System

Abstract

A system is provided.SOLUTION: A system, comprising: means for collecting, standardizing, and integrating data from a plurality of data sources in a company; means for developing a data analysis model using the integrated data and using a machine learning algorithm; means for providing a user interface that can be intuitively operated by a user; means for extracting work problems using the data analysis model and listing the work problems; means for prioritizing the extracted work problems and presenting solutions; and means for reviewing the presented solutions with a user and executing a feasible solution.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In internal operations, a large amount of data is scattered across various departments and systems, making it difficult to effectively collect, integrate, and analyze the data. Furthermore, extracting useful business issues from vast amounts of data and quickly presenting solutions requires advanced technology and time. This results in delays in the early detection and resolution of problems, leading to reduced operational efficiency and an increased risk of large-scale problems. [Means for solving the problem]

[0005] This invention first provides a means for collecting, standardizing, and integrating data from multiple internal data sources. Next, the integrated data is used to develop a data analysis model using a machine learning algorithm to identify business issues. Furthermore, it provides a user interface that can be operated intuitively by the user, prioritizes the identified issues, and presents solutions starting with the most important ones. Finally, it provides a system that includes a means for examining the presented solutions together with the user and implementing feasible solutions, thereby improving business efficiency and preventing problems before they occur.

[0006] "Internal data" is a collection of information generated by various departments and related systems within a company or organization, and is a general term for data resources related to business activities.

[0007] "Data collection" is the process of obtaining necessary information from multiple data sources, and refers to the procedures for extracting and collecting data.

[0008] "Data integration" is the process of converting data of different formats and structures into a single standardized format and centralizing it.

[0009] "Standardization" is the process of converting collected data into a unified format, and is a means of ensuring compatibility between different data sources.

[0010] A "machine learning algorithm" is a set of techniques and methods used in data analysis, a collection of mathematical techniques for discovering patterns in data and building predictive models.

[0011] A "data analysis model" is an analytical tool created based on collected and integrated data, and is a structured framework for deriving insights and conclusions from data.

[0012] "User interface" is a general term for the screens and input devices that allow users to operate a system, and provides a means for interacting with the system intuitively and efficiently.

[0013] "Business challenges" are problems that companies and organizations face when carrying out their business, or elements that require improvement, and are challenges related to optimizing and streamlining business processes.

[0014] "Priority" is a standard for ranking issues or tasks based on their importance or urgency, and is an indicator for determining the order in which they should be addressed according to their importance.

[0015] A "solution" is a specific approach or measure set for a specific issue, a proposal aimed at solving or improving a problem.

[0016] "User feedback" refers to opinions and evaluations provided by users of a system, and refers to information that is useful for improving and optimizing the system. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention relates to a system for supporting data analysis and problem solving in in-house operations. Specific embodiments for carrying out the present invention will be described in detail below.

[0039] Internal data collection and integration

[0040] The server automatically collects data from various departments and related systems within the company. For example, it collects data in various formats, such as sales data, employee performance data, and customer feedback data. Because this data is often stored in different formats, the server consolidates and standardizes the collected data to centralize it.

[0041] Development of data analysis models using machine learning algorithms

[0042] The server uses the integrated data to develop a data analysis model using machine learning algorithms. This model is used to extract business issues and utilizes advanced algorithms such as random forests and neural networks. To develop the model, the data is divided into training data and test data, the model is trained using the training data, and its accuracy is evaluated using the test data.

[0043] Providing a user interface

[0044] The terminal provides a user interface that users can operate intuitively. For example, a web application-style interface can be used, allowing users to access and operate the system through a browser. The interface displays the results of data analysis, extracted business issues, and solutions to each issue.

[0045] Extracting and listing business issues

[0046] The server uses the developed data analysis model to extract business issues from the integrated data. For example, it identifies specific issues such as problems with product quality, issues related to declining employee performance, and customer complaints. The extracted issues are listed so that users can easily check them.

[0047] Prioritizing issues and proposing solutions

[0048] The server prioritizes the extracted business issues, determining the order based on the impact and urgency of the issues. Solutions are presented starting with the most important issues, and the server notifies the user through the user interface. Specific examples include strengthening quality control, conducting regular training, and optimizing resource allocation.

[0049] Solution review and implementation

[0050] The user examines the solutions presented by the server and selects a feasible one. To help the user put the selected solution into practice, the server also provides a detailed execution plan and information on the necessary resources. This allows the user to efficiently solve business problems.

[0051] As a specific example, if the server detects a sudden drop in sales of a particular product from sales data, it will extract the issue as a quality control problem and suggest a solution: "Review the quality control process." The user will then carefully examine the proposed solution, create an action plan, and apply it.

[0052] This invention makes it possible to make maximum use of in-house data, thereby improving business efficiency and preventing large-scale problems.

[0053] The processing flow will be explained below.

[0054] Step 1: Collect data

[0055] The server collects data from various departments within the company, such as sales data, employee performance data, customer feedback, etc. The data is available in various formats, including CSV files, Excel files, and JSON files.

[0056] The server uses APIs and database connections to collect data.

[0057] Step 2: Integrate and standardize data

[0058] The server consolidates the collected data and performs standardization processes to unify data in different formats, such as standardizing date formats and cleaning unnecessary data.

[0059] The server uses an ETL (Extract, Transform, Load) process to transform the data into an analyzable format so that all the data can be treated as a single unified dataset.

[0060] Step 3: Developing a data analysis model

[0061] The server uses the data combined in the previous step to apply machine learning algorithms, for example, random forests or neural networks to train models.

[0062] The server splits the data into training data and test data, evaluates the accuracy of the model, and adjusts the hyperparameters until a highly accurate model is obtained.

[0063] Step 4: Providing a User Interface

[0064] The terminal provides a user interface that allows users to intuitively operate the system, typically in the form of a web application.

[0065] The terminal displays a dashboard that allows users to view and operate the results of data analysis and extracted business issues.

[0066] Step 5: Identify and list business issues

[0067] The server uses a data analysis model to extract business issues from the integrated data, such as declining sales of a particular product or poor employee performance.

[0068] The server lists the extracted tasks and presents them to the user through a user interface.

[0069] Step 6: Prioritize issues and present solutions

[0070] The server prioritizes the extracted business issues based on their impact and urgency, and creates solutions starting with the most critical issues.

[0071] The server generates specific solutions for each problem and presents them to the user through a user interface, such as reviewing quality control processes or strengthening employee training.

[0072] Step 7: Refine and implement the solution

[0073] The user examines the solutions presented by the server, selects feasible solutions from the presented ones, and creates a specific implementation plan.

[0074] The server supports the allocation of detailed information and resources required to implement solutions, and helps users to efficiently solve problems based on this information.

[0075] By going through the above steps, the present invention realizes effective analysis of in-house data and rapid resolution of business issues. At each step, the server, terminal, and user work together to improve business efficiency and prevent large-scale problems.

[0076] Example 1

[0077] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0078] Many companies face challenges in collecting data from multiple internal data sources and utilizing it effectively. In particular, integrating data stored in different formats, identifying business issues, prioritizing those issues, and presenting optimal solutions are difficult. Furthermore, there is a need for a user interface that allows users to intuitively grasp the results of data analysis. The present invention aims to solve these challenges and provide a system that utilizes data efficiently and effectively.

[0079] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0080] In this invention, the server includes: means for automatically collecting and acquiring data from multiple internal data sources; means for converting the collected data into a unified format and integrating and standardizing the data; means for using the integrated data to build a data analysis model using a machine learning algorithm; means for providing a web-based interface that can be intuitively operated by a user; means for automatically extracting and listing business issues using the built data analysis model; means for prioritizing the extracted business issues and presenting solutions; and means for reviewing the presented solutions based on user feedback and providing an implementation plan for the selected solution. This makes it possible to efficiently collect and integrate internal data, effectively analyze it, extract business issues, prioritize them, present solutions, and provide them in a format that is intuitively understandable to the user.

[0081] "Data source" refers to the source of data provided by multiple departments and related systems within the company.

[0082] "Data collection" refers to the process of automatically obtaining the necessary data from internal data sources.

[0083] "Unified data format" refers to converting data stored in different formats into one standard format.

[0084] "Data integration" refers to the process of combining data collected from different data sources into one continuous data set.

[0085] "Data standardization" refers to the process of organizing integrated data into a consistent format.

[0086] "Machine learning algorithm" refers to the statistical techniques and computational methods used to build data analysis models.

[0087] "Data analysis model" refers to a model built using machine learning algorithms to extract specific business issues based on integrated and standardized data.

[0088] "Web-based interface" refers to a user interface accessible through a browser.

[0089] "Business issue extraction" refers to the process of using a data analysis model to identify issues related to internal business operations.

[0090] "Listing up" refers to compiling the extracted business issues in a list format.

[0091] "Prioritization" refers to setting the order in which extracted business issues should be addressed based on their impact and urgency.

[0092] "Providing solutions" refers to showing specific measures for the extracted business issues.

[0093] "User feedback" refers to the process of collecting opinions and ratings from users.

[0094] "Scrutiny" refers to examining the proposed solution in detail and assessing its validity.

[0095] "Providing an action plan" refers to showing the steps and resources required to specifically implement the solution selected by the user.

[0096] The present invention relates to a system for supporting data analysis and problem solving in in-house operations. Specific embodiments for carrying out the present invention will be described in detail below.

[0097] Internal data collection and integration

[0098] The server automatically collects data from various departments and related systems within the company. For example, it obtains sales data, employee performance data, and customer feedback data through a database management system (DBMS) or RESTful API. This data is often stored in different formats, so the server uses a data conversion tool (Python script) to convert this data into a unified format (CSV or JSON) and standardize it.

[0099] Development of data analysis models using machine learning algorithms

[0100] The server uses the integrated data to build a data analysis model using machine learning algorithms. This model is used to extract business issues, and random forest or neural network models are developed using Python and the TensorFlow or Scikit-learn library. The data is divided into training data and test data, and the training data is used to train the model, and the test data is used to evaluate the accuracy of the model.

[0101] Providing a user interface

[0102] The terminal provides a user interface that users can operate intuitively. Specifically, a web-based interface built with React.js is used. Users can access the system through a browser and view the results of data analysis and extracted business issues. The interface is created using Bootstrap and Material-UI.

[0103] Extracting and listing business issues

[0104] The server uses the developed data analysis model to extract business issues from the integrated data. For example, it identifies specific issues such as problems with product quality, issues related to declining employee performance, and customer complaints. These issues are saved in JSON format and notified to the user interface via a RESTful API. For example, if the server detects from sales data that sales of a particular product have dropped sharply, it will extract the issue as a problem related to the quality of that product and suggest a solution: "reviewing the quality control process."

[0105] Prioritizing issues and proposing solutions

[0106] The server prioritizes the extracted business issues, setting the order based on impact and urgency, and presenting solutions starting with the most important issues. For example, it might suggest solutions such as "reviewing the quality control process" or "conducting regular training." This information is also displayed on the user interface via a RESTful API.

[0107] Solution review and implementation

[0108] The user examines the solutions presented by the server and selects a feasible one. The selected solution is then provided along with a detailed implementation plan. For example, if "reviewing the quality control process" is selected as a solution, specific considerations, required resources, and a schedule are presented.

[0109] Specific examples

[0110] If the server detects from sales data that sales of a particular product have dropped sharply, it will identify the issue as a problem with the quality of that product and suggest a "review of the quality control process" as a solution.

[0111] Example of input prompt for generative AI model

[0112] Here are some example prompts to input to a generative AI model:

[0113] "Use departmental performance data to identify factors associated with poor employee performance."

[0114] "Analyze customer feedback data and extract key complaints."

[0115] "Use random forest to build a product sales prediction model."

[0116] This invention makes it possible to make maximum use of in-house data, thereby improving business efficiency and preventing large-scale problems.

[0117] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0118] Step 1: Collect data

[0119] The server automatically collects data from each department and related systems within the company. It uses a database management system (DBMS) and RESTful APIs to obtain sales data, employee performance data, and customer feedback data. This data is collected in a temporary storage area within the server.

[0120] Specifically, a Python script runs periodically, sends an API request, and retrieves the latest data, which is then converted to CSV format and saved.

[0121] Input: API request, database query

[0122] Output: CSV format data file

[0123] Step 2: Integrate and standardize data

[0124] The server converts the collected data into a unified format, consolidating and standardizing the data, and converting data from different formats into a unified schema for the SQL database.

[0125] Specifically, a data conversion Python script is run to convert each dataset into a unified format (e.g., all numeric data is rounded to two decimal places), and the converted data is imported into a MySQL database.

[0126] Input: CSV format data file

[0127] Output: Data in a unified format (stored in an SQL database)

[0128] Step 3: Building a machine learning model

[0129] The server uses the integrated data to build machine learning models, developing random forest and neural network models using Python, TensorFlow, and Scikit-learn.

[0130] Specifically, the server loads the data using a Python script and splits it into training and test data using SciPy. Next, it builds a neural network model using TensorFlow and trains it using the training data. The accuracy of the model is evaluated using the test data, and the models that are confirmed to have high accuracy are saved.

[0131] Input: Unified format data (SQL database)

[0132] Output: A trained machine learning model

[0133] Step 4: Providing a User Interface

[0134] The terminal provides an intuitive user interface, allowing users to view the results of data analysis and extracted business issues through a web-based interface built with React.js.

[0135] Specifically, when a user opens a web browser and accesses a specific URL, the device receives HTML, CSS, and JavaScript files from the server and displays information dynamically constructed by React.js.

[0136] Input: User's browser access

[0137] Output: Web page displaying analysis results and business issues

[0138] Step 5: Identify and list business issues

[0139] The server uses the developed data analysis model to extract business issues from the integrated data, identifying and listing issues such as product quality problems, poor employee performance, and customer dissatisfaction.

[0140] Specifically, the server periodically re-analyzes the integrated data and extracts business issues using the stored machine learning model. The extracted issues are saved in JSON format and delivered to the front end via a RESTful API.

[0141] Input: Integrated data, machine learning model

[0142] Output: Extracted business issues (saved in JSON format)

[0143] Step 6: Prioritize issues and present solutions

[0144] The server prioritizes the extracted business issues based on their impact and urgency, and presents solutions starting with the most important issues.

[0145] Specifically, the system runs a prioritization algorithm to calculate an impact score for each issue, after which the solution is displayed in the user interface.

[0146] Input: Extracted business issues (JSON format)

[0147] Output: Prioritized issues and solutions

[0148] Step 7: Refine and implement the solution

[0149] The user reviews the proposed solutions and selects a viable one, which is then provided with a detailed implementation plan.

[0150] Specifically, the user selects a solution on the user interface and sends that information to the server. Based on the selected solution, the server generates specific study items, required resources, and a schedule, and displays them on the user interface.

[0151] Input: User's solution selection

[0152] Output: Detailed execution plan

[0153] (Application example 1)

[0154] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0155] Modern factories require real-time monitoring of each robot's performance and error status, and the ability to quickly address these issues. However, achieving this requires a system that can efficiently collect and analyze large amounts of data and provide users with appropriate solutions. Conventional systems take time to integrate and analyze data, identify issues, and present solutions, resulting in delays in providing appropriate solutions. Another challenge is providing an interface that is easy for users to use.

[0156] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0157] In this invention, the server includes: means for collecting, standardizing, and integrating data from multiple data sources within a company; means for using the integrated data to develop a data analysis model using a machine learning algorithm; means for providing a user interface that can be intuitively operated by a user; means for extracting and listing business issues using the data analysis model; means for prioritizing the extracted business issues and proposing solutions; means for examining the proposed solutions together with the user and implementing feasible ones; means for collecting robot data in real time; and means for analyzing the collected data, extracting issues, prioritizing them, and displaying solutions on a smartphone screen. This makes it possible to monitor robot performance and error status in a factory in real time and quickly and effectively resolve issues.

[0158] Key Word Definitions

[0159] "Data source" is a general term for a system or device that provides data.

[0160] "Standardization" is the process of converting data of different formats into a consistent format.

[0161] "Integration" means combining data obtained from multiple different data sources into a single data set.

[0162] A "machine learning algorithm" is a program or method that learns patterns from data and automatically performs tasks such as prediction and categorization.

[0163] A "data analysis model" is a specific computational model constructed using machine learning algorithms for analyzing and predicting data.

[0164] A "user interface" is a visual and operational interface that allows a user to operate a system or application.

[0165] A "business issue" is a specific problem or obstacle that needs to be solved in the operations or work processes of a company or organization.

[0166] "Priority" means determining the order in which multiple issues or tasks should be handled based on their importance and urgency.

[0167] A "solution" is a specific action or method that should be taken to address a specific problem or issue.

[0168] "Real-time collection" is the process of collecting data immediately without delay.

[0169] A "smartphone screen" is a smartphone display and an interface for displaying applications and information.

[0170] "Robot data" refers to operational data such as performance and error information obtained from robots operating in factories.

[0171] MODE FOR CARRYING OUT THE INVENTION

[0172] The present invention provides a system for monitoring the performance of robots in a factory and the occurrence of errors in real time, and for responding quickly and effectively. Specific embodiments for carrying out the present invention will be described in detail below.

[0173] Configuration and Overview

[0174] The system consists of the following elements:

[0175] 1. Data collection and integration:

[0176] The server automatically collects data from multiple data sources within the factory. Specifically, this includes operation data, performance data, and error occurrence information for each robot. Because this data is stored in different formats, the server standardizes and centralizes the data.

[0177] 2. Development of data analysis models using machine learning algorithms:

[0178] The server uses the integrated data to develop a data analysis model using a machine learning algorithm (e.g., RandomForestClassifier). This model detects robot anomalies and identifies operational issues. It also splits the data into training and test data, trains the model, and evaluates its accuracy.

[0179] 3. Providing the user interface:

[0180] The terminal (e.g., a smartphone) provides a user interface that can be operated intuitively by the user. Specifically, a dashboard-style interface is considered, allowing the user to access the system through the smartphone screen and check the analysis results and solutions.

[0181] 4. Extract and list business issues:

[0182] The server uses the developed data analysis model to extract business issues from the integrated data. The extracted issues are listed so that users can easily check them. For example, they may include the cause of a particular robot's shutdown or frequent errors.

[0183] 5. Prioritizing issues and proposing solutions:

[0184] The server prioritizes the extracted business issues and presents solutions based on the impact and urgency of the issues. For example, this could include the timing of preventive maintenance or part replacement for a specific robot.

[0185] 6. Solution Examination and Implementation:

[0186] The user can then examine the solutions presented by the server and implement the most appropriate one. Specifically, the user can check the details of the solution and the implementation procedure through the user interface.

[0187] Hardware and Software

[0188] Hardware: Smartphone

[0189] Software: Python, requests library, scikit-learn

[0190] Specific examples

[0191] For example, if a particular robot in a factory stops working multiple times over a certain period of time, the system will identify the cause and suggest preventative maintenance. Users can view the following information on their smartphone screen:

[0192] Prompt Sentence Examples

[0193] "Factory robot 22 has stopped working three times in one week. Please provide possible issues that could be causing the downtime and solutions."

[0194] This makes it possible to monitor robot performance and error conditions within the factory in real time and resolve issues quickly and effectively.

[0195] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0196] Step 1:

[0197] The server collects operational data, performance data, and error information from each robot in the factory in real time. Because this data is stored in different formats, the server standardizes and centralizes the data.

[0198] Input: Operation data, performance data, and error information sent from each robot

[0199] Output: Standardized and unified dataset

[0200] Step 2:

[0201] The server uses the standardized data to develop a data analysis model using a machine learning algorithm (e.g., RandomForestClassifier). The model is divided into training data and test data, trained, and its accuracy is evaluated.

[0202] Input: Standardized dataset

[0203] Output: A trained data analysis model

[0204] Step 3:

[0205] The server uses a trained data analysis model to extract robot anomalies and operational issues from the integrated data, identifying and listing information according to the type and situation of the issue.

[0206] Input: Trained data analysis model, standardized dataset

[0207] Output: A list of extracted anomalies and business issues

[0208] Step 4:

[0209] The server prioritizes the extracted business issues and presents solutions to each issue using machine learning models as a reference. Priorities are determined based on the importance and urgency of the issues.

[0210] Input: List of anomalies and business issues

[0211] Output: A prioritized list of issues and solutions

[0212] Step 5:

[0213] The terminal displays the prioritized list of issues and solutions sent from the server to the user through a user interface, allowing the user to intuitively operate the terminal and check detailed information.

