-related data,

[1645] A means for the server to receive and store uploaded data,

[1646] The server preprocesses the received data, performing means for imputing missing values ​​and detecting and correcting outliers.

[1647] A server analyzes pre-processed data and generates multiple machine learning models,

[1648] A server provides a means for displaying the results of the generated machine learning model in a dashboard format using visualization means,

[1649] A means by which the server generates optimal business improvement suggestions and new business ideas based on the analysis results,

[1650] A means for the user to verify the proposed solution,

[1651] A server analyzes other users' data within the system and uses this to match users who can offer each other business opportunities.

[1652] A system that includes this.

[1653] (Claim 2)

[1654] The system according to claim 1, which uses data storage as a storage location for uploaded data.

[1655] (Claim 3)

[1656] The system according to claim 1, which generates at least one of a sales forecasting model, a consumer behavior analysis model, or an inventory management model based on preprocessed data.

[1657] "Application Example 1"

[1658] (Claim 1)

[1659] A means for users to upload business-related data,

[1660] A means for the server to receive and store uploaded data,

[1661] The server has means for preprocessing the received data, including imputing missing values ​​and formatting the data.

[1662] A server analyzes pre-processed data and generates multiple AI models,

[1663] A means of visualizing the results of the AI ​​model generated by the server in a dashboard format,

[1664] The server provides a means to generate optimal business improvement suggestions and new business ideas based on the analysis results.

[1665] A means for the user to verify the proposed solution,

[1666] A server analyzes other user data within the system and matches users who can offer each other business opportunities.

[1667] The server generates production forecasting models, equipment maintenance models, and inventory optimization models based on pre-processed data, and provides a means to apply the results of these models to factory production operations.

[1668] A system that includes this.

[1669] (Claim 2)

[1670] The system according to claim 1, which uses a database as a storage location for uploaded data.

[1671] (Claim 3)

[1672] The system according to claim 1, which generates at least one of a production forecasting model, an equipment maintenance model, or an inventory optimization model based on pre-processed data.

[1673] "Example 2 of combining an emotion engine"

[1674] (Claim 1)

[1675] A means for users to upload information related to their work,

[1676] A means for the server to receive and store the uploaded information,

[1677] The server has means for preprocessing the received information, including imputing missing values ​​and formatting the information.

[1678] A server analyzes pre-processed information and generates multiple machine learning models,

[1679] A means of visualizing the results of the machine learning model generated by the server in a dashboard format,

[1680] A server that generates optimal business improvement suggestions and new business ideas based on analysis results,

[1681] A means for analyzing a user's emotional state using an emotion analysis engine and displaying the results,

[1682] A means by which the server adjusts the suggested content based on the user's emotional state,

[1683] A means for users to verify the proposed solution,

[1684] A server analyzes other users' information within the system and uses this to match users who can offer each other business opportunities.

[1685] A system that includes this.

[1686] (Claim 2)

[1687] The system according to claim 1, which uses a database as a storage location for uploaded information.

[1688] (Claim 3)

[1689] The system according to claim 1, which generates at least one of a sales forecasting model, a customer behavior analysis model, or an inventory optimization model based on preprocessed information.

[1690] "Application example 2 when combining with an emotional engine"

[1691] (Claim 1)

[1692] A means for users to upload business-related data,

[1693] A means for the server to receive and store uploaded data,

[1694] The server has means for preprocessing the received data, including imputing missing values ​​and formatting the data.

[1695] A server analyzes pre-processed data and generates multiple AI models,

[1696] A means of visualizing the results of the AI ​​model generated by the server in a dashboard format,

[1697] The server provides a means to generate optimal business improvement suggestions and new business ideas based on the analysis results.

[1698] A means for the user to verify the proposed solution,

[1699] A server analyzes other user data within the system and matches users who can offer each other business opportunities.

[1700] A means including an emotion engine that analyzes the emotional state of factory workers in real time,

[1701] A means of suggesting optimal production schedules and tasks based on emotional state,

[1702] A system that includes this.

[1703] (Claim 2)

[1704] The system according to claim 1, which uses a database as a storage location for uploaded data.

[1705] (Claim 3)

[1706] The system according to claim 1, which generates at least one of a sales forecasting model, a customer behavior analysis model, or an inventory optimization model based on preprocessed data. [Explanation of Symbols]

[1707] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for users to upload business-related data, A means for the server to receive and store uploaded data, The server has means for preprocessing the received data, including imputing missing values ​​and formatting the data. A server analyzes pre-processed data and generates multiple AI models, A means of visualizing the results of the AI ​​model generated by the server in a dashboard format, The server provides a means to generate optimal business improvement suggestions and new business ideas based on the analysis results. A means for the user to verify the proposed solution, A server analyzes other user data within the system and matches users who can offer each other business opportunities. A system that includes this.

2. The system according to claim 1, which uses a database as a storage location for uploaded data.

3. The system according to claim 1, which generates at least one of a sales forecasting model, a customer behavior analysis model, or an inventory optimization model based on pre-processed data.

Images