system

Abstract

Provide a system. [Solution] means for receiving the uploaded data; means for analyzing the received data using a generative AI model; means for generating a system configuration diagram based on the analysis results; A means for visualizing the generated system configuration diagram; A system that includes a means for monitoring the operational status of the system.

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] Systems that have been in operation for a long time tend to have complex configurations, making analysis difficult when the original personnel are not present. Modifying and operating a system under such circumstances requires a great deal of time and effort, so efficiency is required. It is also important to constantly monitor whether the system configuration is being properly maintained, and to detect problems early and take preventative measures. The purpose of this invention is to solve these problems and support the efficient analysis, modification, and operation of systems. [Means for solving the problem]

[0005] The present invention solves the problems by the following means:

[0006] means for receiving the uploaded data;

[0007] means for analyzing the received data using a generative AI model;

[0008] means for generating a system configuration diagram based on the analysis results;

[0009] A means for visualizing the generated system configuration diagram;

[0010] We provide a system equipped with a means for monitoring the operational status of a system. This system automatically analyzes data such as code files, log files, specifications, and manuals, and provides users with a visualized system configuration diagram, allowing them to quickly grasp the overall picture of the system and the scope of its impact. In addition, by monitoring the operational status in real time, we support the proper operation of the system by detecting and notifying abnormalities early on.

[0011] "Uploaded data" refers to data such as code files, log files, specifications, and manuals sent by users to the system.

[0012] A "generative AI model" refers to a trained model that uses artificial intelligence to analyze data and extract information.

[0013] "Analysis" refers to the process of analyzing received data using a generative AI model to extract the structure and dependencies within the code.

[0014] A "system configuration diagram" is a diagram generated based on the analysis results that visually shows the dependencies and communication paths between each component within a system.

[0015] "Visualization" refers to displaying the generated system configuration diagram on a user terminal and providing it in an interactive format.

[0016] "Operational status monitoring" refers to continuously monitoring the real-time operating status and performance data within the system to detect abnormalities.

[0017] "Anomaly detection" refers to detecting unusual patterns or errors in the system's operating status and discovering problems early on.

[0018] "User terminal" refers to a computing device through which a user accesses and operates the system.

[0019] "Means for receiving" refers to a function that enables the server to receive data sent from the user terminal.

[0020] "Providing" refers to displaying the analysis results of the generative AI model, system configuration diagrams, and operational status monitoring results in a form that is easy for users to understand and make them available. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] The present invention provides a system for visualizing and monitoring the configuration of a system that has been in operation for a long period of time, thereby supporting efficient analysis, modification, and operation of the system.

[0043] System Overview

[0044] The system includes the following key features:

[0045] 1. Data Collection

[0046] The user uploads the code file, log file, specification, or manual that he / she wants to analyze to the server.

[0047] 2. Data Analysis

[0048] The server analyzes the received files using a generative AI model to extract code structure, log patterns, and specification contents.

[0049] 3. System configuration diagram generation

[0050] Based on the analysis results, the server generates a system configuration diagram that shows the dependencies and communication paths between each component of the system.

[0051] 4. Visualization

[0052] The terminal visually displays an interactive system configuration diagram to the user, allowing the user to manipulate the diagram.

[0053] 5. Surveillance

[0054] The server monitors the system's operational status in real time and notifies the user if an abnormality is detected.

[0055] Program processing

[0056] 1. Data Collection

[0057] Users log in to the system's web portal and select and upload the files they want to analyze, which can be in a variety of formats, including source code, log files, specifications, and manuals.

[0058] 2. Data Analysis

[0059] The server receives the uploaded files and identifies their data format. It uses a generative AI model to analyze the code structure and extract dependencies between functions, classes, and modules. For log files, it analyzes entries and identifies patterns of errors and warnings.

[0060] 3. System configuration diagram generation

[0061] The server aggregates the analysis results and generates a data structure that illustrates the relationships between components. This data structure is then used to generate a system diagram, which visually shows how the parts of the system interact with each other.

[0062] 4. Visualization

[0063] The terminal displays the generated system diagram in the user's browser. The user can interact with the diagram and view detailed information. For example, clicking on a specific module displays details about its dependencies and functions.

[0064] 5. Surveillance

[0065] The server monitors the system's operational status in real time and detects abnormal patterns and errors. If an abnormality is detected, the user is notified and a warning message is displayed on the dashboard. At the same time, detailed information about the abnormality and the scope of its impact are also reported to the user.

[0066] Specific examples

[0067] 1. Data Collection

[0068] A user logs into the system's web portal and uploads the latest application code file (e.g., app_code.py) and system log file (e.g., server_log.txt).

[0069] 2. Data Analysis

[0070] The server receives app_code.py and server_log.txt, inputs these files into the AI ​​model, and begins analysis. The AI ​​model extracts function dependencies within the code and identifies error patterns from the log file.

[0071] 3. System configuration diagram generation

[0072] Based on the analysis results, the server generates a system configuration diagram showing the relationships between functions, classes, and modules. This configuration diagram visually displays dependencies between modules and error locations.

[0073] 4. Visualization

[0074] The device displays a system diagram in the user's browser. The user can click on the diagram to view details of specific modules or functions. For example, clicking on Module A displays the associated functions and dependencies.

[0075] 5. Surveillance

[0076] The server performs real-time monitoring of the system and displays a warning on the dashboard if it detects any abnormal behavior. For example, if memory usage spikes, an alert is generated, showing the affected module and how to address it.

[0077] In this way, the system of the present invention enables the user to quickly understand the entire system and appropriately monitor the operational status, thereby supporting efficient system modification and operation.

[0078] The processing flow will be explained below.

[0079] Step 1:

[0080] The user logs into the system's web portal and clicks the "Upload analysis file" button.

[0081] Step 2:

[0082] The user selects the files they want to analyze (e.g., source code files, log files, specifications, or manuals) and uploads them to the server.

[0083] Step 3:

[0084] The server receives the uploaded file and automatically identifies the file format and content, for example, checking whether it is a code file, log file, or specification document.

[0085] Step 4:

[0086] The server inputs the received files into a generative AI model, which analyzes the code structure, function call relationships, and dependencies. For example, it extracts that function A calls function B, or that module X depends on library Y.

[0087] Step 5:

[0088] The server analyzes the log file entries to identify the frequency and occurrence patterns of errors and warnings, for example, the frequency of occurrence of the error message "ERROR" and the warning message "WARNING".

[0089] Step 6:

[0090] The server analyzes the text of specifications and manuals and extracts important points and constraints of the system specifications.

[0091] Step 7:

[0092] Based on the analysis results, the server generates a data structure that shows the dependencies and communication paths between each component. The dependencies and API call relationships between each module are represented by nodes and edges.

[0093] Step 8:

[0094] The server generates a system configuration diagram based on the generated data structure. This diagram includes the relationships between modules and components, the locations of errors, and so on.

[0095] Step 9:

[0096] The terminal displays the system configuration diagram in the user's browser, and the user can interactively click on each node or edge to display detailed information.

[0097] Step 10:

[0098] Users can explore the diagram and learn more about specific modules and components. For example, clicking on Module A displays the functions and dependencies associated with that module.

[0099] Step 11:

[0100] The server monitors the system's operation in real time, checking for new log entries and changes in system state, and running algorithms to detect abnormal patterns and errors.

[0101] Step 12:

[0102] If the server detects an abnormality, it will send an alert to the user, providing them with a notification containing detailed information about the abnormality and the extent of its impact.

[0103] Step 13:

[0104] Users receive alerts and can view detailed information in a dashboard, such as memory usage spikes or CPU overloads.

[0105] As described above, by performing specific processing for each step, the user can easily grasp the overall structure and operational status of the system, enabling efficient modification and operation.

[0106] Example 1

[0107] 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."

[0108] With existing systems, it is difficult to quickly grasp the overall picture of the system and efficiently monitor and modify it. In particular, in complex systems that have been in operation for a long time, it is important to visualize the dependencies and communication paths between components and monitor the operational status in real time, but there are currently no easy ways to achieve this. A notification system is also needed to respond instantly when an abnormality occurs.

[0109] 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.

[0110] In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, means for monitoring the system's operational status, means for selecting uploaded data after user authentication, means for interactively displaying details of the configuration diagram to the user, and means for notifying the user when an abnormality is detected. This allows the user to quickly grasp the overall picture of the system and efficiently analyze, repair, and operate it. Real-time monitoring of the system's operational status and immediate notification of abnormalities enable early detection and response to problems.

[0111] "Uploaded Data" refers to electronic data such as source code, log files, specifications, or manuals that a user sends to the system.

[0112] "Means of receiving" refers to the functions and processes by which the server obtains uploaded data.

[0113] "Generative AI models" refer to artificial intelligence algorithms used to automate the analysis of data and extract advanced information.

[0114] "Means for analyzing" refers to the functions or processes used to analyze received data and extract meaningful information or patterns.

[0115] A "system configuration diagram" is a diagram that visually shows the dependencies and communication paths between each component within a system.

[0116] "Visualization means" refers to the functions and processes for visually displaying the generated system configuration diagram to the user.

[0117] "Means for monitoring the operational status of the system" refers to functions and processes for monitoring in real time whether the system is operating normally and detecting abnormalities.

[0118] "Means for selecting uploaded data after authentication" refers to the functionality or process for selecting and using data within the system after a user has provided valid authentication information.

[0119] "Means for interactively displaying details of the configuration diagram" refers to functions and processes that allow a user to manipulate the system configuration diagram and dynamically view detailed information.

[0120] "Means for notifying users when an abnormality is detected" refers to functions and processes for quickly notifying users of an abnormality when it is discovered during system monitoring.

[0121] This invention relates to a system for visualizing and monitoring system configurations. This system receives uploaded data and analyzes it using a generative AI model. It then generates a system configuration diagram based on the analysis results and provides it visually to the user. It also includes a function to monitor the system's operational status in real time and notify the user when an abnormality is detected.

[0122] 1. Data Collection and Reception

[0123] Users log in to the system through a web portal and upload the source code, log files, specifications, or manuals they want to analyze. For example, a user can select and upload files named app_code.py and server_log.txt. These data are then transferred to the server.

[0124] 2. Data Analysis

[0125] The server receives the uploaded data and feeds it into a generative AI model that extracts function dependencies in the code and identifies error patterns in log files. The hardware used is a dedicated server, and the software includes a deep learning framework.

[0126] Example: The server generates a prompt statement saying "Start code analysis" and sends it to the generative AI model.

[0127] 3. Generating a system configuration diagram

[0128] The server generates a data structure for a system configuration diagram based on the results of the data analysis. This configuration diagram includes dependencies and communication paths between each component of the system. The server then draws a visual system configuration diagram based on this data structure.

[0129] 4. Visualization

[0130] The terminal displays the generated system diagram in the user's browser. The user can click on the diagram to interactively view the details of a specific module or component. For example, when the user clicks on module A, a pop-up appears with details of its functions and dependencies.

[0131] 5. Real-time monitoring and notifications

[0132] The server continuously monitors the system's operational status. If it detects abnormal behavior or an error pattern, it notifies the user and displays a warning message on the dashboard. The hardware used is a module dedicated to monitoring, and the software includes a monitoring tool. For example, if the server detects a sudden increase in memory usage, it displays a warning message on the dashboard saying, "Memory usage has increased sharply, affecting module A."

[0133] In this way, this system allows users to quickly grasp the overall picture of the system and efficiently analyze, repair, and operate it.In addition, real-time monitoring of the system's operating status and immediate notification of abnormalities enable early detection and response to problems.

[0134] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0135] Step 1:

[0136] The user accesses the web portal and enters their credentials. If the correct credentials are entered, the user is able to access the dashboard.