[0214] Input: A prioritized list of issues and solutions sent from the server

[0215] Output: Analysis results and solutions displayed on the smartphone screen

[0216] Step 6:

[0217] Users can examine the presented solutions, select the most appropriate one, and put it into action. Specific steps and information on the necessary resources are also provided, allowing for efficient problem-solving.

[0218] Input: Solution displayed on smartphone screen

[0219] Output: The selected solution and its implementation plan

[0220] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0221] The present invention combines a system that supports data analysis and problem solving in in-house operations with an emotion engine that recognizes user emotions. Specific embodiments for carrying out the present invention will be described in detail below.

[0222] Internal data collection and integration

[0223] The server automatically collects data from various departments and related systems within the company, such as sales data, employee performance data, customer feedback data, etc. Because the data exists in various formats, the server standardizes and consolidates the collected data.

[0224] Development of data analysis models using machine learning algorithms

[0225] The server uses machine learning algorithms to develop a data analysis model based on the integrated data. To develop the model, the data is divided into training data and test data, and the model is trained using the training data. The accuracy of the model is evaluated using the test data, and the model with the highest accuracy is selected.

[0226] Providing a user interface

[0227] The terminal provides a user interface that can be operated intuitively by the user. A web application-style interface is provided, and users can access the system via a browser and check analysis results and business issues.

[0228] Extracting and listing business issues

[0229] The server uses a data analysis model to extract business issues from the integrated data. For example, it detects and lists problems related to product quality or poor employee performance. The extracted issues are then provided to the user through a user interface.

[0230] Prioritizing issues and proposing solutions

[0231] The server prioritizes the extracted business issues based on their impact and urgency. Solutions are generated for the most important issues first and are notified to the user through the user interface. Specific solutions include strengthening quality control and implementing employee training.

[0232] Incorporating an emotion engine

[0233] One of the features of the present invention is that it incorporates an emotion engine to recognize the user's emotions in real time and adjust the analysis results and presented solutions according to the user's emotional state. The emotion engine analyzes emotions from the user's facial expressions, voice tone, text input, etc.

[0234] Dynamic adjustment of emotion-based interfaces

[0235] The device dynamically adjusts the user interface based on data obtained from the emotion engine. For example, if the user is stressed, it will simplify the solution suggestions and provide flexible support. If the user is relaxed, it will provide detailed information to support decision-making.

[0236] Emotion history analysis

[0237] The server analyzes the user's emotional history and presents solutions at the optimal time based on past emotional patterns, enabling appropriate feedback that takes into account the user's emotional state.

[0238] For example, if sales data detects a sudden drop in sales of a particular product, the issue is extracted as a quality control problem. If the emotion engine recognizes that the user's stress level is high, the solution is simplified and a simple suggestion such as "review the quality control process" is made. If the user is relaxed, a detailed implementation plan is presented.

[0239] Through the above steps, the present invention combines data analysis and emotion recognition to provide optimal solutions for users, improving work efficiency and reducing stress.

[0240] The processing flow will be explained below.

[0241] Step 1: Collect data

[0242] The server collects data from various departments and related systems within the company, including sales data, employee performance data, and customer feedback data.

[0243] I won't provide any code examples, but the server retrieves data using an API or database connection.

[0244] Step 2: Integrate and standardize data

[0245] The server consolidates the collected data and performs standardization processes, such as standardizing date formats and normalizing text data.

[0246] The server applies an ETL (Extract, Transform, Load) process to produce a unified dataset, which brings the data into a single, analyzable format.

[0247] Step 3: Developing a data analysis model

[0248] The server uses the combined data to develop data analysis models using machine learning algorithms, such as random forests and neural networks.

[0249] The server splits the data into training data and test data, trains the model using the training data, and evaluates the model on the test data to measure accuracy.

[0250] Step 4: Providing a User Interface

[0251] The terminal provides a user interface that can be operated intuitively by the user. The interface is in the form of a web application, and the user accesses it from a browser.

[0252] The interface on the terminal displays the results of data analysis and extracted business issues, which the user uses to interact with the system.

[0253] Step 5: Identify and list business issues

[0254] The server uses data analysis models to extract specific business issues from the integrated data, such as declining sales of a particular product, poor employee performance, or customer dissatisfaction.

[0255] The extracted issues are provided to the user as a list via a user interface, and the user checks this list to identify issues that require action.

[0256] Step 6: Prioritize the issues and present solutions

[0257] The server prioritizes the extracted business issues based on their impact and urgency. The impact of the issues is evaluated using a data analysis model.

[0258] The server generates specific solutions in order of priority and presents them to the user through a user interface. For example, it may suggest solutions such as "reviewing the quality control process" or "strengthening employee training."

[0259] Step 7: Recognizing user emotions with the emotion engine

[0260] The server analyzes the user's emotional state based on the user's emotional data acquired from the terminal (for example, facial expressions, voice tone, and analysis results of text input).

[0261] The emotion engine recognizes the user's emotions in real time, so if the user is feeling stressed, for example, this is fed back to the system.

[0262] Step 8: Dynamically adjust the interface based on emotions

[0263] The device dynamically adjusts the user interface based on data from the emotion engine, simplifying suggested solutions and providing more support when the user is feeling stressed.

[0264] For example, you can omit the details of the solution and show only the key points, or change the color scheme and layout to reduce visual strain.

[0265] Step 9: Analyze emotion history and provide solutions at the optimal time

[0266] The server analyzes the user's past emotional history and understands their emotional patterns, which allows it to present solutions at the optimal time.

[0267] Present detailed solutions and additional information when the user's emotional state is stable, which increases the solution's acceptability.

[0268] Step 10: Refine and implement the solution

[0269] The user reviews the proposed solutions and selects a feasible one, and can take into account the emotion engine's feedback when selecting a solution.

[0270] The server provides detailed plans and resource information for implementing the selected solutions, allowing users to quickly create action plans based on the information provided and solve business problems.

[0271] Through these steps, the present invention improves work efficiency and reduces stress by taking into account the user's emotions. The server, terminals, and users work together to provide a more effective data analysis and problem-solving process.

[0272] Example 2

[0273] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0274] In recent years, companies have placed increasing importance on identifying and resolving problems through business data analysis. However, existing systems face many challenges. For example, they lack the ability to easily collect and integrate data from multiple data sources, the interfaces for effectively utilizing analysis results are not intuitive, the analytical models are not accurate enough, and it takes time to prioritize business issues and present solutions. Furthermore, they present uniform feedback and solutions without considering the user's emotional state, which can increase user stress and reduce work efficiency.

[0275] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0276] In this invention, the server includes a means for collecting, standardizing, and integrating data from multiple internal data sources, a means for using the integrated data to develop a data analysis model using a machine learning algorithm, and a means for providing a user interface that can be intuitively operated by users. This enables data to be automatically collected from each department and related system and integrated in a consistent format. Furthermore, high-precision data analysis using the machine learning model enables rapid identification of business issues and the presentation of effective solutions. Furthermore, by including a means for recognizing user emotions in real time and dynamically adjusting the interface based on those emotions, the server provides optimal feedback and solutions to individual users, improving work efficiency and reducing stress.

[0277] A "data source" is a source of raw data provided by multiple departments and related systems within a company.

[0278] "Standardization" is the process of converting collected data into a consistent format and structure and integrating it.

[0279] "Integration" means combining data collected from multiple data sources into a single dataset.

[0280] A "machine learning algorithm" is a computational method that learns patterns and regularities from large amounts of data and uses them to make predictions and classifications.

[0281] A "data analysis model" is a computational model developed using machine learning algorithms to extract useful information from data.

[0282] A "user interface" is an interface that includes visual and operational elements through which a user interacts with a system.

[0283] "Business issues" are problems or areas for improvement that need to be resolved in the company's business processes.

[0284] "Solutions" are specific measures and action plans presented for the identified business issues.

[0285] An "emotion engine" is a software or hardware system that analyzes emotions from a user's facial expressions, tone of voice, text input, etc.

[0286] "Dynamic adjustment" refers to changing the behavior of an interface or system in real time according to the user's current state and environment.

[0287] "Emotion history" is a record of the user's past emotional states and the saved data.

[0288] "Analysis" is the process of examining collected data and information in detail to find meaning and patterns.

[0289] The present invention combines a system for supporting data analysis and problem solving in in-house operations with an emotion engine that recognizes user emotions. The following describes in detail the embodiments of the present invention.

[0290] The server automatically collects data from multiple internal data sources, such as sales data from each department, employee performance data, and customer feedback data, via APIs and database queries. The collected data is standardized and integrated using Python scripts and SQL.

[0291] Next, the server develops an analytical model using machine learning algorithms based on the integrated data. It uses open-source libraries such as Scikit-learn and TensorFlow to split the data into training data and test data. The model is trained using the training data and evaluated using the test data. Evaluation metrics include precision, recall, and F1 score.

[0292] The terminal provides an intuitive user interface, which is provided in the form of a web application developed with React and Vue.js and can be accessed via a browser. The interface displays a data dashboard and a list of business issues, allowing users to view analysis results and issue details.

[0293] The server uses a data analysis model to extract and list business issues. For example, it detects product quality problems and declining employee performance. The extracted issues are prioritized based on their impact and urgency, and solutions are generated. The generated solutions are presented to the user through a user interface. Specific solutions include strengthening quality control and implementing employee training.

[0294] One of the features of this invention is the incorporation of an emotion engine, which can recognize the user's emotions in real time. The emotion engine uses facial expression analysis tools such as OpenCV and natural language analysis engines to analyze emotions from voice tone and text input. Based on the analyzed emotion data, the interface content and presented solutions are dynamically adjusted.

[0295] The device dynamically adjusts the user interface based on data from the emotion engine. For example, if the device detects that the user is feeling stressed, it will simplify the solutions it presents and flexibly change the support it provides. Conversely, if the user is relaxed, it will provide more detailed information to help them make decisions.

[0296] The server also analyzes the user's emotional history and presents solutions at the optimal time, making it possible to provide effective feedback to the user. As a specific example, if sales data shows a sudden drop in sales of a particular product, the server will identify this as a quality control issue. If the emotion engine recognizes that the user's stress level is high, it will present a simple solution such as "reviewing the quality control process." On the other hand, if the user is relaxed, it will provide a detailed implementation plan.

[0297] An example of a prompt to be input to the generative AI model is, "Please summarize a use case for this system's project management functionality. For example, please explain how it helped you in a particular project, including examples of specific challenges and solutions."

[0298] Through the above steps, the present invention combines data analysis and emotion recognition to provide optimal solutions for users, improving work efficiency and reducing stress.

[0299] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0300] Step 1:

[0301] The server collects data from multiple data sources within the company. In this step, sales data, employee performance data, customer feedback data, etc. are obtained through APIs and database queries. As input, it receives raw data from each data source, and as output, it obtains a raw dataset before standardization. Specifically, the server runs periodically scheduled jobs and sends instructions to retrieve data.

[0302] Step 2:

[0303] The server standardizes and consolidates the collected data. It receives raw data in various formats (CSV, JSON, SQL, etc.) as input and generates a unified dataset in a unified format as output. Specifically, the server uses Python scripts and Pandas to convert and standardize data. For example, it handles missing values ​​in the data, unifies different formats, and extracts necessary fields.

[0304] Step 3:

[0305] The server develops a data analysis model based on the integrated data. It receives the integrated dataset as input and generates a trained model as output. Specifically, the server uses Scikit-learn or TensorFlow to split the data into training data and test data, and then trains the model using the training data. During this process, it also performs cross-validation and hyperparameter tuning.

[0306] Step 4:

[0307] The terminal provides the user interface. It receives GUI components and user browser requests as input, and displays an operable interface as output. Specifically, the terminal develops a web application using React or Vue.js to visualize data and set up an operation panel. For example, it dynamically displays analysis results or a list of business issues on a dashboard.

[0308] Step 5:

[0309] The server uses a data analysis model to extract and list business issues. It uses the trained model and the integrated dataset as input and generates a list of issues as output. Specifically, the server inputs data into the analysis model and detects various business issues (e.g., quality issues, performance degradation, customer dissatisfaction, etc.). The detected issues are stored in a database.

[0310] Step 6:

[0311] The server prioritizes the extracted business issues and generates and presents solutions. Based on the list of issues and a prioritization algorithm as input, it generates a prioritized list of issues and their corresponding solutions as output. Specifically, it scores issues based on their impact and urgency, and generates optimal solutions. These solutions are presented to the user through a user interface.

[0312] Step 7:

[0313] The server uses an emotion engine to obtain the user's emotional data in real time. It receives the user's facial expression images, voice data, and text input as input, and generates analyzed emotional data as output. Specifically, it analyzes facial expressions using tools such as OpenCV, and also performs voice tone analysis and text analysis in parallel.

[0314] Step 8:

[0315] The device dynamically adjusts the user interface based on the data obtained from the emotion engine. It receives analyzed emotion data as input and provides an adjusted interface as output. Specifically, if the user is feeling stressed, it reduces the complexity of the interface and presents simple solutions. On the other hand, if the user is relaxed, it provides detailed information to support decision-making.

[0316] Step 9:

[0317] The server analyzes the user's emotional history and presents solutions at the optimal time. It receives past emotional data as input and presents solutions at the optimal time based on the emotional patterns as output. Specifically, the server performs time series analysis and extracts patterns from the emotional history. This makes it possible to provide appropriate feedback that takes into account the user's past emotional state.

[0318] (Application example 2)

[0319] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0320] Conventional in-house work support systems focused on identifying work issues and proposing solutions based on data analysis, but because they did not take into account the user's emotional state, they had the problem of increasing stress and strain in the actual work environment.In addition, because they did not provide flexible feedback or adjust the interface according to the user's emotional state, it was difficult to improve the user experience.

[0321] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0322] In this invention, the server includes means for collecting, standardizing, and integrating data from multiple data sources within the company, means for using the integrated data and a machine learning algorithm to develop a data analysis model, means for providing a user interface that can be intuitively operated by a user, means for extracting and listing business issues using the data analysis model, means for prioritizing the extracted business issues and presenting solutions, emotion analysis means for recognizing the user's emotions in real time and adjusting the content of the presentation, and means for providing the user with optimal solutions to business issues based on the collected data and emotion information. Thus, by combining data analysis and emotion recognition, optimal solutions can be provided for the user, improving work efficiency and reducing stress.

[0323] "Data Sources" means the various internal or external information sources used to provide information.

[0324] "Standardization" is the process of unifying data in various formats by converting them into a consistent format.

[0325] "Synthesis" is the act of combining data collected from multiple data sources into a single coherent data set.

[0326] A "machine learning algorithm" is a mathematical technique for automatically learning patterns from data and making predictions or classifications.

[0327] "Data analytics model" refers to a trained machine learning model used to derive insights from data.

[0328] A "user interface" is an interactive screen or tool that allows a user to directly interact with a system.

[0329] "Business issues" refer to various problems and obstacles that arise during the execution of business operations.

[0330] "Prioritization" is the process of determining the order of issues based on importance and urgency.

[0331] A "solution" is a specific means or process for solving a particular challenge or problem.

[0332] "Emotion analysis means" is a technology that recognizes emotions by analyzing a user's facial expressions, voice tone, text input, etc.

[0333] "Emotional history" refers to records and data regarding a user's past emotional states.

[0334] "Feedback" refers to the response or reaction a user receives from a system.

[0335] A system according to the present invention can be implemented using the following hardware and software.

[0336] Hardware

[0337] 1. Server: A high-performance server for collecting, integrating, and analyzing data.

[0338] 2. Camera: A high-resolution camera to capture the facial expressions of workers in real time.

[0339] 3. Microphone: Highly sensitive microphone for analyzing voice tones.

[0340] 4. Terminal: A device that provides a user interface, such as a smartphone, smart glasses, or tablet.

[0341] software

[0342] 1. DeepFace: A machine learning library for facial expression analysis.

[0343] 2. OpenCV: A library for image processing.

[0344] 3. TensorFlow: A library used to train and run machine learning models.

[0345] 4. GPT-3 API: An API for natural language generation.

[0346] 5. Web Application Framework: Building user interfaces using React.js and Django.

[0347] Data collection and analysis

[0348] The server collects, standardizes, and integrates data from multiple data sources within the factory, including sales data, employee performance data, and customer feedback data, all of which exist in various formats. The integrated data is then analyzed using TensorFlow, and a data analysis model is developed using machine learning algorithms.

[0349] Providing a user interface

[0350] The terminal provides an intuitive user interface as a web application that combines React.js and Django, allowing users to check analysis results and business issues via a browser.

[0351] Identifying business issues and presenting solutions

[0352] The server uses a data analysis model based on the collected data to extract and list business issues. It then prioritizes the issues based on their impact and urgency and presents solutions. Specific solutions include strengthening quality control and implementing employee training.

[0353] Use of sentiment analysis methods

[0354] The server uses DeepFace and OpenCV to analyze the user's facial expressions and voice tone in real time to recognize their emotional state. This allows the presented solutions and information to be dynamically adjusted according to the user's emotional state. If the user is feeling stressed, the presented solutions will be simplified and they will be encouraged to take a break if necessary.

[0355] Emotion history management and feedback

[0356] The server analyzes the user's emotional history and presents solutions at the optimal time based on past emotional patterns, thereby improving the user experience and work efficiency.

[0357] Specific examples

[0358] Example 1

[0359] If the worker is relaxed, provide detailed workflow optimization suggestions. Use the following prompt to generate detailed explanations:

[0360] Generate a detailed optimization strategy for the work flow in your factory when workers are relaxed.

[0361] Example 2

[0362] If a worker is feeling stressed, provide a simplified procedure and suggest a break. Use the following prompt to generate the simplified procedure:

[0363] Generate simplified work procedures when workers are stressed. Also suggest breaks for workers.

[0364] By implementing this invention, it becomes possible to perform optimal data analysis and present solutions that take into account the user's emotional state, which is expected to improve work efficiency and reduce stress.

[0365] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0366] Step 1:

[0367] The server collects, standardizes, and integrates data from multiple data sources within the factory. Input data includes sales data, employee performance data, and customer feedback data. The output is standardized integrated data. Specifically, information in different data formats is processed to unify it and compiled into a single data set.

[0368] Step 2:

[0369] The server uses the integrated data to develop a data analysis model using a machine learning algorithm (such as TensorFlow). The input data is the integrated dataset, and the output is a trained data analysis model. Specific operations include splitting the data into training data and test data, and training the model using the training data.

[0370] Step 3:

[0371] The terminal provides a user interface that users can operate intuitively. The input data is the analysis results and a list of business tasks, and the output is the interface screen provided to the user. Specifically, we will use React.js and Django to build a web application that users can access via a browser.

[0372] Step 4:

[0373] The server uses a data analysis model to extract business issues and list them. The input data is the output of the analysis model, and the output is a list of extracted business issues. Specifically, the analysis model detects quality issues and declines in employee performance from business data and lists them as issues.

[0374] Step 5:

[0375] The server prioritizes the extracted business issues based on their impact and urgency, and presents solutions. The input data is a list of business issues, and the output is a prioritized list of solutions. Specifically, it calculates a priority score and generates solutions from the most urgent and important issues.

[0376] Step 6:

[0377] The server uses emotion analysis tools (DeepFace, OpenCV, etc.) to analyze the user's facial expressions and voice tone in real time. The input data is the user's real-time video and audio, and the output is information about the user's emotional state. Specifically, it acquires data from the camera and microphone, analyzes facial expressions and voice tone, and determines the user's emotional state.

[0378] Step 7:

[0379] The device dynamically adjusts the content of the user interface based on the analysis results and the user's emotional state. The input data are the emotion analysis results and solutions to business problems, and the output is an adjusted user interface screen. Specifically, if the user is feeling stressed, the information is simplified, and if the user is relaxed, detailed solutions are presented.

[0380] Step 8:

[0381] The server analyzes the user's emotional history and presents solutions at the optimal time based on past emotional patterns. The input data is emotional history data, and the output is solutions presented at the appropriate time. Specifically, it analyzes the user's emotional patterns and presents feedback at the timing that elicits the user's optimal response.

[0382] Step 9:

[0383] The server uses a generative AI model (such as the GPT-3 API) to generate specific solutions and feedback messages based on the user's emotional state. Specific input prompts include "Generate a detailed optimization strategy for the factory workflow when workers are relaxed" and "Generate simplified work procedures when workers are stressed. Also suggest breaks for workers." The obtained prompts are provided to the user as appropriate solutions based on their emotional state.

[0384] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0385] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0386] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0387] [Second embodiment]

[0388] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0389] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0390] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0391] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0392] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0393] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0394] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0395] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0396] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0397] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0398] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0399] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0400] The present invention relates to a system for supporting data analysis and problem solving in in-house operations. Specific embodiments for carrying out the present invention will be described in detail below.

[0401] Internal data collection and integration

[0402] The server automatically collects data from various departments and related systems within the company. For example, it collects data in various formats, such as sales data, employee performance data, and customer feedback data. Because this data is often stored in different formats, the server consolidates and standardizes the collected data to centralize it.

[0403] Development of data analysis models using machine learning algorithms

[0404] The server uses the integrated data to develop a data analysis model using machine learning algorithms. This model is used to extract business issues and utilizes advanced algorithms such as random forests and neural networks. To develop the model, the data is divided into training data and test data, the model is trained using the training data, and its accuracy is evaluated using the test data.

[0405] Providing a user interface

[0406] The terminal provides a user interface that users can operate intuitively. For example, a web application-style interface can be used, allowing users to access and operate the system through a browser. The interface displays the results of data analysis, extracted business issues, and solutions to each issue.

[0407] Extracting and listing business issues

[0408] The server uses the developed data analysis model to extract business issues from the integrated data. For example, it identifies specific issues such as problems with product quality, issues related to declining employee performance, and customer complaints. The extracted issues are listed so that users can easily check them.

[0409] Prioritizing issues and proposing solutions

[0410] The server prioritizes the extracted business issues, determining the order based on the impact and urgency of the issues. Solutions are presented starting with the most important issues, and the server notifies the user through the user interface. Specific examples include strengthening quality control, conducting regular training, and optimizing resource allocation.

[0411] Solution review and implementation

[0412] The user examines the solutions presented by the server and selects a feasible one. To help the user put the selected solution into practice, the server also provides a detailed execution plan and information on the necessary resources. This allows the user to efficiently solve business problems.

[0413] As a specific example, if the server detects a sudden drop in sales of a particular product from sales data, it will extract the issue as a quality control problem and suggest a solution: "Review the quality control process." The user will then carefully examine the proposed solution, create an action plan, and apply it.

[0414] This invention makes it possible to make maximum use of in-house data, thereby improving business efficiency and preventing large-scale problems.

[0415] The processing flow will be explained below.

[0416] Step 1: Collect data

[0417] The server collects data from various departments within the company, such as sales data, employee performance data, customer feedback, etc. The data is available in various formats, including CSV files, Excel files, and JSON files.

[0418] The server uses APIs and database connections to collect data.

[0419] Step 2: Integrate and standardize data

[0420] The server consolidates the collected data and performs standardization processes to unify data in different formats, such as standardizing date formats and cleaning unnecessary data.

[0421] The server uses an ETL (Extract, Transform, Load) process to transform the data into an analyzable format so that all the data can be treated as a single unified dataset.

[0422] Step 3: Developing a data analysis model

[0423] The server uses the data combined in the previous step to apply machine learning algorithms, for example, random forests or neural networks to train models.

[0424] The server splits the data into training data and test data, evaluates the accuracy of the model, and adjusts the hyperparameters until a highly accurate model is obtained.

[0425] Step 4: Providing a User Interface

[0426] The terminal provides a user interface that allows users to intuitively operate the system, typically in the form of a web application.

[0427] The terminal displays a dashboard that allows users to view and operate the results of data analysis and extracted business issues.

[0428] Step 5: Identify and list business issues

[0429] The server uses a data analysis model to extract business issues from the integrated data, such as declining sales of a particular product or poor employee performance.

[0430] The server lists the extracted tasks and presents them to the user through a user interface.

[0431] Step 6: Prioritize issues and present solutions

[0432] The server prioritizes the extracted business issues based on their impact and urgency, and creates solutions starting with the most critical issues.

[0433] The server generates specific solutions for each problem and presents them to the user through a user interface, such as reviewing quality control processes or strengthening employee training.

[0434] Step 7: Refine and implement the solution

[0435] The user examines the solutions presented by the server, selects feasible solutions from the presented ones, and creates a specific implementation plan.

[0436] The server supports the allocation of detailed information and resources required to implement solutions, and helps users to efficiently solve problems based on this information.

[0437] By going through the above steps, the present invention realizes effective analysis of in-house data and rapid resolution of business issues. At each step, the server, terminal, and user work together to improve business efficiency and prevent large-scale problems.

[0438] Example 1

[0439] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0440] Many companies face challenges in collecting data from multiple internal data sources and utilizing it effectively. In particular, integrating data stored in different formats, identifying business issues, prioritizing those issues, and presenting optimal solutions are difficult. Furthermore, there is a need for a user interface that allows users to intuitively grasp the results of data analysis. The present invention aims to solve these challenges and provide a system that utilizes data efficiently and effectively.

[0441] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0442] In this invention, the server includes: means for automatically collecting and acquiring data from multiple internal data sources; means for converting the collected data into a unified format and integrating and standardizing the data; means for using the integrated data to build a data analysis model using a machine learning algorithm; means for providing a web-based interface that can be intuitively operated by a user; means for automatically extracting and listing business issues using the built data analysis model; means for prioritizing the extracted business issues and presenting solutions; and means for reviewing the presented solutions based on user feedback and providing an implementation plan for the selected solution. This makes it possible to efficiently collect and integrate internal data, effectively analyze it, extract business issues, prioritize them, present solutions, and provide them in a format that is intuitively understandable to the user.

[0443] "Data source" refers to the source of data provided by multiple departments and related systems within the company.

[0444] "Data collection" refers to the process of automatically obtaining the necessary data from internal data sources.

[0445] "Unified data format" refers to converting data stored in different formats into one standard format.

[0446] "Data integration" refers to the process of combining data collected from different data sources into one continuous data set.

[0447] "Data standardization" refers to the process of organizing integrated data into a consistent format.

[0448] "Machine learning algorithm" refers to the statistical techniques and computational methods used to build data analysis models.

[0449] "Data analysis model" refers to a model built using machine learning algorithms to extract specific business issues based on integrated and standardized data.

[0450] "Web-based interface" refers to a user interface accessible through a browser.

[0451] "Business issue extraction" refers to the process of using a data analysis model to identify issues related to internal business operations.

[0452] "Listing up" refers to compiling the extracted business issues in a list format.

[0453] "Prioritization" refers to setting the order in which extracted business issues should be addressed based on their impact and urgency.

[0454] "Providing solutions" refers to showing specific measures for the extracted business issues.

[0455] "User feedback" refers to the process of collecting opinions and ratings from users.

[0456] "Scrutiny" refers to examining the proposed solution in detail and assessing its validity.

[0457] "Providing an action plan" refers to showing the steps and resources required to specifically implement the solution selected by the user.

[0458] The present invention relates to a system for supporting data analysis and problem solving in in-house operations. Specific embodiments for carrying out the present invention will be described in detail below.

[0459] Internal data collection and integration

[0460] The server automatically collects data from various departments and related systems within the company. For example, it obtains sales data, employee performance data, and customer feedback data through a database management system (DBMS) or RESTful API. This data is often stored in different formats, so the server uses a data conversion tool (Python script) to convert this data into a unified format (CSV or JSON) and standardize it.

[0461] Development of data analysis models using machine learning algorithms

[0462] The server uses the integrated data to build a data analysis model using machine learning algorithms. This model is used to extract business issues, and random forest or neural network models are developed using Python and the TensorFlow or Scikit-learn library. The data is divided into training data and test data, and the training data is used to train the model, and the test data is used to evaluate the accuracy of the model.

[0463] Providing a user interface

[0464] The terminal provides a user interface that users can operate intuitively. Specifically, a web-based interface built with React.js is used. Users can access the system through a browser and view the results of data analysis and extracted business issues. The interface is created using Bootstrap and Material-UI.

[0465] Extracting and listing business issues

[0466] The server uses the developed data analysis model to extract business issues from the integrated data. For example, it identifies specific issues such as problems with product quality, issues related to declining employee performance, and customer complaints. These issues are saved in JSON format and notified to the user interface via a RESTful API. For example, if the server detects from sales data that sales of a particular product have dropped sharply, it will extract the issue as a problem related to the quality of that product and suggest a solution: "reviewing the quality control process."

[0467] Prioritizing issues and proposing solutions

[0468] The server prioritizes the extracted business issues, setting the order based on impact and urgency, and presenting solutions starting with the most important issues. For example, it might suggest solutions such as "reviewing the quality control process" or "conducting regular training." This information is also displayed on the user interface via a RESTful API.

[0469] Solution review and implementation

[0470] The user examines the solutions presented by the server and selects a feasible one. The selected solution is then provided along with a detailed implementation plan. For example, if "reviewing the quality control process" is selected as a solution, specific considerations, required resources, and a schedule are presented.

[0471] Specific examples

[0472] If the server detects from sales data that sales of a particular product have dropped sharply, it will identify the issue as a problem with the quality of that product and suggest a "review of the quality control process" as a solution.

[0473] Example of input prompt for generative AI model

[0474] Here are some example prompts to input to a generative AI model:

[0475] "Use departmental performance data to identify factors associated with poor employee performance."

[0476] "Analyze customer feedback data and extract key complaints."

[0477] "Use random forest to build a product sales prediction model."

[0478] This invention makes it possible to make maximum use of in-house data, thereby improving business efficiency and preventing large-scale problems.

[0479] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0480] Step 1: Collect data

[0481] The server automatically collects data from each department and related systems within the company. It uses a database management system (DBMS) and RESTful APIs to obtain sales data, employee performance data, and customer feedback data. This data is collected in a temporary storage area within the server.

[0482] Specifically, a Python script runs periodically, sends an API request, and retrieves the latest data, which is then converted to CSV format and saved.

[0483] Input: API request, database query

[0484] Output: CSV format data file

[0485] Step 2: Integrate and standardize data

[0486] The server converts the collected data into a unified format, consolidating and standardizing the data, and converting data from different formats into a unified schema for the SQL database.

[0487] Specifically, a data conversion Python script is run to convert each dataset into a unified format (e.g., all numeric data is rounded to two decimal places), and the converted data is imported into a MySQL database.

[0488] Input: CSV format data file

[0489] Output: Data in a unified format (stored in an SQL database)

[0490] Step 3: Building a machine learning model

[0491] The server uses the integrated data to build machine learning models, developing random forest and neural network models using Python, TensorFlow, and Scikit-learn.

[0492] Specifically, the server loads the data using a Python script and splits it into training and test data using SciPy. Next, it builds a neural network model using TensorFlow and trains it using the training data. The accuracy of the model is evaluated using the test data, and the models that are confirmed to have high accuracy are saved.

[0493] Input: Unified format data (SQL database)

[0494] Output: A trained machine learning model

[0495] Step 4: Providing a User Interface

[0496] The terminal provides an intuitive user interface, allowing users to view the results of data analysis and extracted business issues through a web-based interface built with React.js.

[0497] Specifically, when a user opens a web browser and accesses a specific URL, the device receives HTML, CSS, and JavaScript files from the server and displays information dynamically constructed by React.js.

[0498] Input: User's browser access

[0499] Output: Web page displaying analysis results and business issues

[0500] Step 5: Identify and list business issues

[0501] The server uses the developed data analysis model to extract business issues from the integrated data, identifying and listing issues such as product quality problems, poor employee performance, and customer dissatisfaction.

[0502] Specifically, the server periodically re-analyzes the integrated data and extracts business issues using the stored machine learning model. The extracted issues are saved in JSON format and delivered to the front end via a RESTful API.

[0503] Input: Integrated data, machine learning model

[0504] Output: Extracted business issues (saved in JSON format)

[0505] Step 6: Prioritize issues and present solutions

[0506] The server prioritizes the extracted business issues based on their impact and urgency, and presents solutions starting with the most important issues.

[0507] Specifically, the system runs a prioritization algorithm to calculate an impact score for each issue, after which the solution is displayed in the user interface.

[0508] Input: Extracted business issues (JSON format)

[0509] Output: Prioritized issues and solutions

[0510] Step 7: Refine and implement the solution

[0511] The user reviews the proposed solutions and selects a viable one, which is then provided with a detailed implementation plan.

[0512] Specifically, the user selects a solution on the user interface and sends that information to the server. Based on the selected solution, the server generates specific study items, required resources, and a schedule, and displays them on the user interface.

[0513] Input: User's solution selection

[0514] Output: Detailed execution plan

[0515] (Application example 1)

[0516] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0517] Modern factories require real-time monitoring of each robot's performance and error status, and the ability to quickly address these issues. However, achieving this requires a system that can efficiently collect and analyze large amounts of data and provide users with appropriate solutions. Conventional systems take time to integrate and analyze data, identify issues, and present solutions, resulting in delays in providing appropriate solutions. Another challenge is providing an interface that is easy for users to use.

[0518] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0519] In this invention, the server includes: means for collecting, standardizing, and integrating data from multiple data sources within a company; means for using the integrated data to develop a data analysis model using a machine learning algorithm; means for providing a user interface that can be intuitively operated by a user; means for extracting and listing business issues using the data analysis model; means for prioritizing the extracted business issues and proposing solutions; means for examining the proposed solutions together with the user and implementing feasible ones; means for collecting robot data in real time; and means for analyzing the collected data, extracting issues, prioritizing them, and displaying solutions on a smartphone screen. This makes it possible to monitor robot performance and error status in a factory in real time and quickly and effectively resolve issues.

[0520] Key Word Definitions

[0521] "Data source" is a general term for a system or device that provides data.

[0522] "Standardization" is the process of converting data of different formats into a consistent format.

[0523] "Integration" means combining data obtained from multiple different data sources into a single data set.

[0524] A "machine learning algorithm" is a program or method that learns patterns from data and automatically performs tasks such as prediction and categorization.

[0525] A "data analysis model" is a specific computational model constructed using machine learning algorithms for analyzing and predicting data.

[0526] A "user interface" is a visual and operational interface that allows a user to operate a system or application.

[0527] A "business issue" is a specific problem or obstacle that needs to be solved in the operations or work processes of a company or organization.

[0528] "Priority" means determining the order in which multiple issues or tasks should be handled based on their importance and urgency.

[0529] A "solution" is a specific action or method that should be taken to address a specific problem or issue.

[0530] "Real-time collection" is the process of collecting data immediately without delay.

[0531] A "smartphone screen" is a smartphone display and an interface for displaying applications and information.

[0532] "Robot data" refers to operational data such as performance and error information obtained from robots operating in factories.

[0533] MODE FOR CARRYING OUT THE INVENTION

[0534] The present invention provides a system for monitoring the performance of robots in a factory and the occurrence of errors in real time, and for responding quickly and effectively. Specific embodiments for carrying out the present invention will be described in detail below.

[0535] Configuration and Overview

[0536] The system consists of the following elements:

[0537] 1. Data collection and integration:

[0538] The server automatically collects data from multiple data sources within the factory. Specifically, this includes operation data, performance data, and error occurrence information for each robot. Because this data is stored in different formats, the server standardizes and centralizes the data.

[0539] 2. Development of data analysis models using machine learning algorithms:

[0540] The server uses the integrated data to develop a data analysis model using a machine learning algorithm (e.g., RandomForestClassifier). This model detects robot anomalies and identifies operational issues. It also splits the data into training and test data, trains the model, and evaluates its accuracy.

[0541] 3. Providing the user interface:

[0542] The terminal (e.g., a smartphone) provides a user interface that can be operated intuitively by the user. Specifically, a dashboard-style interface is considered, allowing the user to access the system through the smartphone screen and check the analysis results and solutions.

[0543] 4. Extract and list business issues:

[0544] The server uses the developed data analysis model to extract business issues from the integrated data. The extracted issues are listed so that users can easily check them. For example, they may include the cause of a particular robot's shutdown or frequent errors.

[0545] 5. Prioritizing issues and proposing solutions:

[0546] The server prioritizes the extracted business issues and presents solutions based on the impact and urgency of the issues. For example, this could include the timing of preventive maintenance or part replacement for a specific robot.

[0547] 6. Solution Examination and Implementation:

[0548] The user can then examine the solutions presented by the server and implement the most appropriate one. Specifically, the user can check the details of the solution and the implementation procedure through the user interface.

[0549] Hardware and Software

[0550] Hardware: Smartphone

[0551] Software: Python, requests library, scikit-learn

[0552] Specific examples

[0553] For example, if a particular robot in a factory stops working multiple times over a certain period of time, the system will identify the cause and suggest preventative maintenance. Users can view the following information on their smartphone screen:

[0554] Prompt Sentence Examples

[0555] "Factory robot 22 has stopped working three times in one week. Please provide possible issues that could be causing the downtime and solutions."

[0556] This makes it possible to monitor robot performance and error conditions within the factory in real time and resolve issues quickly and effectively.

[0557] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0558] Step 1:

[0559] The server collects operational data, performance data, and error information from each robot in the factory in real time. Because this data is stored in different formats, the server standardizes and centralizes the data.

[0560] Input: Operation data, performance data, and error information sent from each robot

[0561] Output: Standardized and unified dataset

[0562] Step 2:

[0563] The server uses the standardized data to develop a data analysis model using a machine learning algorithm (e.g., RandomForestClassifier). The model is divided into training data and test data, trained, and its accuracy is evaluated.

[0564] Input: Standardized dataset

[0565] Output: A trained data analysis model

[0566] Step 3:

[0567] The server uses a trained data analysis model to extract robot anomalies and operational issues from the integrated data, identifying and listing information according to the type and situation of the issue.

[0568] Input: Trained data analysis model, standardized dataset

[0569] Output: A list of extracted anomalies and business issues

[0570] Step 4:

[0571] The server prioritizes the extracted business issues and presents solutions to each issue using machine learning models as a reference. Priorities are determined based on the importance and urgency of the issues.

[0572] Input: List of anomalies and business issues

[0573] Output: A prioritized list of issues and solutions

[0574] Step 5:

[0575] The terminal displays the prioritized list of issues and solutions sent from the server to the user through a user interface, allowing the user to intuitively operate the terminal and check detailed information.

[0576] Input: A prioritized list of issues and solutions sent from the server

[0577] Output: Analysis results and solutions displayed on the smartphone screen

[0578] Step 6:

[0579] Users can examine the presented solutions, select the most appropriate one, and put it into action. Specific steps and information on the necessary resources are also provided, allowing for efficient problem-solving.

[0580] Input: Solution displayed on smartphone screen

[0581] Output: The selected solution and its implementation plan

[0582] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0583] The present invention combines a system that supports data analysis and problem solving in in-house operations with an emotion engine that recognizes user emotions. Specific embodiments for carrying out the present invention will be described in detail below.

[0584] Internal data collection and integration

[0585] The server automatically collects data from various departments and related systems within the company, such as sales data, employee performance data, customer feedback data, etc. Because the data exists in various formats, the server standardizes and consolidates the collected data.

[0586] Development of data analysis models using machine learning algorithms

[0587] The server uses machine learning algorithms to develop a data analysis model based on the integrated data. To develop the model, the data is divided into training data and test data, and the model is trained using the training data. The accuracy of the model is evaluated using the test data, and the model with the highest accuracy is selected.

[0588] Providing a user interface

[0589] The terminal provides a user interface that can be operated intuitively by the user. A web application-style interface is provided, and users can access the system via a browser and check analysis results and business issues.

[0590] Extracting and listing business issues

[0591] The server uses a data analysis model to extract business issues from the integrated data. For example, it detects and lists problems related to product quality or poor employee performance. The extracted issues are then provided to the user through a user interface.

[0592] Prioritizing issues and proposing solutions

[0593] The server prioritizes the extracted business issues based on their impact and urgency. Solutions are generated for the most important issues first and are notified to the user through the user interface. Specific solutions include strengthening quality control and implementing employee training.

[0594] Incorporating an emotion engine

[0595] One of the features of the present invention is that it incorporates an emotion engine to recognize the user's emotions in real time and adjust the analysis results and presented solutions according to the user's emotional state. The emotion engine analyzes emotions from the user's facial expressions, voice tone, text input, etc.

[0596] Dynamic adjustment of emotion-based interfaces

[0597] The device dynamically adjusts the user interface based on data obtained from the emotion engine. For example, if the user is stressed, it will simplify the solution suggestions and provide flexible support. If the user is relaxed, it will provide detailed information to support decision-making.

[0598] Emotion history analysis

[0599] The server analyzes the user's emotional history and presents solutions at the optimal time based on past emotional patterns, enabling appropriate feedback that takes into account the user's emotional state.