[0137] Input: Username, Password

[0138] Output: Authentication token, dashboard screen

[0139] Specific operation: The user accesses "example.com", enters their username and password, and presses the "Login" button.

[0140] Step 2:

[0141] The user clicks the upload button on the dashboard, selects the file they want to analyze, and uploads it. This file is then sent to the server.

[0142] Input: File to be analyzed (e.g. app_code.py, server_log.txt)

[0143] Output: A confirmation message for the uploaded file

[0144] Specific behavior: The user clicks the "File Upload" button, selects app_code.py and server_log.txt, and then clicks the "Upload" button.

[0145] Step 3:

[0146] The server receives the uploaded files, identifies the data format of each file, and inputs these files into a generative AI model to perform data analysis.

[0147] Input: Uploaded file

[0148] Output: Analysis results (code dependencies, log error patterns)

[0149] Specific operation: The server passes app_code.py and server_log.txt to the generated AI model, generates a prompt statement saying "Start code analysis", and sends it to the AI ​​model.

[0150] Step 4:

[0151] Based on the results of the data analysis, the server generates a data structure for a system configuration diagram, which includes dependencies and communication paths between components.

[0152] Input: Analysis results (code dependencies, log error patterns)

[0153] Output: System configuration diagram data structure

[0154] Specific operation: The server executes the "process for generating configuration diagram data," registers dependencies and communication paths in a database, and draws a system configuration diagram.

[0155] Step 5:

[0156] The terminal visually displays the generated system configuration diagram in the user's browser, and the user can click on the diagram to view detailed information.

[0157] Input: System configuration diagram data structure

[0158] Output: System configuration diagram on browser

[0159] Specific operation: The terminal displays a system configuration diagram on the browser, and when the user clicks on a specific module, detailed information related to that module will be displayed in a pop-up.

[0160] Step 6:

[0161] The server monitors the system's operational status in real time, detecting abnormal behavior and error patterns. If an abnormality occurs, it notifies the user and displays a warning message on the dashboard.

[0162] Input: Real-time system data

[0163] Output: Anomaly detection, warning message

[0164] Specific operation: When the server performs "real-time monitoring" and detects a sudden increase in memory usage, a warning message will be displayed on the dashboard stating "Memory usage has increased sharply, affecting module A."

[0165] This allows users to efficiently understand the system configuration and operational status, and to respond quickly when a problem occurs.

[0166] (Application example 1)

[0167] 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."

[0168] With conventional systems, it is difficult to efficiently visualize and analyze the configuration of systems that have been in operation for a long time, which has resulted in the problem of system operation and modification taking a great deal of time and effort.In addition, early detection of abnormalities and real-time operational monitoring are insufficient, resulting in problems such as a decline in system stability and reliability.

[0169] 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.

[0170] In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, and means for monitoring the system's operational status and notifying when an abnormality is detected. This enables efficient visualization and analysis of the system configuration, and real-time operational monitoring and abnormality detection.

[0171] The "means for receiving uploaded data" is a function for importing data sent by a user into the server.

[0172] "Means for analysis using a generative AI model" refers to a function that analyzes uploaded data using an artificial intelligence model and extracts data structures and patterns.

[0173] The "means for generating a system configuration diagram" is a function that creates a diagram that visually represents the relationships between each component of the system based on the results of the analyzed data.

[0174] The "means for visualizing the system configuration diagram" is a function that allows the user to interactively display the generated system configuration diagram and operate it.

[0175] "Means for monitoring the system's operational status and notifying users if an abnormality is detected" refers to a function that monitors the system's operation in real time and sends an alert to users if an abnormality occurs.

[0176] MODE FOR CARRYING OUT THE INVENTION

[0177] The present invention provides a system that efficiently visualizes the operation of factory robots, enabling early detection of abnormalities and real-time operation monitoring. Hereinafter, embodiments of the present invention will be described.

[0178] System configuration

[0179] The system primarily consists of the following major components:

[0180] 1. Server

[0181] 2. User device (smartphone, etc.)

[0182] 3. Operational data collection device for factory robots

[0183] System Features

[0184] 1. Means of receiving uploaded data:

[0185] The user terminal receives the factory robot's operational data (e.g., log files and operation history data) from the collection device and uploads it to the cloud server, which receives and stores this data.

[0186] 2. Means of analyzing received data using a generative AI model:

[0187] The server inputs the uploaded data into a generative AI model and begins analysis. The AI ​​model uses a high-performance language model such as GPT-4 (registered trademark). Through analysis, patterns and anomalies are identified within the operational data.

[0188] 3. How to generate a system diagram based on the analysis results:

[0189] Based on the analysis results, the server generates a system configuration diagram that shows the operational status and dependencies of each robot in the factory. The system configuration diagram visually displays the location, communication paths, and operational status of each robot.

[0190] 4. A way to visualize the generated system diagram:

[0191] The generated system configuration diagram is sent to the user's device and displayed in an interactive format, allowing the user to tap and zoom to view detailed information.

[0192] 5. Monitoring the system's operational status and notifying you if an abnormality is detected:

[0193] The server monitors operational data in real time, and if an abnormality is detected, it sends an alert via push notification to the user's device, allowing the user to respond promptly without missing the timing of the abnormality.

[0194] Specific examples of hardware and software used

[0195] Server: Cloud server (e.g. Amazon Web Services)

[0196] User device: Smartphone (iOS or ANDROID (registered trademark))

[0197] Generative AI model: GPT-4 (OpenAI (registered trademark))

[0198] Specific examples

[0199] 1. Data Collection Example:

[0200] The user device receives the latest factory robot operation data (e.g., robot_log.txt) and uploads it to the cloud server.

[0201] 2. Data analysis example:

[0202] The server receives robot_log.txt and begins analyzing it with GPT-4, which extracts dependencies between specific functions and abnormal patterns.

[0203] 3. Example of system configuration diagram generation:

[0204] The server generates a system configuration diagram based on the analysis results, visually representing the operational status and dependencies of each robot.

[0205] 4. Visualization example:

[0206] The system configuration diagram is sent to the user's device and displayed in an interactive format on the device screen, where the user can tap on a specific robot to view more information.

[0207] 5. Monitoring and Notification Examples:

[0208] The server monitors in real time and sends a push notification to the user's device if an abnormality is detected. Example: "Robot 123's memory usage is increasing rapidly. Please check immediately."

[0209] Prompt Sentence Examples

[0210] "Please analyze the following robot operation log data and clearly indicate the dependencies between functions and the location of the error. Log data: [Part of the detailed log data]"

[0211] In this way, it becomes possible to efficiently monitor the operation of factory robots and quickly detect abnormalities.

[0212] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0213] Step 1:

[0214] Data collection

[0215] The user uploads the operation data (e.g., log files) of the factory robot to the user terminal. The uploaded data includes operation history data, error logs, performance data, etc. The user terminal sends this data to the cloud server. The input is the robot operation data (in file format), and the output is the data stored on the cloud server.

[0216] Step 2:

[0217] Data reception

[0218] The server receives data sent from the user's device and stores it in a database. In particular, it checks whether the received data has been uploaded correctly and converts it into the required data format. During this process, detailed log information and error messages are entered, and this is converted into an internal database format and stored.

[0219] Step 3:

[0220] Data analysis preparation

[0221] The server prepares the received data for input to a generative AI model for analysis. Specifically, it converts the data into an appropriate format and generates a prompt. For example, it prepares a prompt such as, "Analyze this robot log and extract behavior patterns and dependencies." The input is the converted log information, and the output is the prompt and converted data that are input to the generative AI model.

[0222] Step 4:

[0223] Data analysis

[0224] The server analyzes the data using a generative AI model (e.g., GPT-4). Here, the prompt sentence and the converted data are input into the AI ​​model, and as a result, the robot's behavior patterns, dependencies, error patterns, etc. are extracted. The input for the analysis is the prompt sentence and data, and the output is the analysis results, such as a dependency list and error log patterns.

[0225] Step 5:

[0226] System configuration diagram generation

[0227] The server generates a system configuration diagram based on the analysis results. This configuration diagram is designed to visually show the placement of each robot, their dependencies, and the locations of abnormalities. The input is a dependency list from the analysis results, and the output is a system configuration diagram.

[0228] Step 6:

[0229] Configuration visualization

[0230] The server sends the generated system configuration diagram to the user's device. The device displays the diagram in an interactive format, allowing the user to zoom, tap, and view detailed information. The input is the system configuration diagram data, and the output is interactive visual information displayed on the device.

[0231] Step 7:

[0232] Operational status monitoring and notification

[0233] The server monitors the system's operational status in real time and sends a notification to the user's device if it detects an abnormality. For example, if the robot's memory usage increases sharply, an alert is sent via push notification. The input to this process is real-time monitoring data, and the output is an alert notification sent to the user when an abnormality occurs.

[0234] 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.

[0235] This invention combines a system that uses a generative AI model to analyze system codes and logs, visualizes and monitors system configuration diagrams, and an emotion engine that recognizes user emotions. This system not only enables users to quickly understand the overall system and maintain proper operating conditions, but also adjusts the interface based on the user's emotions, further improving usability.

[0236] System Overview

[0237] The system includes the following key features:

[0238] 1. Data Collection

[0239] The user uploads the code file, log file, specification, or manual that he / she wants to analyze to the server.

[0240] 2. Data Analysis

[0241] The server analyzes the received files using a generative AI model to extract code structure, log patterns, and specification contents.

[0242] 3. System configuration diagram generation

[0243] Based on the analysis results, the server generates a system configuration diagram that shows the dependencies and communication paths between each component of the system.

[0244] 4. Visualization

[0245] The terminal visually displays an interactive system configuration diagram to the user, allowing the user to manipulate the diagram.

[0246] 5. Surveillance

[0247] The server monitors the system's operational status in real time and notifies the user if an abnormality is detected.

[0248] 6. Emotion recognition

[0249] The server uses an emotion engine to analyze emotions from the user's facial expressions and voice.

[0250] 7. User interface adjustments

[0251] The server adjusts the user interface based on the analyzed emotions to improve usability.

[0252] Program processing

[0253] 1. Data Collection

[0254] Users log into the system's web portal, select and upload the files they want to analyze, and the server receives the data, which can be code files, log files, specifications, or manuals.

[0255] 2. Data Analysis

[0256] The server uses a generative AI model to analyze the uploaded files, extracting the structure and dependencies of functions and classes in the code and identifying error patterns in log files.

[0257] 3. System configuration diagram generation

[0258] The server uses the analysis results to generate a system diagram that shows the relationships between each component. The system diagram visually displays how each part of the system interacts.

[0259] 4. Visualization

[0260] The device displays the generated system diagram in the user's browser. The user can click on the diagram to view detailed information about a specific module or component. For example, clicking on module A displays the functions and dependencies associated with that module.

[0261] 5. Surveillance

[0262] The server monitors the system's operational status in real time, and if any abnormal patterns or errors are detected, an alert notification is sent to the user and detailed information is displayed on the dashboard.

[0263] 6. Emotion recognition

[0264] The server uses an emotion engine to analyze the user's facial expressions and voice to recognize their current emotional state. For example, if the user is feeling stressed, that information will be analyzed.

[0265] 7. User interface adjustments

[0266] The server dynamically adjusts the user interface based on the analysis results obtained from the emotion engine. For example, if the user is feeling stressed, the interface will be simplified or appropriate support will be provided.

[0267] Specific examples

[0268] 1. Data Collection

[0269] A user logs into the system's web portal and uploads the latest application code file (e.g., app_code.py) and system log file (e.g., server_log.txt).

[0270] 2. Data Analysis

[0271] The server inputs app_code.py and server_log.txt into the generative AI model, which analyzes code dependencies and log error patterns.

[0272] 3. System configuration diagram generation

[0273] The server generates a system configuration diagram based on the analysis results and visually displays the interdependencies of each module and component.