[0600] For example, if sales data detects a sudden drop in sales of a particular product, the issue is extracted as a quality control problem. If the emotion engine recognizes that the user's stress level is high, the solution is simplified and a simple suggestion such as "review the quality control process" is made. If the user is relaxed, a detailed implementation plan is presented.

[0601] Through the above steps, the present invention combines data analysis and emotion recognition to provide optimal solutions for users, improving work efficiency and reducing stress.

[0602] The processing flow will be explained below.

[0603] Step 1: Collect data

[0604] The server collects data from various departments and related systems within the company, including sales data, employee performance data, and customer feedback data.

[0605] I won't provide any code examples, but the server retrieves data using an API or database connection.

[0606] Step 2: Integrate and standardize data

[0607] The server consolidates the collected data and performs standardization processes, such as standardizing date formats and normalizing text data.

[0608] The server applies an ETL (Extract, Transform, Load) process to produce a unified dataset, which brings the data into a single, analyzable format.

[0609] Step 3: Developing a data analysis model

[0610] The server uses the combined data to develop data analysis models using machine learning algorithms, such as random forests and neural networks.

[0611] The server splits the data into training data and test data, trains the model using the training data, and evaluates the model on the test data to measure accuracy.

[0612] Step 4: Providing a User Interface

[0613] The terminal provides a user interface that can be operated intuitively by the user. The interface is in the form of a web application, and the user accesses it from a browser.

[0614] The interface on the terminal displays the results of data analysis and extracted business issues, which the user uses to interact with the system.

[0615] Step 5: Identify and list business issues

[0616] The server uses data analysis models to extract specific business issues from the integrated data, such as declining sales of a particular product, poor employee performance, or customer dissatisfaction.

[0617] The extracted issues are provided to the user as a list via a user interface, and the user checks this list to identify issues that require action.

[0618] Step 6: Prioritize the issues and present solutions

[0619] The server prioritizes the extracted business issues based on their impact and urgency. The impact of the issues is evaluated using a data analysis model.

[0620] The server generates specific solutions in order of priority and presents them to the user through a user interface. For example, it may suggest solutions such as "reviewing the quality control process" or "strengthening employee training."

[0621] Step 7: Recognizing user emotions with the emotion engine

[0622] The server analyzes the user's emotional state based on the user's emotional data acquired from the terminal (for example, facial expressions, voice tone, and analysis results of text input).

[0623] The emotion engine recognizes the user's emotions in real time, so if the user is feeling stressed, for example, this is fed back to the system.

[0624] Step 8: Dynamically adjust the interface based on emotions

[0625] The device dynamically adjusts the user interface based on data from the emotion engine, simplifying suggested solutions and providing more support when the user is feeling stressed.

[0626] For example, you can omit the details of the solution and show only the key points, or change the color scheme and layout to reduce visual strain.

[0627] Step 9: Analyze emotion history and provide solutions at the optimal time

[0628] The server analyzes the user's past emotional history and understands their emotional patterns, which allows it to present solutions at the optimal time.

[0629] Present detailed solutions and additional information when the user's emotional state is stable, which increases the solution's acceptability.

[0630] Step 10: Refine and implement the solution

[0631] The user reviews the proposed solutions and selects a feasible one, and can take into account the emotion engine's feedback when selecting a solution.

[0632] The server provides detailed plans and resource information for implementing the selected solutions, allowing users to quickly create action plans based on the information provided and solve business problems.

[0633] Through these steps, the present invention improves work efficiency and reduces stress by taking into account the user's emotions. The server, terminals, and users work together to provide a more effective data analysis and problem-solving process.

[0634] Example 2

[0635] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0636] In recent years, companies have placed increasing importance on identifying and resolving problems through business data analysis. However, existing systems face many challenges. For example, they lack the ability to easily collect and integrate data from multiple data sources, the interfaces for effectively utilizing analysis results are not intuitive, the analytical models are not accurate enough, and it takes time to prioritize business issues and present solutions. Furthermore, they present uniform feedback and solutions without considering the user's emotional state, which can increase user stress and reduce work efficiency.

[0637] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0638] In this invention, the server includes a means for collecting, standardizing, and integrating data from multiple internal data sources, a means for using the integrated data to develop a data analysis model using a machine learning algorithm, and a means for providing a user interface that can be intuitively operated by users. This enables data to be automatically collected from each department and related system and integrated in a consistent format. Furthermore, high-precision data analysis using the machine learning model enables rapid identification of business issues and the presentation of effective solutions. Furthermore, by including a means for recognizing user emotions in real time and dynamically adjusting the interface based on those emotions, the server provides optimal feedback and solutions to individual users, improving work efficiency and reducing stress.

[0639] A "data source" is a source of raw data provided by multiple departments and related systems within a company.

[0640] "Standardization" is the process of converting collected data into a consistent format and structure and integrating it.

[0641] "Integration" means combining data collected from multiple data sources into a single dataset.

[0642] A "machine learning algorithm" is a computational method that learns patterns and regularities from large amounts of data and uses them to make predictions and classifications.

[0643] A "data analysis model" is a computational model developed using machine learning algorithms to extract useful information from data.

[0644] A "user interface" is an interface that includes visual and operational elements through which a user interacts with a system.

[0645] "Business issues" are problems or areas for improvement that need to be resolved in the company's business processes.

[0646] "Solutions" are specific measures and action plans presented for the identified business issues.

[0647] An "emotion engine" is a software or hardware system that analyzes emotions from a user's facial expressions, tone of voice, text input, etc.

[0648] "Dynamic adjustment" refers to changing the behavior of an interface or system in real time according to the user's current state and environment.

[0649] "Emotion history" is a record of the user's past emotional states and the saved data.

[0650] "Analysis" is the process of examining collected data and information in detail to find meaning and patterns.

[0651] The present invention combines a system for supporting data analysis and problem solving in in-house operations with an emotion engine that recognizes user emotions. The following describes in detail the embodiments of the present invention.

[0652] The server automatically collects data from multiple internal data sources, such as sales data from each department, employee performance data, and customer feedback data, via APIs and database queries. The collected data is standardized and integrated using Python scripts and SQL.

[0653] Next, the server develops an analytical model using machine learning algorithms based on the integrated data. It uses open-source libraries such as Scikit-learn and TensorFlow to split the data into training data and test data. The model is trained using the training data and evaluated using the test data. Evaluation metrics include precision, recall, and F1 score.

[0654] The terminal provides an intuitive user interface, which is provided in the form of a web application developed with React and Vue.js and can be accessed via a browser. The interface displays a data dashboard and a list of business issues, allowing users to view analysis results and issue details.

[0655] The server uses a data analysis model to extract and list business issues. For example, it detects product quality problems and declining employee performance. The extracted issues are prioritized based on their impact and urgency, and solutions are generated. The generated solutions are presented to the user through a user interface. Specific solutions include strengthening quality control and implementing employee training.

[0656] One of the features of this invention is the incorporation of an emotion engine, which can recognize the user's emotions in real time. The emotion engine uses facial expression analysis tools such as OpenCV and natural language analysis engines to analyze emotions from voice tone and text input. Based on the analyzed emotion data, the interface content and presented solutions are dynamically adjusted.

[0657] The device dynamically adjusts the user interface based on data from the emotion engine. For example, if the device detects that the user is feeling stressed, it will simplify the solutions it presents and flexibly change the support it provides. Conversely, if the user is relaxed, it will provide more detailed information to help them make decisions.

[0658] The server also analyzes the user's emotional history and presents solutions at the optimal time, making it possible to provide effective feedback to the user. As a specific example, if sales data shows a sudden drop in sales of a particular product, the server will identify this as a quality control issue. If the emotion engine recognizes that the user's stress level is high, it will present a simple solution such as "reviewing the quality control process." On the other hand, if the user is relaxed, it will provide a detailed implementation plan.

[0659] An example of a prompt to be input to the generative AI model is, "Please summarize a use case for this system's project management functionality. For example, please explain how it helped you in a particular project, including examples of specific challenges and solutions."

[0660] Through the above steps, the present invention combines data analysis and emotion recognition to provide optimal solutions for users, improving work efficiency and reducing stress.

[0661] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0662] Step 1:

[0663] The server collects data from multiple data sources within the company. In this step, sales data, employee performance data, customer feedback data, etc. are obtained through APIs and database queries. As input, it receives raw data from each data source, and as output, it obtains a raw dataset before standardization. Specifically, the server runs periodically scheduled jobs and sends instructions to retrieve data.

[0664] Step 2:

[0665] The server standardizes and consolidates the collected data. It receives raw data in various formats (CSV, JSON, SQL, etc.) as input and generates a unified dataset in a unified format as output. Specifically, the server uses Python scripts and Pandas to convert and standardize data. For example, it handles missing values ​​in the data, unifies different formats, and extracts necessary fields.

[0666] Step 3:

[0667] The server develops a data analysis model based on the integrated data. It receives the integrated dataset as input and generates a trained model as output. Specifically, the server uses Scikit-learn or TensorFlow to split the data into training data and test data, and then trains the model using the training data. During this process, it also performs cross-validation and hyperparameter tuning.

[0668] Step 4:

[0669] The terminal provides the user interface. It receives GUI components and user browser requests as input, and displays an operable interface as output. Specifically, the terminal develops a web application using React or Vue.js to visualize data and set up an operation panel. For example, it dynamically displays analysis results or a list of business issues on a dashboard.

[0670] Step 5:

[0671] The server uses a data analysis model to extract and list business issues. It uses the trained model and the integrated dataset as input and generates a list of issues as output. Specifically, the server inputs data into the analysis model and detects various business issues (e.g., quality issues, performance degradation, customer dissatisfaction, etc.). The detected issues are stored in a database.

[0672] Step 6:

[0673] The server prioritizes the extracted business issues and generates and presents solutions. Based on the list of issues and a prioritization algorithm as input, it generates a prioritized list of issues and their corresponding solutions as output. Specifically, it scores issues based on their impact and urgency, and generates optimal solutions. These solutions are presented to the user through a user interface.

[0674] Step 7:

[0675] The server uses an emotion engine to obtain the user's emotional data in real time. It receives the user's facial expression images, voice data, and text input as input, and generates analyzed emotional data as output. Specifically, it analyzes facial expressions using tools such as OpenCV, and also performs voice tone analysis and text analysis in parallel.

[0676] Step 8:

[0677] The device dynamically adjusts the user interface based on the data obtained from the emotion engine. It receives analyzed emotion data as input and provides an adjusted interface as output. Specifically, if the user is feeling stressed, it reduces the complexity of the interface and presents simple solutions. On the other hand, if the user is relaxed, it provides detailed information to support decision-making.

[0678] Step 9:

[0679] The server analyzes the user's emotional history and presents solutions at the optimal time. It receives past emotional data as input and presents solutions at the optimal time based on the emotional patterns as output. Specifically, the server performs time series analysis and extracts patterns from the emotional history. This makes it possible to provide appropriate feedback that takes into account the user's past emotional state.

[0680] (Application example 2)

[0681] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0682] Conventional in-house work support systems focused on identifying work issues and proposing solutions based on data analysis, but because they did not take into account the user's emotional state, they had the problem of increasing stress and strain in the actual work environment.In addition, because they did not provide flexible feedback or adjust the interface according to the user's emotional state, it was difficult to improve the user experience.

[0683] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0684] In this invention, the server includes means for collecting, standardizing, and integrating data from multiple data sources within the company, means for using the integrated data and a machine learning algorithm to develop a data analysis model, means for providing a user interface that can be intuitively operated by a user, means for extracting and listing business issues using the data analysis model, means for prioritizing the extracted business issues and presenting solutions, emotion analysis means for recognizing the user's emotions in real time and adjusting the content of the presentation, and means for providing the user with optimal solutions to business issues based on the collected data and emotion information. Thus, by combining data analysis and emotion recognition, optimal solutions can be provided for the user, improving work efficiency and reducing stress.

[0685] "Data Sources" means the various internal or external information sources used to provide information.

[0686] "Standardization" is the process of unifying data in various formats by converting them into a consistent format.

[0687] "Synthesis" is the act of combining data collected from multiple data sources into a single coherent data set.

[0688] A "machine learning algorithm" is a mathematical technique for automatically learning patterns from data and making predictions or classifications.

[0689] "Data analytics model" refers to a trained machine learning model used to derive insights from data.

[0690] A "user interface" is an interactive screen or tool that allows a user to directly interact with a system.

[0691] "Business issues" refer to various problems and obstacles that arise during the execution of business operations.

[0692] "Prioritization" is the process of determining the order of issues based on importance and urgency.

[0693] A "solution" is a specific means or process for solving a particular challenge or problem.

[0694] "Emotion analysis means" is a technology that recognizes emotions by analyzing a user's facial expressions, voice tone, text input, etc.

[0695] "Emotional history" refers to records and data regarding a user's past emotional states.

[0696] "Feedback" refers to the response or reaction a user receives from a system.

[0697] A system according to the present invention can be implemented using the following hardware and software.

[0698] Hardware

[0699] 1. Server: A high-performance server for collecting, integrating, and analyzing data.

[0700] 2. Camera: A high-resolution camera to capture the facial expressions of workers in real time.

[0701] 3. Microphone: Highly sensitive microphone for analyzing voice tones.

[0702] 4. Terminal: A device that provides a user interface, such as a smartphone, smart glasses, or tablet.

[0703] software

[0704] 1. DeepFace: A machine learning library for facial expression analysis.

[0705] 2. OpenCV: A library for image processing.

[0706] 3. TensorFlow: A library used to train and run machine learning models.

[0707] 4. GPT-3 API: An API for natural language generation.

[0708] 5. Web Application Framework: Building user interfaces using React.js and Django.

[0709] Data collection and analysis

[0710] The server collects, standardizes, and integrates data from multiple data sources within the factory, including sales data, employee performance data, and customer feedback data, all of which exist in various formats. The integrated data is then analyzed using TensorFlow, and a data analysis model is developed using machine learning algorithms.

[0711] Providing a user interface

[0712] The terminal provides an intuitive user interface as a web application that combines React.js and Django, allowing users to check analysis results and business issues via a browser.

[0713] Identifying business issues and presenting solutions

[0714] The server uses a data analysis model based on the collected data to extract and list business issues. It then prioritizes the issues based on their impact and urgency and presents solutions. Specific solutions include strengthening quality control and implementing employee training.

[0715] Use of sentiment analysis methods

[0716] The server uses DeepFace and OpenCV to analyze the user's facial expressions and voice tone in real time to recognize their emotional state. This allows the presented solutions and information to be dynamically adjusted according to the user's emotional state. If the user is feeling stressed, the presented solutions will be simplified and they will be encouraged to take a break if necessary.

[0717] Emotion history management and feedback

[0718] The server analyzes the user's emotional history and presents solutions at the optimal time based on past emotional patterns, thereby improving the user experience and work efficiency.

[0719] Specific examples

[0720] Example 1

[0721] If the worker is relaxed, provide detailed workflow optimization suggestions. Use the following prompt to generate detailed explanations:

[0722] Generate a detailed optimization strategy for the work flow in your factory when workers are relaxed.

[0723] Example 2

[0724] If a worker is feeling stressed, provide a simplified procedure and suggest a break. Use the following prompt to generate the simplified procedure:

[0725] Generate simplified work procedures when workers are stressed. Also suggest breaks for workers.

[0726] By implementing this invention, it becomes possible to perform optimal data analysis and present solutions that take into account the user's emotional state, which is expected to improve work efficiency and reduce stress.

[0727] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0728] Step 1:

[0729] The server collects, standardizes, and integrates data from multiple data sources within the factory. Input data includes sales data, employee performance data, and customer feedback data. The output is standardized integrated data. Specifically, information in different data formats is processed to unify it and compiled into a single data set.

[0730] Step 2:

[0731] The server uses the integrated data to develop a data analysis model using a machine learning algorithm (such as TensorFlow). The input data is the integrated dataset, and the output is a trained data analysis model. Specific operations include splitting the data into training data and test data, and training the model using the training data.

[0732] Step 3:

[0733] The terminal provides a user interface that users can operate intuitively. The input data is the analysis results and a list of business tasks, and the output is the interface screen provided to the user. Specifically, we will use React.js and Django to build a web application that users can access via a browser.

[0734] Step 4:

[0735] The server uses a data analysis model to extract business issues and list them. The input data is the output of the analysis model, and the output is a list of extracted business issues. Specifically, the analysis model detects quality issues and declines in employee performance from business data and lists them as issues.

[0736] Step 5:

[0737] The server prioritizes the extracted business issues based on their impact and urgency, and presents solutions. The input data is a list of business issues, and the output is a prioritized list of solutions. Specifically, it calculates a priority score and generates solutions from the most urgent and important issues.

[0738] Step 6:

[0739] The server uses emotion analysis tools (DeepFace, OpenCV, etc.) to analyze the user's facial expressions and voice tone in real time. The input data is the user's real-time video and audio, and the output is information about the user's emotional state. Specifically, it acquires data from the camera and microphone, analyzes facial expressions and voice tone, and determines the user's emotional state.

[0740] Step 7:

[0741] The device dynamically adjusts the content of the user interface based on the analysis results and the user's emotional state. The input data are the emotion analysis results and solutions to business problems, and the output is an adjusted user interface screen. Specifically, if the user is feeling stressed, the information is simplified, and if the user is relaxed, detailed solutions are presented.

[0742] Step 8:

[0743] The server analyzes the user's emotional history and presents solutions at the optimal time based on past emotional patterns. The input data is emotional history data, and the output is solutions presented at the appropriate time. Specifically, it analyzes the user's emotional patterns and presents feedback at the timing that elicits the user's optimal response.

[0744] Step 9:

[0745] The server uses a generative AI model (such as the GPT-3 API) to generate specific solutions and feedback messages based on the user's emotional state. Specific input prompts include "Generate a detailed optimization strategy for the factory workflow when workers are relaxed" and "Generate simplified work procedures when workers are stressed. Also suggest breaks for workers." The obtained prompts are provided to the user as appropriate solutions based on their emotional state.

[0746] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0747] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0748] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0749] [Third embodiment]

[0750] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0751] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0752] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0753] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0754] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0755] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0756] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0757] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0758] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0759] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0760] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0761] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0762] The present invention relates to a system for supporting data analysis and problem solving in in-house operations. Specific embodiments for carrying out the present invention will be described in detail below.

[0763] Internal data collection and integration

[0764] The server automatically collects data from various departments and related systems within the company. For example, it collects data in various formats, such as sales data, employee performance data, and customer feedback data. Because this data is often stored in different formats, the server consolidates and standardizes the collected data to centralize it.

[0765] Development of data analysis models using machine learning algorithms

[0766] The server uses the integrated data to develop a data analysis model using machine learning algorithms. This model is used to extract business issues and utilizes advanced algorithms such as random forests and neural networks. To develop the model, the data is divided into training data and test data, the model is trained using the training data, and its accuracy is evaluated using the test data.

[0767] Providing a user interface

[0768] The terminal provides a user interface that users can operate intuitively. For example, a web application-style interface can be used, allowing users to access and operate the system through a browser. The interface displays the results of data analysis, extracted business issues, and solutions to each issue.

[0769] Extracting and listing business issues

[0770] The server uses the developed data analysis model to extract business issues from the integrated data. For example, it identifies specific issues such as problems with product quality, issues related to declining employee performance, and customer complaints. The extracted issues are listed so that users can easily check them.

[0771] Prioritizing issues and proposing solutions

[0772] The server prioritizes the extracted business issues, determining the order based on the impact and urgency of the issues. Solutions are presented starting with the most important issues, and the server notifies the user through the user interface. Specific examples include strengthening quality control, conducting regular training, and optimizing resource allocation.

[0773] Solution review and implementation

[0774] The user examines the solutions presented by the server and selects a feasible one. To help the user put the selected solution into practice, the server also provides a detailed execution plan and information on the necessary resources. This allows the user to efficiently solve business problems.

[0775] As a specific example, if the server detects a sudden drop in sales of a particular product from sales data, it will extract the issue as a quality control problem and suggest a solution: "Review the quality control process." The user will then carefully examine the proposed solution, create an action plan, and apply it.

[0776] This invention makes it possible to make maximum use of in-house data, thereby improving business efficiency and preventing large-scale problems.

[0777] The processing flow will be explained below.

[0778] Step 1: Collect data

[0779] The server collects data from various departments within the company, such as sales data, employee performance data, customer feedback, etc. The data is available in various formats, including CSV files, Excel files, and JSON files.

[0780] The server uses APIs and database connections to collect data.

[0781] Step 2: Integrate and standardize data

[0782] The server consolidates the collected data and performs standardization processes to unify data in different formats, such as standardizing date formats and cleaning unnecessary data.

[0783] The server uses an ETL (Extract, Transform, Load) process to transform the data into an analyzable format so that all the data can be treated as a single unified dataset.

[0784] Step 3: Developing a data analysis model

[0785] The server uses the data combined in the previous step to apply machine learning algorithms, for example, random forests or neural networks to train models.

[0786] The server splits the data into training data and test data, evaluates the accuracy of the model, and adjusts the hyperparameters until a highly accurate model is obtained.

[0787] Step 4: Providing a User Interface

[0788] The terminal provides a user interface that allows users to intuitively operate the system, typically in the form of a web application.

[0789] The terminal displays a dashboard that allows users to view and operate the results of data analysis and extracted business issues.

[0790] Step 5: Identify and list business issues

[0791] The server uses a data analysis model to extract business issues from the integrated data, such as declining sales of a particular product or poor employee performance.

[0792] The server lists the extracted tasks and presents them to the user through a user interface.

[0793] Step 6: Prioritize issues and present solutions

[0794] The server prioritizes the extracted business issues based on their impact and urgency, and creates solutions starting with the most critical issues.

[0795] The server generates specific solutions for each problem and presents them to the user through a user interface, such as reviewing quality control processes or strengthening employee training.

[0796] Step 7: Refine and implement the solution

[0797] The user examines the solutions presented by the server, selects feasible solutions from the presented ones, and creates a specific implementation plan.

[0798] The server supports the allocation of detailed information and resources required to implement solutions, and helps users to efficiently solve problems based on this information.

[0799] By going through the above steps, the present invention realizes effective analysis of in-house data and rapid resolution of business issues. At each step, the server, terminal, and user work together to improve business efficiency and prevent large-scale problems.

[0800] Example 1

[0801] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0802] Many companies face challenges in collecting data from multiple internal data sources and utilizing it effectively. In particular, integrating data stored in different formats, identifying business issues, prioritizing those issues, and presenting optimal solutions are difficult. Furthermore, there is a need for a user interface that allows users to intuitively grasp the results of data analysis. The present invention aims to solve these challenges and provide a system that utilizes data efficiently and effectively.

[0803] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0804] In this invention, the server includes: means for automatically collecting and acquiring data from multiple internal data sources; means for converting the collected data into a unified format and integrating and standardizing the data; means for using the integrated data to build a data analysis model using a machine learning algorithm; means for providing a web-based interface that can be intuitively operated by a user; means for automatically extracting and listing business issues using the built data analysis model; means for prioritizing the extracted business issues and presenting solutions; and means for reviewing the presented solutions based on user feedback and providing an implementation plan for the selected solution. This makes it possible to efficiently collect and integrate internal data, effectively analyze it, extract business issues, prioritize them, present solutions, and provide them in a format that is intuitively understandable to the user.

[0805] "Data source" refers to the source of data provided by multiple departments and related systems within the company.

[0806] "Data collection" refers to the process of automatically obtaining the necessary data from internal data sources.

[0807] "Unified data format" refers to converting data stored in different formats into one standard format.

[0808] "Data integration" refers to the process of combining data collected from different data sources into one continuous data set.

[0809] "Data standardization" refers to the process of organizing integrated data into a consistent format.

[0810] "Machine learning algorithm" refers to the statistical techniques and computational methods used to build data analysis models.

[0811] "Data analysis model" refers to a model built using machine learning algorithms to extract specific business issues based on integrated and standardized data.

[0812] "Web-based interface" refers to a user interface accessible through a browser.

[0813] "Business issue extraction" refers to the process of using a data analysis model to identify issues related to internal business operations.

[0814] "Listing up" refers to compiling the extracted business issues in a list format.

[0815] "Prioritization" refers to setting the order in which extracted business issues should be addressed based on their impact and urgency.

[0816] "Providing solutions" refers to showing specific measures for the extracted business issues.

[0817] "User feedback" refers to the process of collecting opinions and ratings from users.

[0818] "Scrutiny" refers to examining the proposed solution in detail and assessing its validity.

[0819] "Providing an action plan" refers to showing the steps and resources required to specifically implement the solution selected by the user.

[0820] The present invention relates to a system for supporting data analysis and problem solving in in-house operations. Specific embodiments for carrying out the present invention will be described in detail below.

[0821] Internal data collection and integration

[0822] The server automatically collects data from various departments and related systems within the company. For example, it obtains sales data, employee performance data, and customer feedback data through a database management system (DBMS) or RESTful API. This data is often stored in different formats, so the server uses a data conversion tool (Python script) to convert this data into a unified format (CSV or JSON) and standardize it.

[0823] Development of data analysis models using machine learning algorithms

[0824] The server uses the integrated data to build a data analysis model using machine learning algorithms. This model is used to extract business issues, and random forest or neural network models are developed using Python and the TensorFlow or Scikit-learn library. The data is divided into training data and test data, and the training data is used to train the model, and the test data is used to evaluate the accuracy of the model.

[0825] Providing a user interface

[0826] The terminal provides a user interface that users can operate intuitively. Specifically, a web-based interface built with React.js is used. Users can access the system through a browser and view the results of data analysis and extracted business issues. The interface is created using Bootstrap and Material-UI.

[0827] Extracting and listing business issues

[0828] The server uses the developed data analysis model to extract business issues from the integrated data. For example, it identifies specific issues such as problems with product quality, issues related to declining employee performance, and customer complaints. These issues are saved in JSON format and notified to the user interface via a RESTful API. For example, if the server detects from sales data that sales of a particular product have dropped sharply, it will extract the issue as a problem related to the quality of that product and suggest a solution: "reviewing the quality control process."

[0829] Prioritizing issues and proposing solutions

[0830] The server prioritizes the extracted business issues, setting the order based on impact and urgency, and presenting solutions starting with the most important issues. For example, it might suggest solutions such as "reviewing the quality control process" or "conducting regular training." This information is also displayed on the user interface via a RESTful API.

[0831] Solution review and implementation

[0832] The user examines the solutions presented by the server and selects a feasible one. The selected solution is then provided along with a detailed implementation plan. For example, if "reviewing the quality control process" is selected as a solution, specific considerations, required resources, and a schedule are presented.

[0833] Specific examples

[0834] If the server detects from sales data that sales of a particular product have dropped sharply, it will identify the issue as a problem with the quality of that product and suggest a "review of the quality control process" as a solution.

[0835] Example of input prompt for generative AI model

[0836] Here are some example prompts to input to a generative AI model:

[0837] "Use departmental performance data to identify factors associated with poor employee performance."

[0838] "Analyze customer feedback data and extract key complaints."

[0839] "Use random forest to build a product sales prediction model."

[0840] This invention makes it possible to make maximum use of in-house data, thereby improving business efficiency and preventing large-scale problems.

[0841] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0842] Step 1: Collect data

[0843] The server automatically collects data from each department and related systems within the company. It uses a database management system (DBMS) and RESTful APIs to obtain sales data, employee performance data, and customer feedback data. This data is collected in a temporary storage area within the server.

[0844] Specifically, a Python script runs periodically, sends an API request, and retrieves the latest data, which is then converted to CSV format and saved.

[0845] Input: API request, database query

[0846] Output: CSV format data file

[0847] Step 2: Integrate and standardize data

[0848] The server converts the collected data into a unified format, consolidating and standardizing the data, and converting data from different formats into a unified schema for the SQL database.

[0849] Specifically, a data conversion Python script is run to convert each dataset into a unified format (e.g., all numeric data is rounded to two decimal places), and the converted data is imported into a MySQL database.

[0850] Input: CSV format data file

[0851] Output: Data in a unified format (stored in an SQL database)

[0852] Step 3: Building a machine learning model

[0853] The server uses the integrated data to build machine learning models, developing random forest and neural network models using Python, TensorFlow, and Scikit-learn.

[0854] Specifically, the server loads the data using a Python script and splits it into training and test data using SciPy. Next, it builds a neural network model using TensorFlow and trains it using the training data. The accuracy of the model is evaluated using the test data, and the models that are confirmed to have high accuracy are saved.

[0855] Input: Unified format data (SQL database)

[0856] Output: A trained machine learning model

[0857] Step 4: Providing a User Interface

[0858] The terminal provides an intuitive user interface, allowing users to view the results of data analysis and extracted business issues through a web-based interface built with React.js.

[0859] Specifically, when a user opens a web browser and accesses a specific URL, the device receives HTML, CSS, and JavaScript files from the server and displays information dynamically constructed by React.js.

[0860] Input: User's browser access

[0861] Output: Web page displaying analysis results and business issues

[0862] Step 5: Identify and list business issues

[0863] The server uses the developed data analysis model to extract business issues from the integrated data, identifying and listing issues such as product quality problems, poor employee performance, and customer dissatisfaction.

[0864] Specifically, the server periodically re-analyzes the integrated data and extracts business issues using the stored machine learning model. The extracted issues are saved in JSON format and delivered to the front end via a RESTful API.

[0865] Input: Integrated data, machine learning model

[0866] Output: Extracted business issues (saved in JSON format)

[0867] Step 6: Prioritize issues and present solutions

[0868] The server prioritizes the extracted business issues based on their impact and urgency, and presents solutions starting with the most important issues.

[0869] Specifically, the system runs a prioritization algorithm to calculate an impact score for each issue, after which the solution is displayed in the user interface.

[0870] Input: Extracted business issues (JSON format)

[0871] Output: Prioritized issues and solutions

[0872] Step 7: Refine and implement the solution

[0873] The user reviews the proposed solutions and selects a viable one, which is then provided with a detailed implementation plan.

[0874] Specifically, the user selects a solution on the user interface and sends that information to the server. Based on the selected solution, the server generates specific study items, required resources, and a schedule, and displays them on the user interface.

[0875] Input: User's solution selection

[0876] Output: Detailed execution plan

[0877] (Application example 1)

[0878] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0879] Modern factories require real-time monitoring of each robot's performance and error status, and the ability to quickly address these issues. However, achieving this requires a system that can efficiently collect and analyze large amounts of data and provide users with appropriate solutions. Conventional systems take time to integrate and analyze data, identify issues, and present solutions, resulting in delays in providing appropriate solutions. Another challenge is providing an interface that is easy for users to use.

[0880] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0881] In this invention, the server includes: means for collecting, standardizing, and integrating data from multiple data sources within a company; means for using the integrated data to develop a data analysis model using a machine learning algorithm; means for providing a user interface that can be intuitively operated by a user; means for extracting and listing business issues using the data analysis model; means for prioritizing the extracted business issues and proposing solutions; means for examining the proposed solutions together with the user and implementing feasible ones; means for collecting robot data in real time; and means for analyzing the collected data, extracting issues, prioritizing them, and displaying solutions on a smartphone screen. This makes it possible to monitor robot performance and error status in a factory in real time and quickly and effectively resolve issues.

[0882] Key Word Definitions

[0883] "Data source" is a general term for a system or device that provides data.

[0884] "Standardization" is the process of converting data of different formats into a consistent format.

[0885] "Integration" means combining data obtained from multiple different data sources into a single data set.

[0886] A "machine learning algorithm" is a program or method that learns patterns from data and automatically performs tasks such as prediction and categorization.

[0887] A "data analysis model" is a specific computational model constructed using machine learning algorithms for analyzing and predicting data.

[0888] A "user interface" is a visual and operational interface that allows a user to operate a system or application.

[0889] A "business issue" is a specific problem or obstacle that needs to be solved in the operations or work processes of a company or organization.

[0890] "Priority" means determining the order in which multiple issues or tasks should be handled based on their importance and urgency.

[0891] A "solution" is a specific action or method that should be taken to address a specific problem or issue.

[0892] "Real-time collection" is the process of collecting data immediately without delay.

[0893] A "smartphone screen" is a smartphone display and an interface for displaying applications and information.

[0894] "Robot data" refers to operational data such as performance and error information obtained from robots operating in factories.

[0895] MODE FOR CARRYING OUT THE INVENTION

[0896] The present invention provides a system for monitoring the performance of robots in a factory and the occurrence of errors in real time, and for responding quickly and effectively. Specific embodiments for carrying out the present invention will be described in detail below.

[0897] Configuration and Overview

[0898] The system consists of the following elements:

[0899] 1. Data collection and integration:

[0900] The server automatically collects data from multiple data sources within the factory. Specifically, this includes operation data, performance data, and error occurrence information for each robot. Because this data is stored in different formats, the server standardizes and centralizes the data.

[0901] 2. Development of data analysis models using machine learning algorithms:

[0902] The server uses the integrated data to develop a data analysis model using a machine learning algorithm (e.g., RandomForestClassifier). This model detects robot anomalies and identifies operational issues. It also splits the data into training and test data, trains the model, and evaluates its accuracy.

[0903] 3. Providing the user interface:

[0904] The terminal (e.g., a smartphone) provides a user interface that can be operated intuitively by the user. Specifically, a dashboard-style interface is considered, allowing the user to access the system through the smartphone screen and check the analysis results and solutions.

[0905] 4. Extract and list business issues:

[0906] The server uses the developed data analysis model to extract business issues from the integrated data. The extracted issues are listed so that users can easily check them. For example, they may include the cause of a particular robot's shutdown or frequent errors.

[0907] 5. Prioritizing issues and proposing solutions:

[0908] The server prioritizes the extracted business issues and presents solutions based on the impact and urgency of the issues. For example, this could include the timing of preventive maintenance or part replacement for a specific robot.

[0909] 6. Solution Examination and Implementation:

[0910] The user can then examine the solutions presented by the server and implement the most appropriate one. Specifically, the user can check the details of the solution and the implementation procedure through the user interface.

[0911] Hardware and Software

[0912] Hardware: Smartphone

[0913] Software: Python, requests library, scikit-learn

[0914] Specific examples

[0915] For example, if a particular robot in a factory stops working multiple times over a certain period of time, the system will identify the cause and suggest preventative maintenance. Users can view the following information on their smartphone screen:

[0916] Prompt Sentence Examples

[0917] "Factory robot 22 has stopped working three times in one week. Please provide possible issues that could be causing the downtime and solutions."

[0918] This makes it possible to monitor robot performance and error conditions within the factory in real time and resolve issues quickly and effectively.

[0919] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0920] Step 1:

[0921] The server collects operational data, performance data, and error information from each robot in the factory in real time. Because this data is stored in different formats, the server standardizes and centralizes the data.

[0922] Input: Operation data, performance data, and error information sent from each robot

[0923] Output: Standardized and unified dataset

[0924] Step 2:

[0925] The server uses the standardized data to develop a data analysis model using a machine learning algorithm (e.g., RandomForestClassifier). The model is divided into training data and test data, trained, and its accuracy is evaluated.

[0926] Input: Standardized dataset

[0927] Output: A trained data analysis model

[0928] Step 3:

[0929] The server uses a trained data analysis model to extract robot anomalies and operational issues from the integrated data, identifying and listing information according to the type and situation of the issue.

[0930] Input: Trained data analysis model, standardized dataset

[0931] Output: A list of extracted anomalies and business issues

[0932] Step 4:

[0933] The server prioritizes the extracted business issues and presents solutions to each issue using machine learning models as a reference. Priorities are determined based on the importance and urgency of the issues.

[0934] Input: List of anomalies and business issues

[0935] Output: A prioritized list of issues and solutions

[0936] Step 5:

[0937] The terminal displays the prioritized list of issues and solutions sent from the server to the user through a user interface, allowing the user to intuitively operate the terminal and check detailed information.

[0938] Input: A prioritized list of issues and solutions sent from the server

[0939] Output: Analysis results and solutions displayed on the smartphone screen

[0940] Step 6:

[0941] Users can examine the presented solutions, select the most appropriate one, and put it into action. Specific steps and information on the necessary resources are also provided, allowing for efficient problem-solving.

[0942] Input: Solution displayed on smartphone screen

[0943] Output: The selected solution and its implementation plan

[0944] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0945] The present invention combines a system that supports data analysis and problem solving in in-house operations with an emotion engine that recognizes user emotions. Specific embodiments for carrying out the present invention will be described in detail below.

[0946] Internal data collection and integration

[0947] The server automatically collects data from various departments and related systems within the company, such as sales data, employee performance data, customer feedback data, etc. Because the data exists in various formats, the server standardizes and consolidates the collected data.

[0948] Development of data analysis models using machine learning algorithms

[0949] The server uses machine learning algorithms to develop a data analysis model based on the integrated data. To develop the model, the data is divided into training data and test data, and the model is trained using the training data. The accuracy of the model is evaluated using the test data, and the model with the highest accuracy is selected.

[0950] Providing a user interface

[0951] The terminal provides a user interface that can be operated intuitively by the user. A web application-style interface is provided, and users can access the system via a browser and check analysis results and business issues.

[0952] Extracting and listing business issues

[0953] The server uses a data analysis model to extract business issues from the integrated data. For example, it detects and lists problems related to product quality or poor employee performance. The extracted issues are then provided to the user through a user interface.

[0954] Prioritizing issues and proposing solutions

[0955] The server prioritizes the extracted business issues based on their impact and urgency. Solutions are generated for the most important issues first and are notified to the user through the user interface. Specific solutions include strengthening quality control and implementing employee training.

[0956] Incorporating an emotion engine

[0957] One of the features of the present invention is that it incorporates an emotion engine to recognize the user's emotions in real time and adjust the analysis results and presented solutions according to the user's emotional state. The emotion engine analyzes emotions from the user's facial expressions, voice tone, text input, etc.

[0958] Dynamic adjustment of emotion-based interfaces

[0959] The device dynamically adjusts the user interface based on data obtained from the emotion engine. For example, if the user is stressed, it will simplify the solution suggestions and provide flexible support. If the user is relaxed, it will provide detailed information to support decision-making.

[0960] Emotion history analysis

[0961] The server analyzes the user's emotional history and presents solutions at the optimal time based on past emotional patterns, enabling appropriate feedback that takes into account the user's emotional state.

[0962] For example, if sales data detects a sudden drop in sales of a particular product, the issue is extracted as a quality control problem. If the emotion engine recognizes that the user's stress level is high, the solution is simplified and a simple suggestion such as "review the quality control process" is made. If the user is relaxed, a detailed implementation plan is presented.

[0963] Through the above steps, the present invention combines data analysis and emotion recognition to provide optimal solutions for users, improving work efficiency and reducing stress.

[0964] The processing flow will be explained below.

[0965] Step 1: Collect data

[0966] The server collects data from various departments and related systems within the company, including sales data, employee performance data, and customer feedback data.

[0967] I won't provide any code examples, but the server retrieves data using an API or database connection.

[0968] Step 2: Integrate and standardize data

[0969] The server consolidates the collected data and performs standardization processes, such as standardizing date formats and normalizing text data.

[0970] The server applies an ETL (Extract, Transform, Load) process to produce a unified dataset, which brings the data into a single, analyzable format.

[0971] Step 3: Developing a data analysis model

[0972] The server uses the combined data to develop data analysis models using machine learning algorithms, such as random forests and neural networks.

[0973] The server splits the data into training data and test data, trains the model using the training data, and evaluates the model on the test data to measure accuracy.

[0974] Step 4: Providing a User Interface

[0975] The terminal provides a user interface that can be operated intuitively by the user. The interface is in the form of a web application, and the user accesses it from a browser.

[0976] The interface on the terminal displays the results of data analysis and extracted business issues, which the user uses to interact with the system.

[0977] Step 5: Identify and list business issues

[0978] The server uses data analysis models to extract specific business issues from the integrated data, such as declining sales of a particular product, poor employee performance, or customer dissatisfaction.

[0979] The extracted issues are provided to the user as a list via a user interface, and the user checks this list to identify issues that require action.

[0980] Step 6: Prioritize the issues and present solutions

[0981] The server prioritizes the extracted business issues based on their impact and urgency. The impact of the issues is evaluated using a data analysis model.

[0982] The server generates specific solutions in order of priority and presents them to the user through a user interface. For example, it may suggest solutions such as "reviewing the quality control process" or "strengthening employee training."

[0983] Step 7: Recognizing user emotions with the emotion engine

[0984] The server analyzes the user's emotional state based on the user's emotional data acquired from the terminal (for example, facial expressions, voice tone, and analysis results of text input).

[0985] The emotion engine recognizes the user's emotions in real time, so if the user is feeling stressed, for example, this is fed back to the system.

[0986] Step 8: Dynamically adjust the interface based on emotions

[0987] The device dynamically adjusts the user interface based on data from the emotion engine, simplifying suggested solutions and providing more support when the user is feeling stressed.