[0274] 4. Visualization

[0275] The terminal displays a system configuration diagram on the user's screen, and the user can click on the diagram to view detailed information about a specific module.

[0276] 5. Surveillance

[0277] The server monitors the system in real time and issues an alert when it detects an abnormality. Information such as sudden increases in memory usage and CPU overload is displayed on the dashboard.

[0278] 6. Emotion recognition

[0279] The server uses an emotion engine to analyze the user's facial expressions and voice to understand their emotional state. For example, if the user is irritated, that emotional data will be analyzed.

[0280] 7. User interface adjustments

[0281] The server adjusts the interface based on the user's emotional data. If the user is feeling stressed, the system automatically simplifies operation and reduces the amount of information presented to the user.

[0282] As described above, the system of the present invention combines a generative AI model and an emotion engine, allowing users to quickly understand the overall system and maintain appropriate operation. Furthermore, usability is improved by adjusting the interface according to the user's emotions.

[0283] The processing flow will be explained below.

[0284] Step 1:

[0285] The user logs into the system's web portal and clicks the "Upload analysis file" button.

[0286] Step 2:

[0287] The user selects the files they want to analyze (e.g., source code files, log files, specifications, or manuals) and uploads them to the server.

[0288] Step 3:

[0289] The server receives the uploaded file and automatically identifies the file format and content, for example, checking whether it is a code file, log file, or specification document.

[0290] Step 4:

[0291] The server inputs the received files into a generative AI model, which analyzes the code structure, function call relationships, and dependencies. For example, it verifies that function A calls function B, or that module X depends on library Y.

[0292] Step 5:

[0293] The server analyzes the log file entries to identify the frequency and occurrence patterns of errors and warnings, for example, by counting the frequency of the error message "ERROR" and the warning message "WARNING."

[0294] Step 6:

[0295] The server analyzes the text of specifications and manuals and extracts important points and constraints of the system specifications.

[0296] Step 7:

[0297] Based on the analysis results, the server generates a data structure that shows the dependencies and communication paths between components. For example, it represents the dependencies and API call relationships between modules using nodes and edges.

[0298] Step 8:

[0299] The server generates a system configuration diagram based on the generated data structure. This diagram includes the relationships between modules and components, the locations of errors, and so on.

[0300] Step 9:

[0301] The terminal displays the system configuration diagram in the user's browser, and the user can interactively click on each node or edge to display detailed information.

[0302] Step 10:

[0303] Users can explore the diagram and learn more about specific modules and components. For example, clicking on Module A displays the functions and dependencies associated with that module.

[0304] Step 11:

[0305] The server monitors the system's operation in real time, checking for new log entries and changes in system state, and running algorithms to detect abnormal patterns and errors.

[0306] Step 12:

[0307] If the server detects an abnormality, it will send an alert to the user, providing them with a notification containing detailed information about the abnormality and the extent of its impact.

[0308] Step 13:

[0309] Users receive alerts and can view detailed information on a dashboard, such as memory usage spikes or CPU overloads.

[0310] Step 14:

[0311] The server uses an emotion engine to analyze the user's facial expressions and voice to recognize their current emotional state. For example, if the user is feeling stressed, that information is obtained.

[0312] Step 15:

[0313] The server adjusts the interface based on the analyzed emotions. For example, if the user is feeling stressed, the server sets the interface to be simpler.

[0314] Step 16:

[0315] The server collects user feedback and accumulates data to improve the system's usability, such as recording the user's operation history and changes in emotional state.

[0316] In this way, the user can understand the overall structure and operational status of the system, and can use an interface that is adapted to his or her emotional state.

[0317] Example 2

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

[0319] Conventional system analysis tools were capable of visualizing the analysis results of system code and logs, but they did not adjust the interface to take user emotions into consideration. As a result, when users felt stressed or dissatisfied with the interface, they were unable to respond appropriately, which sometimes resulted in usability issues. In addition, they lacked the ability to monitor the system's operational status in real time, making it difficult to detect abnormalities early and respond appropriately.

[0320] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, means for monitoring the operation status of the system, means for recognizing user emotions, and means for adjusting the user interface based on the user emotions. This makes it possible to appropriately monitor the operation status of the system and quickly respond to abnormal situations while improving usability.

[0321] "Means for receiving uploaded data" refers to the function of receiving data in the process of a user selecting a file and transferring it to the server.

[0322] "Means for analysis using generative AI models" refers to a function that uses artificial intelligence to analyze code structure and patterns based on uploaded data.

[0323] "Means for generating a system configuration diagram based on the analysis results" refers to the function of creating a diagram that visually shows the configuration of the entire system from the analysis results of the generative AI model.

[0324] "Means for visualizing the generated system configuration diagram" refers to a function that displays the generated system configuration diagram on the user's terminal and allows the user to interactively manipulate the diagram.

[0325] "Means for monitoring the operational status of the system" refers to the function of checking in real time whether the system is operating normally or if any abnormalities have occurred, and sending alerts as necessary.

[0326] "Means for recognizing the user's emotions" refers to a function that analyzes the user's facial expressions and voice data to identify their current emotional state.

[0327] "Means for adjusting the user interface based on the user's emotions" refers to a function that dynamically changes the interface in response to the detected user's emotions, thereby improving usability.

[0328] This invention is a system that uses a generative AI model to analyze code files and log files uploaded by users, and generates, visualizes, and monitors system configuration diagrams. It also aims to improve usability by recognizing user emotions and dynamically adjusting the interface.

[0329] Program Generation and Processing

[0330] Hardware and software used

[0331] Hardware

[0332] Server: a computer with a powerful processor and a large amount of memory

[0333] User device: PC or tablet with internet access

[0334] Webcam: A camera for capturing the user's facial expressions

[0335] Microphone: A microphone for capturing the user's voice

[0336] software

[0337] Generative AI models: for example, GPT-3 (registered trademark)

[0338] Emotion recognition engine: For example, Amazon Rekognition

[0339] Web server: A server that provides file upload functionality and analysis result display functionality

[0340] Log Analysis Tools: Tools for analyzing log files

[0341] System processing flow

[0342] 1. Data Collection

[0343] A user logs into the system's web portal and uploads the code file (e.g., app_code.py) and log file (e.g., server_log.txt) they want to analyze.

[0344] The server receives the uploaded file and stores it in storage.

[0345] 2. Data Analysis

[0346] The server reads the file and enters a prompt sentence into the generative AI model to begin analysis.

[0347] For example: "Analyze the following code file and identify the structure and dependencies of functions and classes."

[0348] The server also passes the contents of the log file to the generative AI model to analyze error patterns.

[0349] For example: "Please analyze the following log files and identify any error patterns or anomalies."

[0350] 3. System configuration diagram generation

[0351] Based on the analysis results of the AI ​​model generated by the server, a system configuration diagram is created showing the dependencies and communication paths between each component.

[0352] A configuration diagram visually represents the interactions between modules and components.

[0353] 4. Visualization

[0354] The terminal displays the system configuration diagram on the user's browser.

[0355] The user can navigate the diagram and view detailed information about specific modules and components.

[0356] For example, when a user clicks on module A, it displays the functions and dependencies associated with that module.

[0357] 5. Surveillance

[0358] The server monitors the system's operational status in real time, and if it detects an abnormality, it generates an alert and notifies the user.

[0359] For example, it will notify you if an abnormal pattern such as a sudden increase in memory usage or CPU overload is detected.

[0360] 6. Emotion recognition

[0361] The server acquires the user's facial expressions and voice data and analyzes them using an emotion recognition engine.

[0362] Example: "Analyze whether the user is feeling stressed."

[0363] The server identifies the user's emotion based on the acquired emotion data.

[0364] 7. User interface adjustments

[0365] The server dynamically adjusts the user interface based on the emotion recognition results.

[0366] Example: If the user is stressed, simplify the interface or provide appropriate support features.

[0367] By combining a generative AI model and an emotion recognition engine, the system of this invention improves usability and enables appropriate monitoring and management of system operations, allowing users to quickly understand the overall system and respond quickly to abnormal situations.

[0368] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0369] Step 1: Data collection

[0370] A user logs into the system's web portal, selects and uploads the code file (e.g., app_code.py) and log file (e.g., server_log.txt) they want to analyze.

[0371] The server receives these files and stores them in storage.

[0372] Input: User-uploaded code and log files

[0373] Output: File saved on the server

[0374] Step 2: Data analysis

[0375] The server reads the saved file and inputs a prompt to the generative AI model (e.g., GPT-3) to begin analysis.

[0376] Specifically, the server inputs the following prompts into the generative AI model:

[0377] Prompt: "Analyze the following code file and identify the structure and dependencies of functions and classes."

[0378] The server obtains the analysis results from the output of the generative AI model.

[0379] Do the same for the log files:

[0380] Prompt: "Analyze the following log files and identify any error patterns or anomalies."

[0381] Input: Code files and log files stored on the server

[0382] Data processing: Performing analysis using generative AI models

[0383] Output: Analysis results of code structure and dependencies, and error patterns in logs

[0384] Step 3: Generate a system configuration diagram

[0385] The server generates a system configuration diagram based on the analysis results of the generated AI model.

[0386] Create a visual diagram showing the dependencies and communication paths of each component.

[0387] Input: Analysis results (code structure, dependencies, log error patterns)

[0388] Data processing: Create a system configuration diagram using a system configuration diagram generation algorithm

[0389] Output: System configuration diagram

[0390] Step 4: Visualization

[0391] The terminal creates an HTML page for displaying the system configuration diagram on the user's browser.

[0392] The terminal displays the system configuration diagram on the user's browser, allowing interactive operation.

[0393] The user can navigate the diagram and view detailed information about specific modules and components.

[0394] Input: System configuration diagram

[0395] Data processing: HTML page generation and diagram display

[0396] Output: System diagram displayed in the user's browser

[0397] Step 5: Monitoring

[0398] The server runs a script that monitors the system's operational status in real time.

[0399] If an anomaly is detected, the server generates an alert and notifies the user.

[0400] For example, abnormal patterns such as sudden increases in memory usage and CPU overloads are detected.

[0401] Input: Real-time data from the system

[0402] Data calculation: Identify anomalies using anomaly detection algorithms

[0403] Output: Alert notification sent to user

[0404] Step 6: Emotion Recognition

[0405] The server captures the user's webcam video and audio data.

[0406] The server analyzes the user's emotions using an emotion recognition engine (e.g., Amazon Rekognition).

[0407] As a specific example, the server identifies stress or irritation from the user's facial expression.

[0408] Input: Webcam video and audio data

[0409] Data calculation: Emotion analysis using emotion recognition engine

[0410] Output: User emotion data

[0411] Step 7: Adjust the user interface

[0412] The server dynamically adjusts the user interface based on the emotion recognition results.

[0413] For example, if a user is feeling stressed, the interface can be simplified and appropriate support functions provided.

[0414] Input: User emotion data

[0415] Data processing: Using interface adjustment algorithms

[0416] Output: A tailored user interface

[0417] At each step, specific data processing or calculations are performed based on the input data, resulting in an output that is used in the next step, enabling the system to achieve real-time monitoring and anomaly detection while improving usability.

[0418] (Application example 2)

[0419] 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."

[0420] Factory robots are required to reduce operator stress and improve operability while providing efficient operation and real-time monitoring. However, current systems make it difficult to visually grasp the robot's operating status, and they do not dynamically adjust the interface to take into account the operator's emotional state. This increases operator stress and reduces productivity.

[0421] 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.

[0422] In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, means for monitoring the operation status of the system, means for recognizing a user's emotion, and means for adjusting the user interface based on the recognized emotion, thereby enabling an operator to visually grasp the operation status of a factory robot in real time and adjust the interface according to the operator's emotional state.