[0988] For example, you can omit the details of the solution and show only the key points, or change the color scheme and layout to reduce visual strain.

[0989] Step 9: Analyze emotion history and provide solutions at the optimal time

[0990] The server analyzes the user's past emotional history and understands their emotional patterns, which allows it to present solutions at the optimal time.

[0991] Present detailed solutions and additional information when the user's emotional state is stable, which increases the solution's acceptability.

[0992] Step 10: Refine and implement the solution

[0993] The user reviews the proposed solutions and selects a feasible one, and can take into account the emotion engine's feedback when selecting a solution.

[0994] The server provides detailed plans and resource information for implementing the selected solutions, allowing users to quickly create action plans based on the information provided and solve business problems.

[0995] Through these steps, the present invention improves work efficiency and reduces stress by taking into account the user's emotions. The server, terminals, and users work together to provide a more effective data analysis and problem-solving process.

[0996] Example 2

[0997] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0998] In recent years, companies have placed increasing importance on identifying and resolving problems through business data analysis. However, existing systems face many challenges. For example, they lack the ability to easily collect and integrate data from multiple data sources, the interfaces for effectively utilizing analysis results are not intuitive, the analytical models are not accurate enough, and it takes time to prioritize business issues and present solutions. Furthermore, they present uniform feedback and solutions without considering the user's emotional state, which can increase user stress and reduce work efficiency.

[0999] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1000] In this invention, the server includes a means for collecting, standardizing, and integrating data from multiple internal data sources, a means for using the integrated data to develop a data analysis model using a machine learning algorithm, and a means for providing a user interface that can be intuitively operated by users. This enables data to be automatically collected from each department and related system and integrated in a consistent format. Furthermore, high-precision data analysis using the machine learning model enables rapid identification of business issues and the presentation of effective solutions. Furthermore, by including a means for recognizing user emotions in real time and dynamically adjusting the interface based on those emotions, the server provides optimal feedback and solutions to individual users, improving work efficiency and reducing stress.

[1001] A "data source" is a source of raw data provided by multiple departments and related systems within a company.

[1002] "Standardization" is the process of converting collected data into a consistent format and structure and integrating it.

[1003] "Integration" means combining data collected from multiple data sources into a single dataset.

[1004] A "machine learning algorithm" is a computational method that learns patterns and regularities from large amounts of data and uses them to make predictions and classifications.

[1005] A "data analysis model" is a computational model developed using machine learning algorithms to extract useful information from data.

[1006] A "user interface" is an interface that includes visual and operational elements through which a user interacts with a system.

[1007] "Business issues" are problems or areas for improvement that need to be resolved in the company's business processes.

[1008] "Solutions" are specific measures and action plans presented for the identified business issues.

[1009] An "emotion engine" is a software or hardware system that analyzes emotions from a user's facial expressions, tone of voice, text input, etc.

[1010] "Dynamic adjustment" refers to changing the behavior of an interface or system in real time according to the user's current state and environment.

[1011] "Emotion history" is a record of the user's past emotional states and the saved data.

[1012] "Analysis" is the process of examining collected data and information in detail to find meaning and patterns.

[1013] The present invention combines a system for supporting data analysis and problem solving in in-house operations with an emotion engine that recognizes user emotions. The following describes in detail the embodiments of the present invention.

[1014] The server automatically collects data from multiple internal data sources, such as sales data from each department, employee performance data, and customer feedback data, via APIs and database queries. The collected data is standardized and integrated using Python scripts and SQL.

[1015] Next, the server develops an analytical model using machine learning algorithms based on the integrated data. It uses open-source libraries such as Scikit-learn and TensorFlow to split the data into training data and test data. The model is trained using the training data and evaluated using the test data. Evaluation metrics include precision, recall, and F1 score.

[1016] The terminal provides an intuitive user interface, which is provided in the form of a web application developed with React and Vue.js and can be accessed via a browser. The interface displays a data dashboard and a list of business issues, allowing users to view analysis results and issue details.

[1017] The server uses a data analysis model to extract and list business issues. For example, it detects product quality problems and declining employee performance. The extracted issues are prioritized based on their impact and urgency, and solutions are generated. The generated solutions are presented to the user through a user interface. Specific solutions include strengthening quality control and implementing employee training.

[1018] One of the features of this invention is the incorporation of an emotion engine, which can recognize the user's emotions in real time. The emotion engine uses facial expression analysis tools such as OpenCV and natural language analysis engines to analyze emotions from voice tone and text input. Based on the analyzed emotion data, the interface content and presented solutions are dynamically adjusted.

[1019] The device dynamically adjusts the user interface based on data from the emotion engine. For example, if the device detects that the user is feeling stressed, it will simplify the solutions it presents and flexibly change the support it provides. Conversely, if the user is relaxed, it will provide more detailed information to help them make decisions.

[1020] The server also analyzes the user's emotional history and presents solutions at the optimal time, making it possible to provide effective feedback to the user. As a specific example, if sales data shows a sudden drop in sales of a particular product, the server will identify this as a quality control issue. If the emotion engine recognizes that the user's stress level is high, it will present a simple solution such as "reviewing the quality control process." On the other hand, if the user is relaxed, it will provide a detailed implementation plan.

[1021] An example of a prompt to be input to the generative AI model is, "Please summarize a use case for this system's project management functionality. For example, please explain how it helped you in a particular project, including examples of specific challenges and solutions."

[1022] Through the above steps, the present invention combines data analysis and emotion recognition to provide optimal solutions for users, improving work efficiency and reducing stress.

[1023] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1024] Step 1:

[1025] The server collects data from multiple data sources within the company. In this step, sales data, employee performance data, customer feedback data, etc. are obtained through APIs and database queries. As input, it receives raw data from each data source, and as output, it obtains a raw dataset before standardization. Specifically, the server runs periodically scheduled jobs and sends instructions to retrieve data.

[1026] Step 2:

[1027] The server standardizes and consolidates the collected data. It receives raw data in various formats (CSV, JSON, SQL, etc.) as input and generates a unified dataset in a unified format as output. Specifically, the server uses Python scripts and Pandas to convert and standardize data. For example, it handles missing values ​​in the data, unifies different formats, and extracts necessary fields.

[1028] Step 3:

[1029] The server develops a data analysis model based on the integrated data. It receives the integrated dataset as input and generates a trained model as output. Specifically, the server uses Scikit-learn or TensorFlow to split the data into training data and test data, and then trains the model using the training data. During this process, it also performs cross-validation and hyperparameter tuning.

[1030] Step 4:

[1031] The terminal provides the user interface. It receives GUI components and user browser requests as input, and displays an operable interface as output. Specifically, the terminal develops a web application using React or Vue.js to visualize data and set up an operation panel. For example, it dynamically displays analysis results or a list of business issues on a dashboard.

[1032] Step 5:

[1033] The server uses a data analysis model to extract and list business issues. It uses the trained model and the integrated dataset as input and generates a list of issues as output. Specifically, the server inputs data into the analysis model and detects various business issues (e.g., quality issues, performance degradation, customer dissatisfaction, etc.). The detected issues are stored in a database.

[1034] Step 6:

[1035] The server prioritizes the extracted business issues and generates and presents solutions. Based on the list of issues and a prioritization algorithm as input, it generates a prioritized list of issues and their corresponding solutions as output. Specifically, it scores issues based on their impact and urgency, and generates optimal solutions. These solutions are presented to the user through a user interface.

[1036] Step 7:

[1037] The server uses an emotion engine to obtain the user's emotional data in real time. It receives the user's facial expression images, voice data, and text input as input, and generates analyzed emotional data as output. Specifically, it analyzes facial expressions using tools such as OpenCV, and also performs voice tone analysis and text analysis in parallel.

[1038] Step 8:

[1039] The device dynamically adjusts the user interface based on the data obtained from the emotion engine. It receives analyzed emotion data as input and provides an adjusted interface as output. Specifically, if the user is feeling stressed, it reduces the complexity of the interface and presents simple solutions. On the other hand, if the user is relaxed, it provides detailed information to support decision-making.

[1040] Step 9:

[1041] The server analyzes the user's emotional history and presents solutions at the optimal time. It receives past emotional data as input and presents solutions at the optimal time based on the emotional patterns as output. Specifically, the server performs time series analysis and extracts patterns from the emotional history. This makes it possible to provide appropriate feedback that takes into account the user's past emotional state.

[1042] (Application example 2)

[1043] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1044] Conventional in-house work support systems focused on identifying work issues and proposing solutions based on data analysis, but because they did not take into account the user's emotional state, they had the problem of increasing stress and strain in the actual work environment.In addition, because they did not provide flexible feedback or adjust the interface according to the user's emotional state, it was difficult to improve the user experience.

[1045] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1046] In this invention, the server includes means for collecting, standardizing, and integrating data from multiple data sources within the company, means for using the integrated data and a machine learning algorithm to develop a data analysis model, means for providing a user interface that can be intuitively operated by a user, means for extracting and listing business issues using the data analysis model, means for prioritizing the extracted business issues and presenting solutions, emotion analysis means for recognizing the user's emotions in real time and adjusting the content of the presentation, and means for providing the user with optimal solutions to business issues based on the collected data and emotion information. Thus, by combining data analysis and emotion recognition, optimal solutions can be provided for the user, improving work efficiency and reducing stress.

[1047] "Data Sources" means the various internal or external information sources used to provide information.

[1048] "Standardization" is the process of unifying data in various formats by converting them into a consistent format.

[1049] "Synthesis" is the act of combining data collected from multiple data sources into a single coherent data set.

[1050] A "machine learning algorithm" is a mathematical technique for automatically learning patterns from data and making predictions or classifications.

[1051] "Data analytics model" refers to a trained machine learning model used to derive insights from data.

[1052] A "user interface" is an interactive screen or tool that allows a user to directly interact with a system.

[1053] "Business issues" refer to various problems and obstacles that arise during the execution of business operations.

[1054] "Prioritization" is the process of determining the order of issues based on importance and urgency.

[1055] A "solution" is a specific means or process for solving a particular challenge or problem.

[1056] "Emotion analysis means" is a technology that recognizes emotions by analyzing a user's facial expressions, voice tone, text input, etc.

[1057] "Emotional history" refers to records and data regarding a user's past emotional states.

[1058] "Feedback" refers to the response or reaction a user receives from a system.

[1059] A system according to the present invention can be implemented using the following hardware and software.

[1060] Hardware

[1061] 1. Server: A high-performance server for collecting, integrating, and analyzing data.

[1062] 2. Camera: A high-resolution camera to capture the facial expressions of workers in real time.

[1063] 3. Microphone: Highly sensitive microphone for analyzing voice tones.

[1064] 4. Terminal: A device that provides a user interface, such as a smartphone, smart glasses, or tablet.

[1065] software

[1066] 1. DeepFace: A machine learning library for facial expression analysis.

[1067] 2. OpenCV: A library for image processing.

[1068] 3. TensorFlow: A library used to train and run machine learning models.

[1069] 4. GPT-3 API: An API for natural language generation.

[1070] 5. Web Application Framework: Building user interfaces using React.js and Django.

[1071] Data collection and analysis

[1072] The server collects, standardizes, and integrates data from multiple data sources within the factory, including sales data, employee performance data, and customer feedback data, all of which exist in various formats. The integrated data is then analyzed using TensorFlow, and a data analysis model is developed using machine learning algorithms.

[1073] Providing a user interface

[1074] The terminal provides an intuitive user interface as a web application that combines React.js and Django, allowing users to check analysis results and business issues via a browser.

[1075] Identifying business issues and presenting solutions

[1076] The server uses a data analysis model based on the collected data to extract and list business issues. It then prioritizes the issues based on their impact and urgency and presents solutions. Specific solutions include strengthening quality control and implementing employee training.

[1077] Use of sentiment analysis methods

[1078] The server uses DeepFace and OpenCV to analyze the user's facial expressions and voice tone in real time to recognize their emotional state. This allows the presented solutions and information to be dynamically adjusted according to the user's emotional state. If the user is feeling stressed, the presented solutions will be simplified and they will be encouraged to take a break if necessary.

[1079] Emotion history management and feedback

[1080] The server analyzes the user's emotional history and presents solutions at the optimal time based on past emotional patterns, thereby improving the user experience and work efficiency.

[1081] Specific examples

[1082] Example 1

[1083] If the worker is relaxed, provide detailed workflow optimization suggestions. Use the following prompt to generate detailed explanations:

[1084] Generate a detailed optimization strategy for the work flow in your factory when workers are relaxed.

[1085] Example 2

[1086] If a worker is feeling stressed, provide a simplified procedure and suggest a break. Use the following prompt to generate the simplified procedure:

[1087] Generate simplified work procedures when workers are stressed. Also suggest breaks for workers.

[1088] By implementing this invention, it becomes possible to perform optimal data analysis and present solutions that take into account the user's emotional state, which is expected to improve work efficiency and reduce stress.

[1089] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1090] Step 1:

[1091] The server collects, standardizes, and integrates data from multiple data sources within the factory. Input data includes sales data, employee performance data, and customer feedback data. The output is standardized integrated data. Specifically, information in different data formats is processed to unify it and compiled into a single data set.

[1092] Step 2:

[1093] The server uses the integrated data to develop a data analysis model using a machine learning algorithm (such as TensorFlow). The input data is the integrated dataset, and the output is a trained data analysis model. Specific operations include splitting the data into training data and test data, and training the model using the training data.

[1094] Step 3:

[1095] The terminal provides a user interface that users can operate intuitively. The input data is the analysis results and a list of business tasks, and the output is the interface screen provided to the user. Specifically, we will use React.js and Django to build a web application that users can access via a browser.

[1096] Step 4:

[1097] The server uses a data analysis model to extract business issues and list them. The input data is the output of the analysis model, and the output is a list of extracted business issues. Specifically, the analysis model detects quality issues and declines in employee performance from business data and lists them as issues.

[1098] Step 5:

[1099] The server prioritizes the extracted business issues based on their impact and urgency, and presents solutions. The input data is a list of business issues, and the output is a prioritized list of solutions. Specifically, it calculates a priority score and generates solutions from the most urgent and important issues.

[1100] Step 6:

[1101] The server uses emotion analysis tools (DeepFace, OpenCV, etc.) to analyze the user's facial expressions and voice tone in real time. The input data is the user's real-time video and audio, and the output is information about the user's emotional state. Specifically, it acquires data from the camera and microphone, analyzes facial expressions and voice tone, and determines the user's emotional state.

[1102] Step 7:

[1103] The device dynamically adjusts the content of the user interface based on the analysis results and the user's emotional state. The input data are the emotion analysis results and solutions to business problems, and the output is an adjusted user interface screen. Specifically, if the user is feeling stressed, the information is simplified, and if the user is relaxed, detailed solutions are presented.

[1104] Step 8:

[1105] The server analyzes the user's emotional history and presents solutions at the optimal time based on past emotional patterns. The input data is emotional history data, and the output is solutions presented at the appropriate time. Specifically, it analyzes the user's emotional patterns and presents feedback at the timing that elicits the user's optimal response.

[1106] Step 9:

[1107] The server uses a generative AI model (such as the GPT-3 API) to generate specific solutions and feedback messages based on the user's emotional state. Specific input prompts include "Generate a detailed optimization strategy for the factory workflow when workers are relaxed" and "Generate simplified work procedures when workers are stressed. Also suggest breaks for workers." The obtained prompts are provided to the user as appropriate solutions based on their emotional state.

[1108] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1109] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1110] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1111] [Fourth embodiment]

[1112] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1113] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1114] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1115] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1116] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1117] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1118] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1119] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1120] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1121] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1122] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1123] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1124] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1125] The present invention relates to a system for supporting data analysis and problem solving in in-house operations. Specific embodiments for carrying out the present invention will be described in detail below.

[1126] Internal data collection and integration

[1127] The server automatically collects data from various departments and related systems within the company. For example, it collects data in various formats, such as sales data, employee performance data, and customer feedback data. Because this data is often stored in different formats, the server consolidates and standardizes the collected data to centralize it.

[1128] Development of data analysis models using machine learning algorithms

[1129] The server uses the integrated data to develop a data analysis model using machine learning algorithms. This model is used to extract business issues and utilizes advanced algorithms such as random forests and neural networks. To develop the model, the data is divided into training data and test data, the model is trained using the training data, and its accuracy is evaluated using the test data.

[1130] Providing a user interface

[1131] The terminal provides a user interface that users can operate intuitively. For example, a web application-style interface can be used, allowing users to access and operate the system through a browser. The interface displays the results of data analysis, extracted business issues, and solutions to each issue.

[1132] Extracting and listing business issues

[1133] The server uses the developed data analysis model to extract business issues from the integrated data. For example, it identifies specific issues such as problems with product quality, issues related to declining employee performance, and customer complaints. The extracted issues are listed so that users can easily check them.

[1134] Prioritizing issues and proposing solutions

[1135] The server prioritizes the extracted business issues, determining the order based on the impact and urgency of the issues. Solutions are presented starting with the most important issues, and the server notifies the user through the user interface. Specific examples include strengthening quality control, conducting regular training, and optimizing resource allocation.

[1136] Solution review and implementation

[1137] The user examines the solutions presented by the server and selects a feasible one. To help the user put the selected solution into practice, the server also provides a detailed execution plan and information on the necessary resources. This allows the user to efficiently solve business problems.

[1138] As a specific example, if the server detects a sudden drop in sales of a particular product from sales data, it will extract the issue as a quality control problem and suggest a solution: "Review the quality control process." The user will then carefully examine the proposed solution, create an action plan, and apply it.

[1139] This invention makes it possible to make maximum use of in-house data, thereby improving business efficiency and preventing large-scale problems.

[1140] The processing flow will be explained below.

[1141] Step 1: Collect data

[1142] The server collects data from various departments within the company, such as sales data, employee performance data, customer feedback, etc. The data is available in various formats, including CSV files, Excel files, and JSON files.

[1143] The server uses APIs and database connections to collect data.

[1144] Step 2: Integrate and standardize data

[1145] The server consolidates the collected data and performs standardization processes to unify data in different formats, such as standardizing date formats and cleaning unnecessary data.

[1146] The server uses an ETL (Extract, Transform, Load) process to transform the data into an analyzable format so that all the data can be treated as a single unified dataset.

[1147] Step 3: Developing a data analysis model

[1148] The server uses the data combined in the previous step to apply machine learning algorithms, for example, random forests or neural networks to train models.

[1149] The server splits the data into training data and test data, evaluates the accuracy of the model, and adjusts the hyperparameters until a highly accurate model is obtained.

[1150] Step 4: Providing a User Interface

[1151] The terminal provides a user interface that allows users to intuitively operate the system, typically in the form of a web application.

[1152] The terminal displays a dashboard that allows users to view and operate the results of data analysis and extracted business issues.

[1153] Step 5: Identify and list business issues

[1154] The server uses a data analysis model to extract business issues from the integrated data, such as declining sales of a particular product or poor employee performance.

[1155] The server lists the extracted tasks and presents them to the user through a user interface.

[1156] Step 6: Prioritize issues and present solutions

[1157] The server prioritizes the extracted business issues based on their impact and urgency, and creates solutions starting with the most critical issues.

[1158] The server generates specific solutions for each problem and presents them to the user through a user interface, such as reviewing quality control processes or strengthening employee training.

[1159] Step 7: Refine and implement the solution

[1160] The user examines the solutions presented by the server, selects feasible solutions from the presented ones, and creates a specific implementation plan.

[1161] The server supports the allocation of detailed information and resources required to implement solutions, and helps users to efficiently solve problems based on this information.

[1162] By going through the above steps, the present invention realizes effective analysis of in-house data and rapid resolution of business issues. At each step, the server, terminal, and user work together to improve business efficiency and prevent large-scale problems.

[1163] Example 1

[1164] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1165] Many companies face challenges in collecting data from multiple internal data sources and utilizing it effectively. In particular, integrating data stored in different formats, identifying business issues, prioritizing those issues, and presenting optimal solutions are difficult. Furthermore, there is a need for a user interface that allows users to intuitively grasp the results of data analysis. The present invention aims to solve these challenges and provide a system that utilizes data efficiently and effectively.

[1166] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1167] In this invention, the server includes: means for automatically collecting and acquiring data from multiple internal data sources; means for converting the collected data into a unified format and integrating and standardizing the data; means for using the integrated data to build a data analysis model using a machine learning algorithm; means for providing a web-based interface that can be intuitively operated by a user; means for automatically extracting and listing business issues using the built data analysis model; means for prioritizing the extracted business issues and presenting solutions; and means for reviewing the presented solutions based on user feedback and providing an implementation plan for the selected solution. This makes it possible to efficiently collect and integrate internal data, effectively analyze it, extract business issues, prioritize them, present solutions, and provide them in a format that is intuitively understandable to the user.

[1168] "Data source" refers to the source of data provided by multiple departments and related systems within the company.

[1169] "Data collection" refers to the process of automatically obtaining the necessary data from internal data sources.

[1170] "Unified data format" refers to converting data stored in different formats into one standard format.

[1171] "Data integration" refers to the process of combining data collected from different data sources into one continuous data set.

[1172] "Data standardization" refers to the process of organizing integrated data into a consistent format.

[1173] "Machine learning algorithm" refers to the statistical techniques and computational methods used to build data analysis models.

[1174] "Data analysis model" refers to a model built using machine learning algorithms to extract specific business issues based on integrated and standardized data.

[1175] "Web-based interface" refers to a user interface accessible through a browser.

[1176] "Business issue extraction" refers to the process of using a data analysis model to identify issues related to internal business operations.

[1177] "Listing up" refers to compiling the extracted business issues in a list format.

[1178] "Prioritization" refers to setting the order in which extracted business issues should be addressed based on their impact and urgency.

[1179] "Providing solutions" refers to showing specific measures for the extracted business issues.

[1180] "User feedback" refers to the process of collecting opinions and ratings from users.

[1181] "Scrutiny" refers to examining the proposed solution in detail and assessing its validity.

[1182] "Providing an action plan" refers to showing the steps and resources required to specifically implement the solution selected by the user.

[1183] The present invention relates to a system for supporting data analysis and problem solving in in-house operations. Specific embodiments for carrying out the present invention will be described in detail below.

[1184] Internal data collection and integration

[1185] The server automatically collects data from various departments and related systems within the company. For example, it obtains sales data, employee performance data, and customer feedback data through a database management system (DBMS) or RESTful API. This data is often stored in different formats, so the server uses a data conversion tool (Python script) to convert this data into a unified format (CSV or JSON) and standardize it.

[1186] Development of data analysis models using machine learning algorithms

[1187] The server uses the integrated data to build a data analysis model using machine learning algorithms. This model is used to extract business issues, and random forest or neural network models are developed using Python and the TensorFlow or Scikit-learn library. The data is divided into training data and test data, and the training data is used to train the model, and the test data is used to evaluate the accuracy of the model.

[1188] Providing a user interface

[1189] The terminal provides a user interface that users can operate intuitively. Specifically, a web-based interface built with React.js is used. Users can access the system through a browser and view the results of data analysis and extracted business issues. The interface is created using Bootstrap and Material-UI.

[1190] Extracting and listing business issues

[1191] The server uses the developed data analysis model to extract business issues from the integrated data. For example, it identifies specific issues such as problems with product quality, issues related to declining employee performance, and customer complaints. These issues are saved in JSON format and notified to the user interface via a RESTful API. For example, if the server detects from sales data that sales of a particular product have dropped sharply, it will extract the issue as a problem related to the quality of that product and suggest a solution: "reviewing the quality control process."

[1192] Prioritizing issues and proposing solutions

[1193] The server prioritizes the extracted business issues, setting the order based on impact and urgency, and presenting solutions starting with the most important issues. For example, it might suggest solutions such as "reviewing the quality control process" or "conducting regular training." This information is also displayed on the user interface via a RESTful API.

[1194] Solution review and implementation

[1195] The user examines the solutions presented by the server and selects a feasible one. The selected solution is then provided along with a detailed implementation plan. For example, if "reviewing the quality control process" is selected as a solution, specific considerations, required resources, and a schedule are presented.

[1196] Specific examples

[1197] If the server detects from sales data that sales of a particular product have dropped sharply, it will identify the issue as a problem with the quality of that product and suggest a "review of the quality control process" as a solution.

[1198] Example of input prompt for generative AI model

[1199] Here are some example prompts to input to a generative AI model:

[1200] "Use departmental performance data to identify factors associated with poor employee performance."

[1201] "Analyze customer feedback data and extract key complaints."

[1202] "Use random forest to build a product sales prediction model."

[1203] This invention makes it possible to make maximum use of in-house data, thereby improving business efficiency and preventing large-scale problems.

[1204] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1205] Step 1: Collect data

[1206] The server automatically collects data from each department and related systems within the company. It uses a database management system (DBMS) and RESTful APIs to obtain sales data, employee performance data, and customer feedback data. This data is collected in a temporary storage area within the server.

[1207] Specifically, a Python script runs periodically, sends an API request, and retrieves the latest data, which is then converted to CSV format and saved.

[1208] Input: API request, database query

[1209] Output: CSV format data file

[1210] Step 2: Integrate and standardize data

[1211] The server converts the collected data into a unified format, consolidating and standardizing the data, and converting data from different formats into a unified schema for the SQL database.

[1212] Specifically, a data conversion Python script is run to convert each dataset into a unified format (e.g., all numeric data is rounded to two decimal places), and the converted data is imported into a MySQL database.

[1213] Input: CSV format data file

[1214] Output: Data in a unified format (stored in an SQL database)

[1215] Step 3: Building a machine learning model

[1216] The server uses the integrated data to build machine learning models, developing random forest and neural network models using Python, TensorFlow, and Scikit-learn.

[1217] Specifically, the server loads the data using a Python script and splits it into training and test data using SciPy. Next, it builds a neural network model using TensorFlow and trains it using the training data. The accuracy of the model is evaluated using the test data, and the models that are confirmed to have high accuracy are saved.

[1218] Input: Unified format data (SQL database)

[1219] Output: A trained machine learning model

[1220] Step 4: Providing a User Interface

[1221] The terminal provides an intuitive user interface, allowing users to view the results of data analysis and extracted business issues through a web-based interface built with React.js.

[1222] Specifically, when a user opens a web browser and accesses a specific URL, the device receives HTML, CSS, and JavaScript files from the server and displays information dynamically constructed by React.js.

[1223] Input: User's browser access

[1224] Output: Web page displaying analysis results and business issues

[1225] Step 5: Identify and list business issues

[1226] The server uses the developed data analysis model to extract business issues from the integrated data, identifying and listing issues such as product quality problems, poor employee performance, and customer dissatisfaction.

[1227] Specifically, the server periodically re-analyzes the integrated data and extracts business issues using the stored machine learning model. The extracted issues are saved in JSON format and delivered to the front end via a RESTful API.

[1228] Input: Integrated data, machine learning model

[1229] Output: Extracted business issues (saved in JSON format)

[1230] Step 6: Prioritize issues and present solutions

[1231] The server prioritizes the extracted business issues based on their impact and urgency, and presents solutions starting with the most important issues.

[1232] Specifically, the system runs a prioritization algorithm to calculate an impact score for each issue, after which the solution is displayed in the user interface.

[1233] Input: Extracted business issues (JSON format)

[1234] Output: Prioritized issues and solutions

[1235] Step 7: Refine and implement the solution

[1236] The user reviews the proposed solutions and selects a viable one, which is then provided with a detailed implementation plan.

[1237] Specifically, the user selects a solution on the user interface and sends that information to the server. Based on the selected solution, the server generates specific study items, required resources, and a schedule, and displays them on the user interface.

[1238] Input: User's solution selection

[1239] Output: Detailed execution plan

[1240] (Application example 1)

[1241] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1242] Modern factories require real-time monitoring of each robot's performance and error status, and the ability to quickly address these issues. However, achieving this requires a system that can efficiently collect and analyze large amounts of data and provide users with appropriate solutions. Conventional systems take time to integrate and analyze data, identify issues, and present solutions, resulting in delays in providing appropriate solutions. Another challenge is providing an interface that is easy for users to use.

[1243] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1244] In this invention, the server includes: means for collecting, standardizing, and integrating data from multiple data sources within a company; means for using the integrated data to develop a data analysis model using a machine learning algorithm; means for providing a user interface that can be intuitively operated by a user; means for extracting and listing business issues using the data analysis model; means for prioritizing the extracted business issues and proposing solutions; means for examining the proposed solutions together with the user and implementing feasible ones; means for collecting robot data in real time; and means for analyzing the collected data, extracting issues, prioritizing them, and displaying solutions on a smartphone screen. This makes it possible to monitor robot performance and error status in a factory in real time and quickly and effectively resolve issues.

[1245] Key Word Definitions

[1246] "Data source" is a general term for a system or device that provides data.

[1247] "Standardization" is the process of converting data of different formats into a consistent format.

[1248] "Integration" means combining data obtained from multiple different data sources into a single data set.

[1249] A "machine learning algorithm" is a program or method that learns patterns from data and automatically performs tasks such as prediction and categorization.

[1250] A "data analysis model" is a specific computational model constructed using machine learning algorithms for analyzing and predicting data.

[1251] A "user interface" is a visual and operational interface that allows a user to operate a system or application.

[1252] A "business issue" is a specific problem or obstacle that needs to be solved in the operations or work processes of a company or organization.

[1253] "Priority" means determining the order in which multiple issues or tasks should be handled based on their importance and urgency.

[1254] A "solution" is a specific action or method that should be taken to address a specific problem or issue.

[1255] "Real-time collection" is the process of collecting data immediately without delay.

[1256] A "smartphone screen" is a smartphone display and an interface for displaying applications and information.

[1257] "Robot data" refers to operational data such as performance and error information obtained from robots operating in factories.

[1258] MODE FOR CARRYING OUT THE INVENTION

[1259] The present invention provides a system for monitoring the performance of robots in a factory and the occurrence of errors in real time, and for responding quickly and effectively. Specific embodiments for carrying out the present invention will be described in detail below.

[1260] Configuration and Overview

[1261] The system consists of the following elements:

[1262] 1. Data collection and integration:

[1263] The server automatically collects data from multiple data sources within the factory. Specifically, this includes operation data, performance data, and error occurrence information for each robot. Because this data is stored in different formats, the server standardizes and centralizes the data.

[1264] 2. Development of data analysis models using machine learning algorithms:

[1265] The server uses the integrated data to develop a data analysis model using a machine learning algorithm (e.g., RandomForestClassifier). This model detects robot anomalies and identifies operational issues. It also splits the data into training and test data, trains the model, and evaluates its accuracy.

[1266] 3. Providing the user interface:

[1267] The terminal (e.g., a smartphone) provides a user interface that can be operated intuitively by the user. Specifically, a dashboard-style interface is considered, allowing the user to access the system through the smartphone screen and check the analysis results and solutions.

[1268] 4. Extract and list business issues:

[1269] The server uses the developed data analysis model to extract business issues from the integrated data. The extracted issues are listed so that users can easily check them. For example, they may include the cause of a particular robot's shutdown or frequent errors.

[1270] 5. Prioritizing issues and proposing solutions:

[1271] The server prioritizes the extracted business issues and presents solutions based on the impact and urgency of the issues. For example, this could include the timing of preventive maintenance or part replacement for a specific robot.

[1272] 6. Solution Examination and Implementation:

[1273] The user can then examine the solutions presented by the server and implement the most appropriate one. Specifically, the user can check the details of the solution and the implementation procedure through the user interface.

[1274] Hardware and Software

[1275] Hardware: Smartphone

[1276] Software: Python, requests library, scikit-learn

[1277] Specific examples

[1278] For example, if a particular robot in a factory stops working multiple times over a certain period of time, the system will identify the cause and suggest preventative maintenance. Users can view the following information on their smartphone screen:

[1279] Prompt Sentence Examples

[1280] "Factory robot 22 has stopped working three times in one week. Please provide possible issues that could be causing the downtime and solutions."

[1281] This makes it possible to monitor robot performance and error conditions within the factory in real time and resolve issues quickly and effectively.

[1282] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1283] Step 1:

[1284] The server collects operational data, performance data, and error information from each robot in the factory in real time. Because this data is stored in different formats, the server standardizes and centralizes the data.

[1285] Input: Operation data, performance data, and error information sent from each robot

[1286] Output: Standardized and unified dataset

[1287] Step 2:

[1288] The server uses the standardized data to develop a data analysis model using a machine learning algorithm (e.g., RandomForestClassifier). The model is divided into training data and test data, trained, and its accuracy is evaluated.

[1289] Input: Standardized dataset

[1290] Output: A trained data analysis model

[1291] Step 3:

[1292] The server uses a trained data analysis model to extract robot anomalies and operational issues from the integrated data, identifying and listing information according to the type and situation of the issue.

[1293] Input: Trained data analysis model, standardized dataset

[1294] Output: A list of extracted anomalies and business issues

[1295] Step 4:

[1296] The server prioritizes the extracted business issues and presents solutions to each issue using machine learning models as a reference. Priorities are determined based on the importance and urgency of the issues.

[1297] Input: List of anomalies and business issues

[1298] Output: A prioritized list of issues and solutions

[1299] Step 5:

[1300] The terminal displays the prioritized list of issues and solutions sent from the server to the user through a user interface, allowing the user to intuitively operate the terminal and check detailed information.

[1301] Input: A prioritized list of issues and solutions sent from the server

[1302] Output: Analysis results and solutions displayed on the smartphone screen

[1303] Step 6:

[1304] Users can examine the presented solutions, select the most appropriate one, and put it into action. Specific steps and information on the necessary resources are also provided, allowing for efficient problem-solving.

[1305] Input: Solution displayed on smartphone screen

[1306] Output: The selected solution and its implementation plan

[1307] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1308] The present invention combines a system that supports data analysis and problem solving in in-house operations with an emotion engine that recognizes user emotions. Specific embodiments for carrying out the present invention will be described in detail below.

[1309] Internal data collection and integration

[1310] The server automatically collects data from various departments and related systems within the company, such as sales data, employee performance data, customer feedback data, etc. Because the data exists in various formats, the server standardizes and consolidates the collected data.

[1311] Development of data analysis models using machine learning algorithms

[1312] The server uses machine learning algorithms to develop a data analysis model based on the integrated data. To develop the model, the data is divided into training data and test data, and the model is trained using the training data. The accuracy of the model is evaluated using the test data, and the model with the highest accuracy is selected.

[1313] Providing a user interface

[1314] The terminal provides a user interface that can be operated intuitively by the user. A web application-style interface is provided, and users can access the system via a browser and check analysis results and business issues.

[1315] Extracting and listing business issues

[1316] The server uses a data analysis model to extract business issues from the integrated data. For example, it detects and lists problems related to product quality or poor employee performance. The extracted issues are then provided to the user through a user interface.

[1317] Prioritizing issues and proposing solutions

[1318] The server prioritizes the extracted business issues based on their impact and urgency. Solutions are generated for the most important issues first and are notified to the user through the user interface. Specific solutions include strengthening quality control and implementing employee training.

[1319] Incorporating an emotion engine

[1320] One of the features of the present invention is that it incorporates an emotion engine to recognize the user's emotions in real time and adjust the analysis results and presented solutions according to the user's emotional state. The emotion engine analyzes emotions from the user's facial expressions, voice tone, text input, etc.

[1321] Dynamic adjustment of emotion-based interfaces

[1322] The device dynamically adjusts the user interface based on data obtained from the emotion engine. For example, if the user is stressed, it will simplify the solution suggestions and provide flexible support. If the user is relaxed, it will provide detailed information to support decision-making.

[1323] Emotion history analysis

[1324] The server analyzes the user's emotional history and presents solutions at the optimal time based on past emotional patterns, enabling appropriate feedback that takes into account the user's emotional state.

[1325] For example, if sales data detects a sudden drop in sales of a particular product, the issue is extracted as a quality control problem. If the emotion engine recognizes that the user's stress level is high, the solution is simplified and a simple suggestion such as "review the quality control process" is made. If the user is relaxed, a detailed implementation plan is presented.

[1326] Through the above steps, the present invention combines data analysis and emotion recognition to provide optimal solutions for users, improving work efficiency and reducing stress.

[1327] The processing flow will be explained below.

[1328] Step 1: Collect data

[1329] The server collects data from various departments and related systems within the company, including sales data, employee performance data, and customer feedback data.

[1330] I won't provide any code examples, but the server retrieves data using an API or database connection.

[1331] Step 2: Integrate and standardize data

[1332] The server consolidates the collected data and performs standardization processes, such as standardizing date formats and normalizing text data.

[1333] The server applies an ETL (Extract, Transform, Load) process to produce a unified dataset, which brings the data into a single, analyzable format.

[1334] Step 3: Developing a data analysis model

[1335] The server uses the combined data to develop data analysis models using machine learning algorithms, such as random forests and neural networks.

[1336] The server splits the data into training data and test data, trains the model using the training data, and evaluates the model on the test data to measure accuracy.

[1337] Step 4: Providing a User Interface

[1338] The terminal provides a user interface that can be operated intuitively by the user. The interface is in the form of a web application, and the user accesses it from a browser.

[1339] The interface on the terminal displays the results of data analysis and extracted business issues, which the user uses to interact with the system.

[1340] Step 5: Identify and list business issues

[1341] The server uses data analysis models to extract specific business issues from the integrated data, such as declining sales of a particular product, poor employee performance, or customer dissatisfaction.

[1342] The extracted issues are provided to the user as a list via a user interface, and the user checks this list to identify issues that require action.

[1343] Step 6: Prioritize the issues and present solutions

[1344] The server prioritizes the extracted business issues based on their impact and urgency. The impact of the issues is evaluated using a data analysis model.

[1345] The server generates specific solutions in order of priority and presents them to the user through a user interface. For example, it may suggest solutions such as "reviewing the quality control process" or "strengthening employee training."

[1346] Step 7: Recognizing user emotions with the emotion engine

[1347] The server analyzes the user's emotional state based on the user's emotional data acquired from the terminal (for example, facial expressions, voice tone, and analysis results of text input).

[1348] The emotion engine recognizes the user's emotions in real time, so if the user is feeling stressed, for example, this is fed back to the system.

[1349] Step 8: Dynamically adjust the interface based on emotions

[1350] The device dynamically adjusts the user interface based on data from the emotion engine, simplifying suggested solutions and providing more support when the user is feeling stressed.

[1351] For example, you can omit the details of the solution and show only the key points, or change the color scheme and layout to reduce visual strain.

[1352] Step 9: Analyze emotion history and provide solutions at the optimal time

[1353] The server analyzes the user's past emotional history and understands their emotional patterns, which allows it to present solutions at the optimal time.

[1354] Present detailed solutions and additional information when the user's emotional state is stable, which increases the solution's acceptability.

[1355] Step 10: Refine and implement the solution

[1356] The user reviews the proposed solutions and selects a feasible one, and can take into account the emotion engine's feedback when selecting a solution.

[1357] The server provides detailed plans and resource information for implementing the selected solutions, allowing users to quickly create action plans based on the information provided and solve business problems.

[1358] Through these steps, the present invention improves work efficiency and reduces stress by taking into account the user's emotions. The server, terminals, and users work together to provide a more effective data analysis and problem-solving process.

[1359] Example 2

[1360] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1361] In recent years, companies have placed increasing importance on identifying and resolving problems through business data analysis. However, existing systems face many challenges. For example, they lack the ability to easily collect and integrate data from multiple data sources, the interfaces for effectively utilizing analysis results are not intuitive, the analytical models are not accurate enough, and it takes time to prioritize business issues and present solutions. Furthermore, they present uniform feedback and solutions without considering the user's emotional state, which can increase user stress and reduce work efficiency.

[1362] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1363] In this invention, the server includes a means for collecting, standardizing, and integrating data from multiple internal data sources, a means for using the integrated data to develop a data analysis model using a machine learning algorithm, and a means for providing a user interface that can be intuitively operated by users. This enables data to be automatically collected from each department and related system and integrated in a consistent format. Furthermore, high-precision data analysis using the machine learning model enables rapid identification of business issues and the presentation of effective solutions. Furthermore, by including a means for recognizing user emotions in real time and dynamically adjusting the interface based on those emotions, the server provides optimal feedback and solutions to individual users, improving work efficiency and reducing stress.

[1364] A "data source" is a source of raw data provided by multiple departments and related systems within a company.

[1365] "Standardization" is the process of converting collected data into a consistent format and structure and integrating it.

[1366] "Integration" means combining data collected from multiple data sources into a single dataset.

[1367] A "machine learning algorithm" is a computational method that learns patterns and regularities from large amounts of data and uses them to make predictions and classifications.

[1368] A "data analysis model" is a computational model developed using machine learning algorithms to extract useful information from data.

[1369] A "user interface" is an interface that includes visual and operational elements through which a user interacts with a system.