[0423] The "means for receiving uploaded data" is a function that allows factory operators to send data such as robot operation logs and operating programs to a server, and for the server to receive it.

[0424] "Means of analysis using generative AI models" refers to the use of AI technology to analyze patterns and trends within collected data.

[0425] The "means for generating a system configuration diagram" is a function for creating a diagram that visually represents the relationships and operating status between robots within a factory based on the analysis results.

[0426] "Means for visualizing the generated system configuration diagram" is a function that displays the generated system configuration diagram on the operator's terminal, making it visually easy to understand.

[0427] The "means for monitoring the system's operational status" is a function that continuously monitors the operating status and errors of factory robots in real time, and detects and notifies users if an abnormality occurs.

[0428] "Means for recognizing user emotions" refers to a function that uses devices such as cameras and microphones to analyze the operator's facial expressions and voice to understand their emotional state.

[0429] The "means for adjusting the user interface based on the recognized emotion" is a function that dynamically changes the interface to improve usability in accordance with the recognized emotional state of the operator.

[0430] MODE FOR CARRYING OUT THE INVENTION

[0431] This invention is a system for improving the efficiency of factory robot operations and monitoring them in real time. Furthermore, it aims to reduce operator stress and improve productivity by recognizing the emotions of factory operators and dynamically adjusting the operation interface. This system is composed of the following main hardware and software:

[0432] Hardware

[0433] Device: Any device that can connect to the internet (e.g. smartphone, tablet, PC)

[0434] Camera and microphone: Sensor devices for capturing the operator's facial expressions and voice.

[0435] software

[0436] Generative AI model (e.g., GPT-4): AI technology used to analyze uploaded data

[0437] Emotion recognition engine (e.g., Microsoft® Azure® Face API): an engine for analyzing the emotional state of the operator

[0438] Database (e.g., MySQL (registered trademark)): A database system for storing analysis results and log data

[0439] Web server (e.g., Apache (registered trademark)): A server for hosting the system's core programs

[0440] Real-time monitoring tools (e.g., ElasticSearch (registered trademark), Kibana): Tools for monitoring the operation status of the system

[0441] System program processing

[0442] 1. Data Collection

[0443] Users log in to a dedicated web portal and upload the factory robot's operation log and operating program (e.g., robot_log.txt, robot_program.py).

[0444] 2. Data Analysis

[0445] The server inputs the received data into a generative AI model (e.g., GPT-4) and analyzes the data for patterns and errors.

[0446] 3. System configuration diagram generation

[0447] Based on the analysis results, the server generates a system configuration diagram showing the operational status of the robots within the factory.

[0448] 4. Visualization

[0449] The terminal interactively displays the generated system configuration diagram, allowing the operator to visually check detailed information about each robot.

[0450] 5. Surveillance

[0451] The server monitors the operational status of factory robots in real time and sends an alert to the operator if an abnormality is detected. For example, information on sudden increases in memory usage or CPU overload is displayed on the dashboard.

[0452] 6. Emotion recognition

[0453] The server uses an emotion recognition engine (e.g., Microsoft Azure Face API) to analyze data obtained from the camera and microphone to understand the operator's emotional state. For example, if the operator is feeling stressed, that information will be analyzed.

[0454] 7. User interface adjustments

[0455] The server dynamically adjusts the user interface based on the analysis results obtained from the emotion recognition engine. For example, if the operator is feeling stressed, the interface will be simplified and the displayed information will be reduced, improving usability.

[0456] Specific examples

[0457] 1. Example prompt

[0458] Data Analysis prompt:

[0459] "Analyze the following robot operation log to identify errors and visualize behavioral patterns. Log data: robot_log.txt"

[0460] System configuration diagram generation prompt:

[0461] "Please generate a system configuration diagram for the factory robot based on the analysis results below. Analysis data: analysis results.json"

[0462] Through a series of processes

[0463] This system allows operators to visually grasp the operating status of factory robots in real time and adjusts the interface according to their emotional state, reducing operator stress and improving productivity and usability.

[0464] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0465] Step 1:

[0466] Data collection

[0467] The user logs in to a dedicated web portal and uploads the factory robot's operation log (e.g., robot_log.txt) and operation program (e.g., robot_program.py). The input is the operation log and operation program files, and the server receives these files as output. Specifically, the user accesses the web portal in a browser and uploads the required files using the file selection dialog.

[0468] Step 2:

[0469] Data analysis

[0470] The server inputs the received data into a generative AI model (e.g., GPT-4) and analyzes patterns and errors within the data. The input is the uploaded log file and operation program, and the analysis results are obtained as output. Specifically, the server sends the received data to the GPT-4 interface and enters a data analysis prompt: "Analyze the following robot operation log, identify errors, and visualize behavioral patterns. Log data: robot_log.txt."

[0471] Step 3:

[0472] System configuration diagram generation

[0473] Based on the analysis results, the server generates a system configuration diagram showing the operational status of the factory robots. The input is the analysis results, and the output is an interactive system configuration diagram. Specifically, the server generates the configuration diagram using a JavaScript (registered trademark) library (e.g., D3.js). "Please generate a system configuration diagram for the factory robots based on the following analysis results. Analysis data: Analysis results.json"

[0474] Step 4:

[0475] Visualization

[0476] The terminal interactively displays the generated system configuration diagram, allowing the operator to visually check detailed information about each robot. The input is the generated configuration diagram, and the output is visual information displayed on the operator's terminal. Specifically, the terminal displays the configuration diagram in a web browser, and the user can click to check detailed information.

[0477] Step 5:

[0478] Monitoring

[0479] The server monitors the operational status of factory robots in real time and sends an alert to the operator if an abnormality is detected. The input is real-time log data, and the output is an alert that an abnormality has been detected. Specifically, the server monitors the log data using Elasticsearch and Kibana, and if an abnormality is detected, it notifies the operator via Slack or email.

[0480] Step 6:

[0481] emotion recognition

[0482] The server uses an emotion recognition engine (e.g., Microsoft Azure Face API) to analyze data acquired from the camera and microphone to understand the operator's emotional state. The input is real-time data from the camera and microphone, and the output is an evaluation of the operator's emotional state. Specifically, the server sends real-time data to the emotion recognition engine and inputs a prompt such as "Please analyze the operator's emotional state."

[0483] Step 7:

[0484] User Interface Adjustments

[0485] The server dynamically adjusts the user interface based on the analysis results obtained from the emotion recognition engine. The input is the emotion analysis results, and the output is an adjusted user interface displayed on the terminal. Specifically, the server uses JavaScript and React.js to change the interface and adjust the displayed information appropriately according to the operator's stress level.

[0486] 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.

[0487] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0488] 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.

[0489] [Second embodiment]

[0490] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0491] 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.

[0492] 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).

[0493] 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.

[0494] 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.

[0495] 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).

[0496] 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. 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.

[0497] 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.

[0498] 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.

[0499] 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.

[0500] In the smart glasses 214, 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.

[0501] 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."

[0502] The present invention provides a system for visualizing and monitoring the configuration of a system that has been in operation for a long period of time, thereby supporting efficient analysis, modification, and operation of the system.

[0503] System Overview

[0504] The system includes the following key features:

[0505] 1. Data Collection

[0506] The user uploads the code file, log file, specification, or manual that he / she wants to analyze to the server.

[0507] 2. Data Analysis

[0508] The server analyzes the received files using a generative AI model to extract code structure, log patterns, and specification contents.

[0509] 3. System configuration diagram generation

[0510] Based on the analysis results, the server generates a system configuration diagram that shows the dependencies and communication paths between each component of the system.

[0511] 4. Visualization

[0512] The terminal visually displays an interactive system configuration diagram to the user, allowing the user to manipulate the diagram.

[0513] 5. Surveillance

[0514] The server monitors the system's operational status in real time and notifies the user if an abnormality is detected.

[0515] Program processing

[0516] 1. Data Collection

[0517] Users log in to the system's web portal and select and upload the files they want to analyze, which can be in a variety of formats, including source code, log files, specifications, and manuals.

[0518] 2. Data Analysis

[0519] The server receives the uploaded files and identifies their data format. It uses a generative AI model to analyze the code structure and extract dependencies between functions, classes, and modules. For log files, it analyzes entries and identifies patterns of errors and warnings.

[0520] 3. System configuration diagram generation

[0521] The server aggregates the analysis results and generates a data structure that illustrates the relationships between components. This data structure is then used to generate a system diagram, which visually shows how the parts of the system interact with each other.

[0522] 4. Visualization

[0523] The terminal displays the generated system diagram in the user's browser. The user can interact with the diagram and view detailed information. For example, clicking on a specific module displays details about its dependencies and functions.

[0524] 5. Surveillance

[0525] The server monitors the system's operational status in real time and detects abnormal patterns and errors. If an abnormality is detected, the user is notified and a warning message is displayed on the dashboard. At the same time, detailed information about the abnormality and the scope of its impact are also reported to the user.

[0526] Specific examples

[0527] 1. Data Collection

[0528] A user logs into the system's web portal and uploads the latest application code file (e.g., app_code.py) and system log file (e.g., server_log.txt).

[0529] 2. Data Analysis

[0530] The server receives app_code.py and server_log.txt, inputs these files into the AI ​​model, and begins analysis. The AI ​​model extracts function dependencies within the code and identifies error patterns from the log file.

[0531] 3. System configuration diagram generation

[0532] Based on the analysis results, the server generates a system configuration diagram showing the relationships between functions, classes, and modules. This configuration diagram visually displays dependencies between modules and error locations.

[0533] 4. Visualization

[0534] The device displays a system diagram in the user's browser. The user can click on the diagram to view details of specific modules or functions. For example, clicking on Module A displays the associated functions and dependencies.

[0535] 5. Surveillance

[0536] The server performs real-time monitoring of the system and displays a warning on the dashboard if it detects any abnormal behavior. For example, if memory usage spikes, an alert is generated, showing the affected module and how to address it.

[0537] In this way, the system of the present invention enables the user to quickly understand the entire system and appropriately monitor the operational status, thereby supporting efficient system modification and operation.

[0538] The processing flow will be explained below.

[0539] Step 1:

[0540] The user logs into the system's web portal and clicks the "Upload analysis file" button.

[0541] Step 2:

[0542] The user selects the files they want to analyze (e.g., source code files, log files, specifications, or manuals) and uploads them to the server.

[0543] Step 3:

[0544] The server receives the uploaded file and automatically identifies the file format and content, for example, checking whether it is a code file, log file, or specification document.

[0545] Step 4:

[0546] The server inputs the received files into a generative AI model, which analyzes the code structure, function call relationships, and dependencies. For example, it extracts that function A calls function B, or that module X depends on library Y.

[0547] Step 5:

[0548] The server analyzes the log file entries to identify the frequency and occurrence patterns of errors and warnings, for example, the frequency of occurrence of the error message "ERROR" and the warning message "WARNING".

[0549] Step 6:

[0550] The server analyzes the text of specifications and manuals and extracts important points and constraints of the system specifications.

[0551] Step 7:

[0552] Based on the analysis results, the server generates a data structure that shows the dependencies and communication paths between each component. The dependencies and API call relationships between each module are represented by nodes and edges.

[0553] Step 8:

[0554] The server generates a system configuration diagram based on the generated data structure. This diagram includes the relationships between modules and components, the locations of errors, and so on.

[0555] Step 9:

[0556] The terminal displays the system configuration diagram in the user's browser, and the user can interactively click on each node or edge to display detailed information.

[0557] Step 10:

[0558] Users can explore the diagram and learn more about specific modules and components. For example, clicking on Module A displays the functions and dependencies associated with that module.

[0559] Step 11:

[0560] The server monitors the system's operation in real time, checking for new log entries and changes in system state, and running algorithms to detect abnormal patterns and errors.

[0561] Step 12:

[0562] If the server detects an abnormality, it will send an alert to the user, providing them with a notification containing detailed information about the abnormality and the extent of its impact.

[0563] Step 13:

[0564] Users receive alerts and can view detailed information in a dashboard, such as memory usage spikes or CPU overloads.

[0565] As described above, by performing specific processing for each step, the user can easily grasp the overall structure and operational status of the system, enabling efficient modification and operation.

[0566] Example 1

[0567] 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."

[0568] With existing systems, it is difficult to quickly grasp the overall picture of the system and efficiently monitor and modify it. In particular, in complex systems that have been in operation for a long time, it is important to visualize the dependencies and communication paths between components and monitor the operational status in real time, but there are currently no easy ways to achieve this. A notification system is also needed to respond instantly when an abnormality occurs.

[0569] 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.

[0570] In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, means for monitoring the system's operational status, means for selecting uploaded data after user authentication, means for interactively displaying details of the configuration diagram to the user, and means for notifying the user when an abnormality is detected. This allows the user to quickly grasp the overall picture of the system and efficiently analyze, repair, and operate it. Real-time monitoring of the system's operational status and immediate notification of abnormalities enable early detection and response to problems.

[0571] "Uploaded Data" refers to electronic data such as source code, log files, specifications, or manuals that a user sends to the system.

[0572] "Means of receiving" refers to the functions and processes by which the server obtains uploaded data.

[0573] "Generative AI models" refer to artificial intelligence algorithms used to automate the analysis of data and extract advanced information.

[0574] "Means for analyzing" refers to the functions or processes used to analyze received data and extract meaningful information or patterns.

[0575] A "system configuration diagram" is a diagram that visually shows the dependencies and communication paths between each component within a system.

[0576] "Visualization means" refers to the functions and processes for visually displaying the generated system configuration diagram to the user.

[0577] "Means for monitoring the operational status of the system" refers to functions and processes for monitoring in real time whether the system is operating normally and detecting abnormalities.

[0578] "Means for selecting uploaded data after authentication" refers to the functionality or process for selecting and using data within the system after a user has provided valid authentication information.

[0579] "Means for interactively displaying details of the configuration diagram" refers to functions and processes that allow a user to manipulate the system configuration diagram and dynamically view detailed information.

[0580] "Means for notifying users when an abnormality is detected" refers to functions and processes for quickly notifying users of an abnormality when it is discovered during system monitoring.

[0581] This invention relates to a system for visualizing and monitoring system configurations. This system receives uploaded data and analyzes it using a generative AI model. It then generates a system configuration diagram based on the analysis results and provides it visually to the user. It also includes a function to monitor the system's operational status in real time and notify the user when an abnormality is detected.

[0582] 1. Data Collection and Reception

[0583] Users log in to the system through a web portal and upload the source code, log files, specifications, or manuals they want to analyze. For example, a user can select and upload files named app_code.py and server_log.txt. These data are then transferred to the server.

[0584] 2. Data Analysis

[0585] The server receives the uploaded data and feeds it into a generative AI model that extracts function dependencies in the code and identifies error patterns in log files. The hardware used is a dedicated server, and the software includes a deep learning framework.

[0586] Example: The server generates a prompt statement saying "Start code analysis" and sends it to the generative AI model.

[0587] 3. Generating a system configuration diagram

[0588] The server generates a data structure for a system configuration diagram based on the results of the data analysis. This configuration diagram includes dependencies and communication paths between each component of the system. The server then draws a visual system configuration diagram based on this data structure.

[0589] 4. Visualization

[0590] The terminal displays the generated system diagram in the user's browser. The user can click on the diagram to interactively view the details of a specific module or component. For example, when the user clicks on module A, a pop-up appears with details of its functions and dependencies.

[0591] 5. Real-time monitoring and notifications

[0592] The server continuously monitors the system's operational status. If it detects abnormal behavior or an error pattern, it notifies the user and displays a warning message on the dashboard. The hardware used is a module dedicated to monitoring, and the software includes a monitoring tool. For example, if the server detects a sudden increase in memory usage, it displays a warning message on the dashboard saying, "Memory usage has increased sharply, affecting module A."

[0593] In this way, this system allows users to quickly grasp the overall picture of the system and efficiently analyze, repair, and operate it.In addition, real-time monitoring of the system's operating status and immediate notification of abnormalities enable early detection and response to problems.

[0594] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0595] Step 1:

[0596] The user accesses the web portal and enters their credentials. If the correct credentials are entered, the user is able to access the dashboard.

[0597] Input: Username, Password

[0598] Output: Authentication token, dashboard screen

[0599] Specific operation: The user accesses "example.com", enters their username and password, and presses the "Login" button.

[0600] Step 2:

[0601] The user clicks the upload button on the dashboard, selects the file they want to analyze, and uploads it. This file is then sent to the server.

[0602] Input: File to be analyzed (e.g. app_code.py, server_log.txt)

[0603] Output: A confirmation message for the uploaded file

[0604] Specific behavior: The user clicks the "File Upload" button, selects app_code.py and server_log.txt, and then clicks the "Upload" button.

[0605] Step 3:

[0606] The server receives the uploaded files, identifies the data format of each file, and inputs these files into a generative AI model to perform data analysis.

[0607] Input: Uploaded file

[0608] Output: Analysis results (code dependencies, log error patterns)

[0609] Specific operation: The server passes app_code.py and server_log.txt to the generated AI model, generates a prompt statement saying "Start code analysis", and sends it to the AI ​​model.

[0610] Step 4:

[0611] Based on the results of the data analysis, the server generates a data structure for a system configuration diagram, which includes dependencies and communication paths between components.

[0612] Input: Analysis results (code dependencies, log error patterns)

[0613] Output: System configuration diagram data structure

[0614] Specific operation: The server executes the "process for generating configuration diagram data," registers dependencies and communication paths in a database, and draws a system configuration diagram.

[0615] Step 5:

[0616] The terminal visually displays the generated system configuration diagram in the user's browser, and the user can click on the diagram to view detailed information.

[0617] Input: System configuration diagram data structure

[0618] Output: System configuration diagram on browser

[0619] Specific operation: The terminal displays a system configuration diagram on the browser, and when the user clicks on a specific module, detailed information related to that module will be displayed in a pop-up.

[0620] Step 6:

[0621] The server monitors the system's operational status in real time, detecting abnormal behavior and error patterns. If an abnormality occurs, it notifies the user and displays a warning message on the dashboard.

[0622] Input: Real-time system data

[0623] Output: Anomaly detection, warning message

[0624] Specific operation: When the server performs "real-time monitoring" and detects a sudden increase in memory usage, a warning message will be displayed on the dashboard stating "Memory usage has increased sharply, affecting module A."

[0625] This allows users to efficiently understand the system configuration and operational status, and to respond quickly when a problem occurs.

[0626] (Application example 1)

[0627] 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."

[0628] With conventional systems, it is difficult to efficiently visualize and analyze the configuration of systems that have been in operation for a long time, which has resulted in the problem of system operation and modification taking a great deal of time and effort.In addition, early detection of abnormalities and real-time operational monitoring are insufficient, resulting in problems such as a decline in system stability and reliability.

[0629] 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.

[0630] In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, and means for monitoring the system's operational status and notifying when an abnormality is detected. This enables efficient visualization and analysis of the system configuration, and real-time operational monitoring and abnormality detection.

[0631] The "means for receiving uploaded data" is a function for importing data sent by a user into the server.

[0632] "Means for analysis using a generative AI model" refers to a function that analyzes uploaded data using an artificial intelligence model and extracts data structures and patterns.

[0633] The "means for generating a system configuration diagram" is a function that creates a diagram that visually represents the relationships between each component of the system based on the results of the analyzed data.

[0634] The "means for visualizing the system configuration diagram" is a function that allows the user to interactively display the generated system configuration diagram and operate it.

[0635] "Means for monitoring the system's operational status and notifying users if an abnormality is detected" refers to a function that monitors the system's operation in real time and sends an alert to users if an abnormality occurs.

[0636] MODE FOR CARRYING OUT THE INVENTION

[0637] The present invention provides a system that efficiently visualizes the operation of factory robots, enabling early detection of abnormalities and real-time operation monitoring. Hereinafter, embodiments of the present invention will be described.

[0638] System configuration

[0639] The system primarily consists of the following major components:

[0640] 1. Server

[0641] 2. User device (smartphone, etc.)

[0642] 3. Operational data collection device for factory robots

[0643] System Features

[0644] 1. Means of receiving uploaded data:

[0645] The user terminal receives the factory robot's operational data (e.g., log files and operation history data) from the collection device and uploads it to the cloud server, which receives and stores this data.

[0646] 2. Means of analyzing received data using a generative AI model:

[0647] The server inputs the uploaded data into a generative AI model and begins analysis. The AI ​​model uses a high-performance language model such as GPT-4. Through analysis, patterns and anomalies are identified within the operational data.

[0648] 3. How to generate a system diagram based on the analysis results:

[0649] Based on the analysis results, the server generates a system configuration diagram that shows the operational status and dependencies of each robot in the factory. The system configuration diagram visually displays the location, communication paths, and operational status of each robot.

[0650] 4. A way to visualize the generated system diagram:

[0651] The generated system configuration diagram is sent to the user's device and displayed in an interactive format, allowing the user to tap and zoom to view detailed information.

[0652] 5. Monitoring the system's operational status and notifying you if an abnormality is detected:

[0653] The server monitors operational data in real time, and if an abnormality is detected, it sends an alert via push notification to the user's device, allowing the user to respond promptly without missing the timing of the abnormality.

[0654] Specific examples of hardware and software used

[0655] Server: Cloud server (e.g. Amazon Web Services)

[0656] User device: Smartphone (iOS or Android)

[0657] Generative AI model: GPT-4 (OpenAI)

[0658] Specific examples

[0659] 1. Data Collection Example:

[0660] The user device receives the latest factory robot operation data (e.g., robot_log.txt) and uploads it to the cloud server.

[0661] 2. Data analysis example:

[0662] The server receives robot_log.txt and begins analyzing it with GPT-4, which extracts dependencies between specific functions and abnormal patterns.

[0663] 3. Example of system configuration diagram generation:

[0664] The server generates a system configuration diagram based on the analysis results, visually representing the operational status and dependencies of each robot.

[0665] 4. Visualization example:

[0666] The system configuration diagram is sent to the user's device and displayed in an interactive format on the device screen, where the user can tap on a specific robot to view more information.

[0667] 5. Monitoring and Notification Examples:

[0668] The server monitors in real time and sends a push notification to the user's device if an abnormality is detected. Example: "Robot 123's memory usage is increasing rapidly. Please check immediately."

[0669] Prompt Sentence Examples

[0670] "Please analyze the following robot operation log data and clearly indicate the dependencies between functions and the location of the error. Log data: [Part of the detailed log data]"

[0671] In this way, it becomes possible to efficiently monitor the operation of factory robots and quickly detect abnormalities.

[0672] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0673] Step 1:

[0674] Data collection

[0675] The user uploads the operation data (e.g., log files) of the factory robot to the user terminal. The uploaded data includes operation history data, error logs, performance data, etc. The user terminal sends this data to the cloud server. The input is the robot operation data (in file format), and the output is the data stored on the cloud server.

[0676] Step 2:

[0677] Data reception

[0678] The server receives data sent from the user's device and stores it in a database. In particular, it checks whether the received data has been uploaded correctly and converts it into the required data format. During this process, detailed log information and error messages are entered, and this is converted into an internal database format and stored.

[0679] Step 3:

[0680] Data analysis preparation

[0681] The server prepares the received data for input to a generative AI model for analysis. Specifically, it converts the data into an appropriate format and generates a prompt. For example, it prepares a prompt such as, "Analyze this robot log and extract behavior patterns and dependencies." The input is the converted log information, and the output is the prompt and converted data that are input to the generative AI model.