[1370] "Business issues" are problems or areas for improvement that need to be resolved in the company's business processes.

[1371] "Solutions" are specific measures and action plans presented for the identified business issues.

[1372] An "emotion engine" is a software or hardware system that analyzes emotions from a user's facial expressions, tone of voice, text input, etc.

[1373] "Dynamic adjustment" refers to changing the behavior of an interface or system in real time according to the user's current state and environment.

[1374] "Emotion history" is a record of the user's past emotional states and the saved data.

[1375] "Analysis" is the process of examining collected data and information in detail to find meaning and patterns.

[1376] The present invention combines a system for supporting data analysis and problem solving in in-house operations with an emotion engine that recognizes user emotions. The following describes in detail the embodiments of the present invention.

[1377] The server automatically collects data from multiple internal data sources, such as sales data from each department, employee performance data, and customer feedback data, via APIs and database queries. The collected data is standardized and integrated using Python scripts and SQL.

[1378] Next, the server develops an analytical model using machine learning algorithms based on the integrated data. It uses open-source libraries such as Scikit-learn and TensorFlow to split the data into training data and test data. The model is trained using the training data and evaluated using the test data. Evaluation metrics include precision, recall, and F1 score.

[1379] The terminal provides an intuitive user interface, which is provided in the form of a web application developed with React and Vue.js and can be accessed via a browser. The interface displays a data dashboard and a list of business issues, allowing users to view analysis results and issue details.

[1380] The server uses a data analysis model to extract and list business issues. For example, it detects product quality problems and declining employee performance. The extracted issues are prioritized based on their impact and urgency, and solutions are generated. The generated solutions are presented to the user through a user interface. Specific solutions include strengthening quality control and implementing employee training.

[1381] One of the features of this invention is the incorporation of an emotion engine, which can recognize the user's emotions in real time. The emotion engine uses facial expression analysis tools such as OpenCV and natural language analysis engines to analyze emotions from voice tone and text input. Based on the analyzed emotion data, the interface content and presented solutions are dynamically adjusted.

[1382] The device dynamically adjusts the user interface based on data from the emotion engine. For example, if the device detects that the user is feeling stressed, it will simplify the solutions it presents and flexibly change the support it provides. Conversely, if the user is relaxed, it will provide more detailed information to help them make decisions.

[1383] The server also analyzes the user's emotional history and presents solutions at the optimal time, making it possible to provide effective feedback to the user. As a specific example, if sales data shows a sudden drop in sales of a particular product, the server will identify this as a quality control issue. If the emotion engine recognizes that the user's stress level is high, it will present a simple solution such as "reviewing the quality control process." On the other hand, if the user is relaxed, it will provide a detailed implementation plan.

[1384] An example of a prompt to be input to the generative AI model is, "Please summarize a use case for this system's project management functionality. For example, please explain how it helped you in a particular project, including examples of specific challenges and solutions."

[1385] Through the above steps, the present invention combines data analysis and emotion recognition to provide optimal solutions for users, improving work efficiency and reducing stress.

[1386] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1387] Step 1:

[1388] The server collects data from multiple data sources within the company. In this step, sales data, employee performance data, customer feedback data, etc. are obtained through APIs and database queries. As input, it receives raw data from each data source, and as output, it obtains a raw dataset before standardization. Specifically, the server runs periodically scheduled jobs and sends instructions to retrieve data.

[1389] Step 2:

[1390] The server standardizes and consolidates the collected data. It receives raw data in various formats (CSV, JSON, SQL, etc.) as input and generates a unified dataset in a unified format as output. Specifically, the server uses Python scripts and Pandas to convert and standardize data. For example, it handles missing values ​​in the data, unifies different formats, and extracts necessary fields.

[1391] Step 3:

[1392] The server develops a data analysis model based on the integrated data. It receives the integrated dataset as input and generates a trained model as output. Specifically, the server uses Scikit-learn or TensorFlow to split the data into training data and test data, and then trains the model using the training data. During this process, it also performs cross-validation and hyperparameter tuning.

[1393] Step 4:

[1394] The terminal provides the user interface. It receives GUI components and user browser requests as input, and displays an operable interface as output. Specifically, the terminal develops a web application using React or Vue.js to visualize data and set up an operation panel. For example, it dynamically displays analysis results or a list of business issues on a dashboard.

[1395] Step 5:

[1396] The server uses a data analysis model to extract and list business issues. It uses the trained model and the integrated dataset as input and generates a list of issues as output. Specifically, the server inputs data into the analysis model and detects various business issues (e.g., quality issues, performance degradation, customer dissatisfaction, etc.). The detected issues are stored in a database.

[1397] Step 6:

[1398] The server prioritizes the extracted business issues and generates and presents solutions. Based on the list of issues and a prioritization algorithm as input, it generates a prioritized list of issues and their corresponding solutions as output. Specifically, it scores issues based on their impact and urgency, and generates optimal solutions. These solutions are presented to the user through a user interface.

[1399] Step 7:

[1400] The server uses an emotion engine to obtain the user's emotional data in real time. It receives the user's facial expression images, voice data, and text input as input, and generates analyzed emotional data as output. Specifically, it analyzes facial expressions using tools such as OpenCV, and also performs voice tone analysis and text analysis in parallel.

[1401] Step 8:

[1402] The device dynamically adjusts the user interface based on the data obtained from the emotion engine. It receives analyzed emotion data as input and provides an adjusted interface as output. Specifically, if the user is feeling stressed, it reduces the complexity of the interface and presents simple solutions. On the other hand, if the user is relaxed, it provides detailed information to support decision-making.

[1403] Step 9:

[1404] The server analyzes the user's emotional history and presents solutions at the optimal time. It receives past emotional data as input and presents solutions at the optimal time based on the emotional patterns as output. Specifically, the server performs time series analysis and extracts patterns from the emotional history. This makes it possible to provide appropriate feedback that takes into account the user's past emotional state.

[1405] (Application example 2)

[1406] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1407] Conventional in-house work support systems focused on identifying work issues and proposing solutions based on data analysis, but because they did not take into account the user's emotional state, they had the problem of increasing stress and strain in the actual work environment.In addition, because they did not provide flexible feedback or adjust the interface according to the user's emotional state, it was difficult to improve the user experience.

[1408] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1409] In this invention, the server includes means for collecting, standardizing, and integrating data from multiple data sources within the company, means for using the integrated data and a machine learning algorithm to develop a data analysis model, means for providing a user interface that can be intuitively operated by a user, means for extracting and listing business issues using the data analysis model, means for prioritizing the extracted business issues and presenting solutions, emotion analysis means for recognizing the user's emotions in real time and adjusting the content of the presentation, and means for providing the user with optimal solutions to business issues based on the collected data and emotion information. Thus, by combining data analysis and emotion recognition, optimal solutions can be provided for the user, improving work efficiency and reducing stress.

[1410] "Data Sources" means the various internal or external information sources used to provide information.

[1411] "Standardization" is the process of unifying data in various formats by converting them into a consistent format.

[1412] "Synthesis" is the act of combining data collected from multiple data sources into a single coherent data set.

[1413] A "machine learning algorithm" is a mathematical technique for automatically learning patterns from data and making predictions or classifications.

[1414] "Data analytics model" refers to a trained machine learning model used to derive insights from data.

[1415] A "user interface" is an interactive screen or tool that allows a user to directly interact with a system.

[1416] "Business issues" refer to various problems and obstacles that arise during the execution of business operations.

[1417] "Prioritization" is the process of determining the order of issues based on importance and urgency.

[1418] A "solution" is a specific means or process for solving a particular challenge or problem.

[1419] "Emotion analysis means" is a technology that recognizes emotions by analyzing a user's facial expressions, voice tone, text input, etc.

[1420] "Emotional history" refers to records and data regarding a user's past emotional states.

[1421] "Feedback" refers to the response or reaction a user receives from a system.

[1422] A system according to the present invention can be implemented using the following hardware and software.

[1423] Hardware

[1424] 1. Server: A high-performance server for collecting, integrating, and analyzing data.

[1425] 2. Camera: A high-resolution camera to capture the facial expressions of workers in real time.

[1426] 3. Microphone: Highly sensitive microphone for analyzing voice tones.

[1427] 4. Terminal: A device that provides a user interface, such as a smartphone, smart glasses, or tablet.

[1428] software

[1429] 1. DeepFace: A machine learning library for facial expression analysis.

[1430] 2. OpenCV: A library for image processing.

[1431] 3. TensorFlow: A library used to train and run machine learning models.

[1432] 4. GPT-3 API: An API for natural language generation.

[1433] 5. Web Application Framework: Building user interfaces using React.js and Django.

[1434] Data collection and analysis

[1435] The server collects, standardizes, and integrates data from multiple data sources within the factory, including sales data, employee performance data, and customer feedback data, all of which exist in various formats. The integrated data is then analyzed using TensorFlow, and a data analysis model is developed using machine learning algorithms.

[1436] Providing a user interface

[1437] The terminal provides an intuitive user interface as a web application that combines React.js and Django, allowing users to check analysis results and business issues via a browser.

[1438] Identifying business issues and presenting solutions

[1439] The server uses a data analysis model based on the collected data to extract and list business issues. It then prioritizes the issues based on their impact and urgency and presents solutions. Specific solutions include strengthening quality control and implementing employee training.

[1440] Use of sentiment analysis methods

[1441] The server uses DeepFace and OpenCV to analyze the user's facial expressions and voice tone in real time to recognize their emotional state. This allows the presented solutions and information to be dynamically adjusted according to the user's emotional state. If the user is feeling stressed, the presented solutions will be simplified and they will be encouraged to take a break if necessary.

[1442] Emotion history management and feedback

[1443] The server analyzes the user's emotional history and presents solutions at the optimal time based on past emotional patterns, thereby improving the user experience and work efficiency.

[1444] Specific examples

[1445] Example 1

[1446] If the worker is relaxed, provide detailed workflow optimization suggestions. Use the following prompt to generate detailed explanations:

[1447] Generate a detailed optimization strategy for the work flow in your factory when workers are relaxed.

[1448] Example 2

[1449] If a worker is feeling stressed, provide a simplified procedure and suggest a break. Use the following prompt to generate the simplified procedure:

[1450] Generate simplified work procedures when workers are stressed. Also suggest breaks for workers.

[1451] By implementing this invention, it becomes possible to perform optimal data analysis and present solutions that take into account the user's emotional state, which is expected to improve work efficiency and reduce stress.

[1452] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1453] Step 1:

[1454] The server collects, standardizes, and integrates data from multiple data sources within the factory. Input data includes sales data, employee performance data, and customer feedback data. The output is standardized integrated data. Specifically, information in different data formats is processed to unify it and compiled into a single data set.

[1455] Step 2:

[1456] The server uses the integrated data to develop a data analysis model using a machine learning algorithm (such as TensorFlow). The input data is the integrated dataset, and the output is a trained data analysis model. Specific operations include splitting the data into training data and test data, and training the model using the training data.

[1457] Step 3:

[1458] The terminal provides a user interface that users can operate intuitively. The input data is the analysis results and a list of business tasks, and the output is the interface screen provided to the user. Specifically, we will use React.js and Django to build a web application that users can access via a browser.

[1459] Step 4:

[1460] The server uses a data analysis model to extract business issues and list them. The input data is the output of the analysis model, and the output is a list of extracted business issues. Specifically, the analysis model detects quality issues and declines in employee performance from business data and lists them as issues.

[1461] Step 5:

[1462] The server prioritizes the extracted business issues based on their impact and urgency, and presents solutions. The input data is a list of business issues, and the output is a prioritized list of solutions. Specifically, it calculates a priority score and generates solutions from the most urgent and important issues.

[1463] Step 6:

[1464] The server uses emotion analysis tools (DeepFace, OpenCV, etc.) to analyze the user's facial expressions and voice tone in real time. The input data is the user's real-time video and audio, and the output is information about the user's emotional state. Specifically, it acquires data from the camera and microphone, analyzes facial expressions and voice tone, and determines the user's emotional state.

[1465] Step 7:

[1466] The device dynamically adjusts the content of the user interface based on the analysis results and the user's emotional state. The input data are the emotion analysis results and solutions to business problems, and the output is an adjusted user interface screen. Specifically, if the user is feeling stressed, the information is simplified, and if the user is relaxed, detailed solutions are presented.

[1467] Step 8:

[1468] The server analyzes the user's emotional history and presents solutions at the optimal time based on past emotional patterns. The input data is emotional history data, and the output is solutions presented at the appropriate time. Specifically, it analyzes the user's emotional patterns and presents feedback at the timing that elicits the user's optimal response.

[1469] Step 9:

[1470] The server uses a generative AI model (such as the GPT-3 API) to generate specific solutions and feedback messages based on the user's emotional state. Specific input prompts include "Generate a detailed optimization strategy for the factory workflow when workers are relaxed" and "Generate simplified work procedures when workers are stressed. Also suggest breaks for workers." The obtained prompts are provided to the user as appropriate solutions based on their emotional state.

[1471] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1472] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1473] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1474] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1475] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1476] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1477] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1478] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1479] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1480] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1481] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1482] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1483] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1484] 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.

[1485] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1486] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1487] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1488] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1489] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1490] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1491] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1492] The following is further disclosed regarding the above embodiment.

[1493] (Claim 1)

[1494] A means to collect, standardize, and integrate data from multiple internal data sources;

[1495] a means for using the integrated data to develop a data analysis model using machine learning algorithms;

[1496] A means for providing a user interface that can be intuitively operated by a user;

[1497] A method for extracting and listing business issues using a data analysis model,

[1498] A means to prioritize the extracted business issues and present solutions;

[1499] It is a means to examine the proposed solutions together with the users and put into practice those that are feasible.

[1500] A system including:

[1501] (Claim 2)

[1502] A means to integrate data collected from multiple internal data sources and develop analytical models using machine learning algorithms;

[1503] A means to provide an interface that is easy for users to operate and to extract business issues using a data analysis model;

[1504] A method for prioritizing the extracted issues and presenting solutions starting with the most important issues.

[1505] A means to refine proposed solutions based on user feedback

[1506] 10. The system of claim 1, comprising:

[1507] (Claim 3)

[1508] The system of claim 1, including a means for automating a series of processes from collecting and integrating internal data, developing data analysis models, providing a user interface, extracting and prioritizing business issues, and presenting and examining solutions.

[1509] "Example 1"

[1510] (Claim 1)

[1511] A means of collecting and automatically acquiring data from multiple data sources within the company,

[1512] A means of converting the collected data into a uniform format and integrating and standardizing the data;

[1513] a means for using the integrated data to build a data analysis model using a machine learning algorithm;

[1514] means for providing a web-based interface that is intuitive for users to operate;

[1515] A means to automatically extract and list business issues using the constructed data analysis model,

[1516] A means to prioritize the extracted business issues and present solutions;

[1517] means for reviewing the proposed solutions based on user feedback and providing an implementation plan for the selected solution;

[1518] A system including:

[1519] (Claim 2)

[1520] A means to convert data collected from multiple internal data sources into a unified format and build a data analysis model using machine learning algorithms.

[1521] A web-based interface is provided that allows users to intuitively operate it, and a means is provided for extracting business issues using a data analysis model.

[1522] A method for prioritizing the extracted issues based on their impact and urgency, and presenting solutions starting with the most important issues;

[1523] a means for vetting the proposed solutions based on user feedback;

[1524] 10. The system of claim 1, comprising:

[1525] (Claim 3)

[1526] The system of claim 1 includes a means for automating a series of processes, from collecting and integrating internal data, to building a data analysis model, providing a web-based interface, extracting and prioritizing business issues, and presenting and examining solutions.

[1527] "Application Example 1"

[1528] Claims

[1529] (Claim 1)

[1530] A means to collect, standardize, and integrate data from multiple internal data sources;

[1531] a means for using the integrated data to develop a data analysis model using machine learning algorithms;

[1532] A means for providing a user interface that can be intuitively operated by a user;

[1533] A method for extracting and listing business issues using a data analysis model,

[1534] A means to prioritize the extracted business issues and present solutions;

[1535] A means to examine proposed solutions together with users and implement feasible ones;

[1536] a means for real-time collection of robotic data;

[1537] A method for analyzing collected data, extracting issues, prioritizing them, and displaying solutions on a smartphone screen.

[1538] A system including:

[1539] (Claim 2)

[1540] A means to integrate data collected from multiple internal data sources and develop analytical models using machine learning algorithms;

[1541] A means to provide an interface that is easy for users to operate and to extract business issues using a data analysis model;

[1542] A method for prioritizing the extracted issues and presenting solutions starting with the most important issues.

[1543] a means for vetting the proposed solutions based on user feedback;

[1544] A means for collecting robot data in real time and providing analytical results;

[1545] 10. The system of claim 1, comprising:

[1546] (Claim 3)

[1547] It is a means to automate a series of processes from collecting and integrating internal data, developing data analysis models, providing user interfaces, extracting and prioritizing business issues, presenting solutions, and examining them.

[1548] 10. The system of claim 1, including means for automating real-time collection and analysis of robotic data.

[1549] "Example 2: Combining Emotion Engines"

[1550] (Claim 1)

[1551] A means to collect, standardize, and integrate data from multiple internal data sources;

[1552] a means for using the integrated data to develop a data analysis model using machine learning algorithms;

[1553] A means for providing a user interface that can be intuitively operated by a user;

[1554] A method for extracting and listing business issues using a data analysis model,

[1555] A means to prioritize the extracted business issues and present solutions;

[1556] A means to examine proposed solutions together with users and implement feasible ones;

[1557] means for recognizing a user's emotions in real time and dynamically adjusting a user interface based on the emotions;

[1558] A method for analyzing the user's emotional history and presenting solutions at the optimal time.

[1559] A system including:

[1560] (Claim 2)

[1561] A means to integrate data collected from multiple internal data sources and develop analytical models using machine learning algorithms;

[1562] A means to provide an interface that is easy for users to operate and to extract business issues using a data analysis model;

[1563] A method for prioritizing the extracted issues and presenting solutions starting with the most important issues.

[1564] a means for vetting the proposed solutions based on user feedback;

[1565] means for recognizing a user's emotion and adjusting the interface based on the emotion;

[1566] 10. The system of claim 1, comprising:

[1567] (Claim 3)

[1568] It is a means to automate a series of processes from collecting and integrating internal data, developing data analysis models, providing user interfaces, extracting and prioritizing business issues, presenting solutions, and examining them.

[1569] 2. The system according to claim 1, further comprising means for storing and analyzing a user's emotional history and reflecting the result in the presentation of a solution.

[1570] "Application example 2 when combining emotion engines"

[1571] (Claim 1)

[1572] A means to collect, standardize, and integrate data from multiple internal data sources;

[1573] a means for using the integrated data to develop a data analysis model using machine learning algorithms;

[1574] A means for providing a user interface that can be intuitively operated by a user;

[1575] A method for extracting and listing business issues using a data analysis model,

[1576] A means to prioritize the extracted business issues and present solutions;

[1577] An emotion analysis means for recognizing a user's emotion in real time and adjusting the content to be presented;

[1578] A means to provide users with optimal solutions to business issues based on collected data and emotional information, and

[1579] A system including:

[1580] (Claim 2)

[1581] 2. The system according to claim 1, further comprising means for analyzing the user's emotional history using an emotion analysis means and presenting a solution at an optimal timing based on the user's past emotional patterns.

[1582] (Claim 3)

[1583] The system of claim 1 includes a means for automating a series of processes from collecting and integrating internal data, developing a data analysis model, providing a user interface, extracting and prioritizing business issues, presenting and examining solutions, and providing appropriate feedback that takes into account the user's emotional state using emotion analysis means. [Explanation of symbols]

[1584] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means to collect, standardize, and integrate data from multiple internal data sources; a means for using the integrated data to develop a data analysis model using machine learning algorithms; A means for providing a user interface that can be intuitively operated by a user; A method for extracting and listing business issues using a data analysis model, A means to prioritize the extracted business issues and present solutions; It is a means to examine the proposed solutions together with the users and put into practice those that are feasible. A system including:

2. A means to integrate data collected from multiple internal data sources and develop analytical models using machine learning algorithms; A means to provide an interface that is easy for users to operate and to extract business issues using a data analysis model; A method for prioritizing the extracted issues and presenting solutions starting with the most important issues. A means to refine proposed solutions based on user feedback The system of claim 1 , comprising:

3. The system of claim 1, further comprising a means for automating a series of processes from collecting and integrating internal data to developing a data analysis model, providing a user interface, extracting and prioritizing business issues, and presenting and examining solutions.

Images