[0682] Step 4:

[0683] Data analysis

[0684] The server analyzes the data using a generative AI model (e.g., GPT-4). Here, the prompt sentence and the converted data are input into the AI ​​model, and as a result, the robot's behavior patterns, dependencies, error patterns, etc. are extracted. The input for the analysis is the prompt sentence and data, and the output is the analysis results, such as a dependency list and error log patterns.

[0685] Step 5:

[0686] System configuration diagram generation

[0687] The server generates a system configuration diagram based on the analysis results. This configuration diagram is designed to visually show the placement of each robot, their dependencies, and the locations of abnormalities. The input is a dependency list from the analysis results, and the output is a system configuration diagram.

[0688] Step 6:

[0689] Configuration visualization

[0690] The server sends the generated system configuration diagram to the user's device. The device displays the diagram in an interactive format, allowing the user to zoom, tap, and view detailed information. The input is the system configuration diagram data, and the output is interactive visual information displayed on the device.

[0691] Step 7:

[0692] Operational status monitoring and notification

[0693] The server monitors the system's operational status in real time and sends a notification to the user's device if it detects an abnormality. For example, if the robot's memory usage increases sharply, an alert is sent via push notification. The input to this process is real-time monitoring data, and the output is an alert notification sent to the user when an abnormality occurs.

[0694] 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.

[0695] This invention combines a system that uses a generative AI model to analyze system codes and logs, visualizes and monitors system configuration diagrams, and an emotion engine that recognizes user emotions. This system not only enables users to quickly understand the overall system and maintain proper operating conditions, but also adjusts the interface based on the user's emotions, further improving usability.

[0696] System Overview

[0697] The system includes the following key features:

[0698] 1. Data Collection

[0699] The user uploads the code file, log file, specification, or manual that he / she wants to analyze to the server.

[0700] 2. Data Analysis

[0701] The server analyzes the received files using a generative AI model to extract code structure, log patterns, and specification contents.

[0702] 3. System configuration diagram generation

[0703] Based on the analysis results, the server generates a system configuration diagram that shows the dependencies and communication paths between each component of the system.

[0704] 4. Visualization

[0705] The terminal visually displays an interactive system configuration diagram to the user, allowing the user to manipulate the diagram.

[0706] 5. Surveillance

[0707] The server monitors the system's operational status in real time and notifies the user if an abnormality is detected.

[0708] 6. Emotion recognition

[0709] The server uses an emotion engine to analyze emotions from the user's facial expressions and voice.

[0710] 7. User interface adjustments

[0711] The server adjusts the user interface based on the analyzed emotions to improve usability.

[0712] Program processing

[0713] 1. Data Collection

[0714] Users log into the system's web portal, select and upload the files they want to analyze, and the server receives the data, which can be code files, log files, specifications, or manuals.

[0715] 2. Data Analysis

[0716] The server uses a generative AI model to analyze the uploaded files, extracting the structure and dependencies of functions and classes in the code and identifying error patterns in log files.

[0717] 3. System configuration diagram generation

[0718] The server uses the analysis results to generate a system diagram that shows the relationships between each component. The system diagram visually displays how each part of the system interacts.

[0719] 4. Visualization

[0720] The device displays the generated system diagram in the user's browser. The user can click on the diagram to view detailed information about a specific module or component. For example, clicking on module A displays the functions and dependencies associated with that module.

[0721] 5. Surveillance

[0722] The server monitors the system's operational status in real time, and if any abnormal patterns or errors are detected, an alert notification is sent to the user and detailed information is displayed on the dashboard.

[0723] 6. Emotion recognition

[0724] The server uses an emotion engine to analyze the user's facial expressions and voice to recognize their current emotional state. For example, if the user is feeling stressed, that information will be analyzed.

[0725] 7. User interface adjustments

[0726] The server dynamically adjusts the user interface based on the analysis results obtained from the emotion engine. For example, if the user is feeling stressed, the interface will be simplified or appropriate support will be provided.

[0727] Specific examples

[0728] 1. Data Collection

[0729] A user logs into the system's web portal and uploads the latest application code file (e.g., app_code.py) and system log file (e.g., server_log.txt).

[0730] 2. Data Analysis

[0731] The server inputs app_code.py and server_log.txt into the generative AI model, which analyzes code dependencies and log error patterns.

[0732] 3. System configuration diagram generation

[0733] The server generates a system configuration diagram based on the analysis results and visually displays the interdependencies of each module and component.

[0734] 4. Visualization

[0735] The terminal displays a system configuration diagram on the user's screen, and the user can click on the diagram to view detailed information about a specific module.

[0736] 5. Surveillance

[0737] The server monitors the system in real time and issues an alert when it detects an abnormality. Information such as sudden increases in memory usage and CPU overload is displayed on the dashboard.

[0738] 6. Emotion recognition

[0739] The server uses an emotion engine to analyze the user's facial expressions and voice to understand their emotional state. For example, if the user is irritated, that emotional data will be analyzed.

[0740] 7. User interface adjustments

[0741] The server adjusts the interface based on the user's emotional data. If the user is feeling stressed, the system automatically simplifies operation and reduces the amount of information presented to the user.

[0742] As described above, the system of the present invention combines a generative AI model and an emotion engine, allowing users to quickly understand the overall system and maintain appropriate operation. Furthermore, usability is improved by adjusting the interface according to the user's emotions.

[0743] The processing flow will be explained below.

[0744] Step 1:

[0745] The user logs into the system's web portal and clicks the "Upload analysis file" button.

[0746] Step 2:

[0747] The user selects the files they want to analyze (e.g., source code files, log files, specifications, or manuals) and uploads them to the server.

[0748] Step 3:

[0749] The server receives the uploaded file and automatically identifies the file format and content, for example, checking whether it is a code file, log file, or specification document.

[0750] Step 4:

[0751] The server inputs the received files into a generative AI model, which analyzes the code structure, function call relationships, and dependencies. For example, it verifies that function A calls function B, or that module X depends on library Y.

[0752] Step 5:

[0753] The server analyzes the log file entries to identify the frequency and occurrence patterns of errors and warnings, for example, by counting the frequency of the error message "ERROR" and the warning message "WARNING."

[0754] Step 6:

[0755] The server analyzes the text of specifications and manuals and extracts important points and constraints of the system specifications.

[0756] Step 7:

[0757] Based on the analysis results, the server generates a data structure that shows the dependencies and communication paths between components. For example, it represents the dependencies and API call relationships between modules using nodes and edges.

[0758] Step 8:

[0759] The server generates a system configuration diagram based on the generated data structure. This diagram includes the relationships between modules and components, the locations of errors, and so on.

[0760] Step 9:

[0761] The terminal displays the system configuration diagram in the user's browser, and the user can interactively click on each node or edge to display detailed information.

[0762] Step 10:

[0763] Users can explore the diagram and learn more about specific modules and components. For example, clicking on Module A displays the functions and dependencies associated with that module.

[0764] Step 11:

[0765] The server monitors the system's operation in real time, checking for new log entries and changes in system state, and running algorithms to detect abnormal patterns and errors.

[0766] Step 12:

[0767] If the server detects an abnormality, it will send an alert to the user, providing them with a notification containing detailed information about the abnormality and the extent of its impact.

[0768] Step 13:

[0769] Users receive alerts and can view detailed information on a dashboard, such as memory usage spikes or CPU overloads.

[0770] Step 14:

[0771] The server uses an emotion engine to analyze the user's facial expressions and voice to recognize their current emotional state. For example, if the user is feeling stressed, that information is obtained.

[0772] Step 15:

[0773] The server adjusts the interface based on the analyzed emotions. For example, if the user is feeling stressed, the server sets the interface to be simpler.

[0774] Step 16:

[0775] The server collects user feedback and accumulates data to improve the system's usability, such as recording the user's operation history and changes in emotional state.

[0776] In this way, the user can understand the overall structure and operational status of the system, and can use an interface that is adapted to his or her emotional state.

[0777] Example 2

[0778] 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."

[0779] Conventional system analysis tools were capable of visualizing the analysis results of system code and logs, but they did not adjust the interface to take user emotions into consideration. As a result, when users felt stressed or dissatisfied with the interface, they were unable to respond appropriately, which sometimes resulted in usability issues. In addition, they lacked the ability to monitor the system's operational status in real time, making it difficult to detect abnormalities early and respond appropriately.

[0780] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, means for monitoring the operation status of the system, means for recognizing user emotions, and means for adjusting the user interface based on the user emotions. This makes it possible to appropriately monitor the operation status of the system and quickly respond to abnormal situations while improving usability.

[0781] "Means for receiving uploaded data" refers to the function of receiving data in the process of a user selecting a file and transferring it to the server.

[0782] "Means for analysis using generative AI models" refers to a function that uses artificial intelligence to analyze code structure and patterns based on uploaded data.

[0783] "Means for generating a system configuration diagram based on the analysis results" refers to the function of creating a diagram that visually shows the configuration of the entire system from the analysis results of the generative AI model.

[0784] "Means for visualizing the generated system configuration diagram" refers to a function that displays the generated system configuration diagram on the user's terminal and allows the user to interactively manipulate the diagram.

[0785] "Means for monitoring the operational status of the system" refers to the function of checking in real time whether the system is operating normally or if any abnormalities have occurred, and sending alerts as necessary.

[0786] "Means for recognizing the user's emotions" refers to a function that analyzes the user's facial expressions and voice data to identify their current emotional state.

[0787] "Means for adjusting the user interface based on the user's emotions" refers to a function that dynamically changes the interface in response to the detected user's emotions, thereby improving usability.

[0788] This invention is a system that uses a generative AI model to analyze code files and log files uploaded by users, and generates, visualizes, and monitors system configuration diagrams. It also aims to improve usability by recognizing user emotions and dynamically adjusting the interface.

[0789] Program Generation and Processing

[0790] Hardware and software used

[0791] Hardware

[0792] Server: a computer with a powerful processor and a large amount of memory

[0793] User device: PC or tablet with internet access

[0794] Webcam: A camera for capturing the user's facial expressions

[0795] Microphone: A microphone for capturing the user's voice

[0796] software

[0797] Generative AI models: e.g., GPT-3

[0798] Emotion recognition engine: For example, Amazon Rekognition

[0799] Web server: A server that provides file upload functionality and analysis result display functionality

[0800] Log Analysis Tools: Tools for analyzing log files

[0801] System processing flow

[0802] 1. Data Collection

[0803] A user logs into the system's web portal and uploads the code file (e.g., app_code.py) and log file (e.g., server_log.txt) they want to analyze.

[0804] The server receives the uploaded file and stores it in storage.

[0805] 2. Data Analysis

[0806] The server reads the file and enters a prompt sentence into the generative AI model to begin analysis.

[0807] For example: "Analyze the following code file and identify the structure and dependencies of functions and classes."

[0808] The server also passes the contents of the log file to the generative AI model to analyze error patterns.

[0809] For example: "Please analyze the following log files and identify any error patterns or anomalies."

[0810] 3. System configuration diagram generation

[0811] Based on the analysis results of the AI ​​model generated by the server, a system configuration diagram is created showing the dependencies and communication paths between each component.

[0812] A configuration diagram visually represents the interactions between modules and components.

[0813] 4. Visualization

[0814] The terminal displays the system configuration diagram on the user's browser.

[0815] The user can navigate the diagram and view detailed information about specific modules and components.

[0816] For example, when a user clicks on module A, it displays the functions and dependencies associated with that module.

[0817] 5. Surveillance

[0818] The server monitors the system's operational status in real time, and if it detects an abnormality, it generates an alert and notifies the user.

[0819] For example, it will notify you if an abnormal pattern such as a sudden increase in memory usage or CPU overload is detected.

[0820] 6. Emotion recognition

[0821] The server acquires the user's facial expressions and voice data and analyzes them using an emotion recognition engine.

[0822] Example: "Analyze whether the user is feeling stressed."

[0823] The server identifies the user's emotion based on the acquired emotion data.

[0824] 7. User interface adjustments

[0825] The server dynamically adjusts the user interface based on the emotion recognition results.

[0826] Example: If the user is stressed, simplify the interface or provide appropriate support features.

[0827] By combining a generative AI model and an emotion recognition engine, the system of this invention improves usability and enables appropriate monitoring and management of system operations, allowing users to quickly understand the overall system and respond quickly to abnormal situations.

[0828] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0829] Step 1: Data collection

[0830] A user logs into the system's web portal, selects and uploads the code file (e.g., app_code.py) and log file (e.g., server_log.txt) they want to analyze.

[0831] The server receives these files and stores them in storage.

[0832] Input: User-uploaded code and log files

[0833] Output: File saved on the server

[0834] Step 2: Data analysis

[0835] The server reads the saved file and inputs a prompt to the generative AI model (e.g., GPT-3) to begin analysis.

[0836] Specifically, the server inputs the following prompts into the generative AI model:

[0837] Prompt: "Analyze the following code file and identify the structure and dependencies of functions and classes."

[0838] The server obtains the analysis results from the output of the generative AI model.

[0839] Do the same for the log files:

[0840] Prompt: "Analyze the following log files and identify any error patterns or anomalies."

[0841] Input: Code files and log files stored on the server

[0842] Data processing: Performing analysis using generative AI models

[0843] Output: Analysis results of code structure and dependencies, and error patterns in logs

[0844] Step 3: Generate a system configuration diagram

[0845] The server generates a system configuration diagram based on the analysis results of the generated AI model.

[0846] Create a visual diagram showing the dependencies and communication paths of each component.

[0847] Input: Analysis results (code structure, dependencies, log error patterns)

[0848] Data processing: Create a system configuration diagram using a system configuration diagram generation algorithm

[0849] Output: System configuration diagram

[0850] Step 4: Visualization

[0851] The terminal creates an HTML page for displaying the system configuration diagram on the user's browser.

[0852] The terminal displays the system configuration diagram on the user's browser, allowing interactive operation.

[0853] The user can navigate the diagram and view detailed information about specific modules and components.

[0854] Input: System configuration diagram

[0855] Data processing: HTML page generation and diagram display

[0856] Output: System diagram displayed in the user's browser

[0857] Step 5: Monitoring

[0858] The server runs a script that monitors the system's operational status in real time.

[0859] If an anomaly is detected, the server generates an alert and notifies the user.

[0860] For example, abnormal patterns such as sudden increases in memory usage and CPU overloads are detected.

[0861] Input: Real-time data from the system

[0862] Data calculation: Identify anomalies using anomaly detection algorithms

[0863] Output: Alert notification sent to user

[0864] Step 6: Emotion Recognition

[0865] The server captures the user's webcam video and audio data.

[0866] The server analyzes the user's emotions using an emotion recognition engine (e.g., Amazon Rekognition).

[0867] As a specific example, the server identifies stress or irritation from the user's facial expression.

[0868] Input: Webcam video and audio data

[0869] Data calculation: Emotion analysis using emotion recognition engine

[0870] Output: User emotion data

[0871] Step 7: Adjust the user interface

[0872] The server dynamically adjusts the user interface based on the emotion recognition results.

[0873] For example, if a user is feeling stressed, the interface can be simplified and appropriate support functions provided.

[0874] Input: User emotion data

[0875] Data processing: Using interface adjustment algorithms

[0876] Output: A tailored user interface

[0877] At each step, specific data processing or calculations are performed based on the input data, resulting in an output that is used in the next step, enabling the system to achieve real-time monitoring and anomaly detection while improving usability.

[0878] (Application example 2)

[0879] 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."

[0880] Factory robots are required to reduce operator stress and improve operability while providing efficient operation and real-time monitoring. However, current systems make it difficult to visually grasp the robot's operating status, and they do not dynamically adjust the interface to take into account the operator's emotional state. This increases operator stress and reduces productivity.

[0881] 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.

[0882] In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, means for monitoring the operation status of the system, means for recognizing a user's emotion, and means for adjusting the user interface based on the recognized emotion, thereby enabling an operator to visually grasp the operation status of a factory robot in real time and adjust the interface according to the operator's emotional state.

[0883] The "means for receiving uploaded data" is a function that allows factory operators to send data such as robot operation logs and operating programs to a server, and for the server to receive it.

[0884] "Means of analysis using generative AI models" refers to the use of AI technology to analyze patterns and trends within collected data.

[0885] The "means for generating a system configuration diagram" is a function for creating a diagram that visually represents the relationships and operating status between robots within a factory based on the analysis results.

[0886] "Means for visualizing the generated system configuration diagram" is a function that displays the generated system configuration diagram on the operator's terminal, making it visually easy to understand.

[0887] The "means for monitoring the system's operational status" is a function that continuously monitors the operating status and errors of factory robots in real time, and detects and notifies users if an abnormality occurs.

[0888] "Means for recognizing user emotions" refers to a function that uses devices such as cameras and microphones to analyze the operator's facial expressions and voice to understand their emotional state.

[0889] The "means for adjusting the user interface based on the recognized emotion" is a function that dynamically changes the interface to improve usability in accordance with the recognized emotional state of the operator.

[0890] MODE FOR CARRYING OUT THE INVENTION

[0891] This invention is a system for improving the efficiency of factory robot operations and monitoring them in real time. Furthermore, it aims to reduce operator stress and improve productivity by recognizing the emotions of factory operators and dynamically adjusting the operation interface. This system is composed of the following main hardware and software:

[0892] Hardware

[0893] Device: Any device that can connect to the internet (e.g. smartphone, tablet, PC)

[0894] Camera and microphone: Sensor devices for capturing the operator's facial expressions and voice.

[0895] software

[0896] Generative AI model (e.g., GPT-4): AI technology used to analyze uploaded data

[0897] Emotion recognition engine (e.g. Microsoft Azure Face API): An engine for analyzing the emotional state of the operator

[0898] Database (e.g. MySQL): A database system for storing analysis results and log data.

[0899] Web server (e.g. Apache): A server that hosts the core programs of the system

[0900] Real-time monitoring tools (e.g., Elasticsearch, Kibana): Tools for monitoring system operation status

[0901] System program processing

[0902] 1. Data Collection

[0903] Users log in to a dedicated web portal and upload the factory robot's operation log and operating program (e.g., robot_log.txt, robot_program.py).

[0904] 2. Data Analysis

[0905] The server inputs the received data into a generative AI model (e.g., GPT-4) and analyzes the data for patterns and errors.

[0906] 3. System configuration diagram generation

[0907] Based on the analysis results, the server generates a system configuration diagram showing the operational status of the robots within the factory.

[0908] 4. Visualization

[0909] The terminal interactively displays the generated system configuration diagram, allowing the operator to visually check detailed information about each robot.

[0910] 5. Surveillance

[0911] The server monitors the operational status of factory robots in real time and sends an alert to the operator if an abnormality is detected. For example, information on sudden increases in memory usage or CPU overload is displayed on the dashboard.

[0912] 6. Emotion recognition

[0913] The server uses an emotion recognition engine (e.g., Microsoft Azure Face API) to analyze data obtained from the camera and microphone to understand the operator's emotional state. For example, if the operator is feeling stressed, that information will be analyzed.

[0914] 7. User interface adjustments

[0915] The server dynamically adjusts the user interface based on the analysis results obtained from the emotion recognition engine. For example, if the operator is feeling stressed, the interface will be simplified and the displayed information will be reduced, improving usability.

[0916] Specific examples

[0917] 1. Example prompt

[0918] Data Analysis prompt:

[0919] "Analyze the following robot operation log to identify errors and visualize behavioral patterns. Log data: robot_log.txt"

[0920] System configuration diagram generation prompt:

[0921] "Please generate a system configuration diagram for the factory robot based on the analysis results below. Analysis data: analysis results.json"

[0922] Through a series of processes

[0923] This system allows operators to visually grasp the operating status of factory robots in real time and adjusts the interface according to their emotional state, reducing operator stress and improving productivity and usability.

[0924] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0925] Step 1:

[0926] Data collection

[0927] The user logs in to a dedicated web portal and uploads the factory robot's operation log (e.g., robot_log.txt) and operation program (e.g., robot_program.py). The input is the operation log and operation program files, and the server receives these files as output. Specifically, the user accesses the web portal in a browser and uploads the required files using the file selection dialog.

[0928] Step 2:

[0929] Data analysis

[0930] The server inputs the received data into a generative AI model (e.g., GPT-4) and analyzes patterns and errors within the data. The input is the uploaded log file and operation program, and the analysis results are obtained as output. Specifically, the server sends the received data to the GPT-4 interface and enters a data analysis prompt: "Analyze the following robot operation log, identify errors, and visualize behavioral patterns. Log data: robot_log.txt."

[0931] Step 3:

[0932] System configuration diagram generation

[0933] Based on the analysis results, the server generates a system configuration diagram showing the operational status of the factory robots. The input is the analysis results, and the output is an interactive system configuration diagram. Specifically, the server uses a JavaScript library (e.g., D3.js) to generate the configuration diagram. "Please generate a system configuration diagram for the factory robots based on the following analysis results. Analysis data: Analysis results.json"

[0934] Step 4:

[0935] Visualization

[0936] The terminal interactively displays the generated system configuration diagram, allowing the operator to visually check detailed information about each robot. The input is the generated configuration diagram, and the output is visual information displayed on the operator's terminal. Specifically, the terminal displays the configuration diagram in a web browser, and the user can click to check detailed information.

[0937] Step 5:

[0938] Monitoring

[0939] The server monitors the operational status of factory robots in real time and sends an alert to the operator if an abnormality is detected. The input is real-time log data, and the output is an alert that an abnormality has been detected. Specifically, the server monitors the log data using Elasticsearch and Kibana, and if an abnormality is detected, it notifies the operator via Slack or email.

[0940] Step 6:

[0941] emotion recognition

[0942] The server uses an emotion recognition engine (e.g., Microsoft Azure Face API) to analyze data acquired from the camera and microphone to understand the operator's emotional state. The input is real-time data from the camera and microphone, and the output is an evaluation of the operator's emotional state. Specifically, the server sends real-time data to the emotion recognition engine and inputs a prompt such as "Please analyze the operator's emotional state."

[0943] Step 7:

[0944] User Interface Adjustments

[0945] The server dynamically adjusts the user interface based on the analysis results obtained from the emotion recognition engine. The input is the emotion analysis results, and the output is an adjusted user interface displayed on the terminal. Specifically, the server uses JavaScript and React.js to change the interface and adjust the displayed information appropriately according to the operator's stress level.

[0946] 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.

[0947] 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.

[0948] 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.

[0949] [Third embodiment]

[0950] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0951] 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.

[0952] 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).

[0953] 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.

[0954] 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.

[0955] 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).

[0956] 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. 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.

[0957] 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.

[0958] 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.

[0959] 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.

[0960] 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.

[0961] 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."

[0962] The present invention provides a system for visualizing and monitoring the configuration of a system that has been in operation for a long period of time, thereby supporting efficient analysis, modification, and operation of the system.

[0963] System Overview

[0964] The system includes the following key features:

[0965] 1. Data Collection

[0966] The user uploads the code file, log file, specification, or manual that he / she wants to analyze to the server.

[0967] 2. Data Analysis

[0968] The server analyzes the received files using a generative AI model to extract code structure, log patterns, and specification contents.

[0969] 3. System configuration diagram generation

[0970] Based on the analysis results, the server generates a system configuration diagram that shows the dependencies and communication paths between each component of the system.

[0971] 4. Visualization

[0972] The terminal visually displays an interactive system configuration diagram to the user, allowing the user to manipulate the diagram.

[0973] 5. Surveillance

[0974] The server monitors the system's operational status in real time and notifies the user if an abnormality is detected.

[0975] Program processing

[0976] 1. Data Collection

[0977] Users log in to the system's web portal and select and upload the files they want to analyze, which can be in a variety of formats, including source code, log files, specifications, and manuals.

[0978] 2. Data Analysis

[0979] The server receives the uploaded files and identifies their data format. It uses a generative AI model to analyze the code structure and extract dependencies between functions, classes, and modules. For log files, it analyzes entries and identifies patterns of errors and warnings.

[0980] 3. System configuration diagram generation

[0981] The server aggregates the analysis results and generates a data structure that illustrates the relationships between components. This data structure is then used to generate a system diagram, which visually shows how the parts of the system interact with each other.

[0982] 4. Visualization

[0983] The terminal displays the generated system diagram in the user's browser. The user can interact with the diagram and view detailed information. For example, clicking on a specific module displays details about its dependencies and functions.

[0984] 5. Surveillance

[0985] The server monitors the system's operational status in real time and detects abnormal patterns and errors. If an abnormality is detected, the user is notified and a warning message is displayed on the dashboard. At the same time, detailed information about the abnormality and the scope of its impact are also reported to the user.

[0986] Specific examples

[0987] 1. Data Collection

[0988] A user logs into the system's web portal and uploads the latest application code file (e.g., app_code.py) and system log file (e.g., server_log.txt).

[0989] 2. Data Analysis

[0990] The server receives app_code.py and server_log.txt, inputs these files into the AI ​​model, and begins analysis. The AI ​​model extracts function dependencies within the code and identifies error patterns from the log file.

[0991] 3. System configuration diagram generation

[0992] Based on the analysis results, the server generates a system configuration diagram showing the relationships between functions, classes, and modules. This configuration diagram visually displays dependencies between modules and error locations.

[0993] 4. Visualization

[0994] The device displays a system diagram in the user's browser. The user can click on the diagram to view details of specific modules or functions. For example, clicking on Module A displays the associated functions and dependencies.

[0995] 5. Surveillance

[0996] The server performs real-time monitoring of the system and displays a warning on the dashboard if it detects any abnormal behavior. For example, if memory usage spikes, an alert is generated, showing the affected module and how to address it.

[0997] In this way, the system of the present invention enables the user to quickly understand the entire system and appropriately monitor the operational status, thereby supporting efficient system modification and operation.

[0998] The processing flow will be explained below.

[0999] Step 1:

[1000] The user logs into the system's web portal and clicks the "Upload analysis file" button.

[1001] Step 2:

[1002] The user selects the files they want to analyze (e.g., source code files, log files, specifications, or manuals) and uploads them to the server.

[1003] Step 3:

[1004] The server receives the uploaded file and automatically identifies the file format and content, for example, checking whether it is a code file, log file, or specification document.

[1005] Step 4:

[1006] The server inputs the received files into a generative AI model, which analyzes the code structure, function call relationships, and dependencies. For example, it extracts that function A calls function B, or that module X depends on library Y.

[1007] Step 5:

[1008] The server analyzes the log file entries to identify the frequency and occurrence patterns of errors and warnings, for example, the frequency of occurrence of the error message "ERROR" and the warning message "WARNING".

[1009] Step 6:

[1010] The server analyzes the text of specifications and manuals and extracts important points and constraints of the system specifications.

[1011] Step 7:

[1012] Based on the analysis results, the server generates a data structure that shows the dependencies and communication paths between each component. The dependencies and API call relationships between each module are represented by nodes and edges.

[1013] Step 8:

[1014] The server generates a system configuration diagram based on the generated data structure. This diagram includes the relationships between modules and components, the locations of errors, and so on.

[1015] Step 9:

[1016] The terminal displays the system configuration diagram in the user's browser, and the user can interactively click on each node or edge to display detailed information.

[1017] Step 10:

[1018] Users can explore the diagram and learn more about specific modules and components. For example, clicking on Module A displays the functions and dependencies associated with that module.

[1019] Step 11:

[1020] The server monitors the system's operation in real time, checking for new log entries and changes in system state, and running algorithms to detect abnormal patterns and errors.

[1021] Step 12:

[1022] If the server detects an abnormality, it will send an alert to the user, providing them with a notification containing detailed information about the abnormality and the extent of its impact.

[1023] Step 13:

[1024] Users receive alerts and can view detailed information in a dashboard, such as memory usage spikes or CPU overloads.

[1025] As described above, by performing specific processing for each step, the user can easily grasp the overall structure and operational status of the system, enabling efficient modification and operation.

[1026] Example 1

[1027] 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."

[1028] With existing systems, it is difficult to quickly grasp the overall picture of the system and efficiently monitor and modify it. In particular, in complex systems that have been in operation for a long time, it is important to visualize the dependencies and communication paths between components and monitor the operational status in real time, but there are currently no easy ways to achieve this. A notification system is also needed to respond instantly when an abnormality occurs.

[1029] 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.

[1030] In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, means for monitoring the system's operational status, means for selecting uploaded data after user authentication, means for interactively displaying details of the configuration diagram to the user, and means for notifying the user when an abnormality is detected. This allows the user to quickly grasp the overall picture of the system and efficiently analyze, repair, and operate it. Real-time monitoring of the system's operational status and immediate notification of abnormalities enable early detection and response to problems.

[1031] "Uploaded Data" refers to electronic data such as source code, log files, specifications, or manuals that a user sends to the system.

[1032] "Means of receiving" refers to the functions and processes by which the server obtains uploaded data.

[1033] "Generative AI models" refer to artificial intelligence algorithms used to automate the analysis of data and extract advanced information.

[1034] "Means for analyzing" refers to the functions or processes used to analyze received data and extract meaningful information or patterns.

[1035] A "system configuration diagram" is a diagram that visually shows the dependencies and communication paths between each component within a system.

[1036] "Visualization means" refers to the functions and processes for visually displaying the generated system configuration diagram to the user.

[1037] "Means for monitoring the operational status of the system" refers to functions and processes for monitoring in real time whether the system is operating normally and detecting abnormalities.

[1038] "Means for selecting uploaded data after authentication" refers to the functionality or process for selecting and using data within the system after a user has provided valid authentication information.

[1039] "Means for interactively displaying details of the configuration diagram" refers to functions and processes that allow a user to manipulate the system configuration diagram and dynamically view detailed information.

[1040] "Means for notifying users when an abnormality is detected" refers to functions and processes for quickly notifying users of an abnormality when it is discovered during system monitoring.

[1041] This invention relates to a system for visualizing and monitoring system configurations. This system receives uploaded data and analyzes it using a generative AI model. It then generates a system configuration diagram based on the analysis results and provides it visually to the user. It also includes a function to monitor the system's operational status in real time and notify the user when an abnormality is detected.

[1042] 1. Data Collection and Reception

[1043] Users log in to the system through a web portal and upload the source code, log files, specifications, or manuals they want to analyze. For example, a user can select and upload files named app_code.py and server_log.txt. These data are then transferred to the server.

[1044] 2. Data Analysis

[1045] The server receives the uploaded data and feeds it into a generative AI model that extracts function dependencies in the code and identifies error patterns in log files. The hardware used is a dedicated server, and the software includes a deep learning framework.

[1046] Example: The server generates a prompt statement saying "Start code analysis" and sends it to the generative AI model.

[1047] 3. Generating a system configuration diagram

[1048] The server generates a data structure for a system configuration diagram based on the results of the data analysis. This configuration diagram includes dependencies and communication paths between each component of the system. The server then draws a visual system configuration diagram based on this data structure.

[1049] 4. Visualization

[1050] The terminal displays the generated system diagram in the user's browser. The user can click on the diagram to interactively view the details of a specific module or component. For example, when the user clicks on module A, a pop-up appears with details of its functions and dependencies.

[1051] 5. Real-time monitoring and notifications

[1052] The server continuously monitors the system's operational status. If it detects abnormal behavior or an error pattern, it notifies the user and displays a warning message on the dashboard. The hardware used is a module dedicated to monitoring, and the software includes a monitoring tool. For example, if the server detects a sudden increase in memory usage, it displays a warning message on the dashboard saying, "Memory usage has increased sharply, affecting module A."

[1053] In this way, this system allows users to quickly grasp the overall picture of the system and efficiently analyze, repair, and operate it.In addition, real-time monitoring of the system's operating status and immediate notification of abnormalities enable early detection and response to problems.

[1054] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1055] Step 1:

[1056] The user accesses the web portal and enters their credentials. If the correct credentials are entered, the user is able to access the dashboard.

[1057] Input: Username, Password

[1058] Output: Authentication token, dashboard screen

[1059] Specific operation: The user accesses "example.com", enters their username and password, and presses the "Login" button.

[1060] Step 2:

[1061] The user clicks the upload button on the dashboard, selects the file they want to analyze, and uploads it. This file is then sent to the server.

[1062] Input: File to be analyzed (e.g. app_code.py, server_log.txt)

[1063] Output: A confirmation message for the uploaded file

[1064] Specific behavior: The user clicks the "File Upload" button, selects app_code.py and server_log.txt, and then clicks the "Upload" button.

[1065] Step 3:

[1066] The server receives the uploaded files, identifies the data format of each file, and inputs these files into a generative AI model to perform data analysis.

[1067] Input: Uploaded file

[1068] Output: Analysis results (code dependencies, log error patterns)

[1069] Specific operation: The server passes app_code.py and server_log.txt to the generated AI model, generates a prompt statement saying "Start code analysis", and sends it to the AI ​​model.

[1070] Step 4:

[1071] Based on the results of the data analysis, the server generates a data structure for a system configuration diagram, which includes dependencies and communication paths between components.

[1072] Input: Analysis results (code dependencies, log error patterns)

[1073] Output: System configuration diagram data structure

[1074] Specific operation: The server executes the "process for generating configuration diagram data," registers dependencies and communication paths in a database, and draws a system configuration diagram.

[1075] Step 5:

[1076] The terminal visually displays the generated system configuration diagram in the user's browser, and the user can click on the diagram to view detailed information.

[1077] Input: System configuration diagram data structure

[1078] Output: System configuration diagram on browser

[1079] Specific operation: The terminal displays a system configuration diagram on the browser, and when the user clicks on a specific module, detailed information related to that module will be displayed in a pop-up.

[1080] Step 6:

[1081] The server monitors the system's operational status in real time, detecting abnormal behavior and error patterns. If an abnormality occurs, it notifies the user and displays a warning message on the dashboard.

[1082] Input: Real-time system data

[1083] Output: Anomaly detection, warning message

[1084] Specific operation: When the server performs "real-time monitoring" and detects a sudden increase in memory usage, a warning message will be displayed on the dashboard stating "Memory usage has increased sharply, affecting module A."

[1085] This allows users to efficiently understand the system configuration and operational status, and to respond quickly when a problem occurs.

[1086] (Application example 1)

[1087] 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."

[1088] With conventional systems, it is difficult to efficiently visualize and analyze the configuration of systems that have been in operation for a long time, which has resulted in the problem of system operation and modification taking a great deal of time and effort.In addition, early detection of abnormalities and real-time operational monitoring are insufficient, resulting in problems such as a decline in system stability and reliability.

[1089] 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.

[1090] In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, and means for monitoring the system's operational status and notifying when an abnormality is detected. This enables efficient visualization and analysis of the system configuration, and real-time operational monitoring and abnormality detection.

[1091] The "means for receiving uploaded data" is a function for importing data sent by a user into the server.

[1092] "Means for analysis using a generative AI model" refers to a function that analyzes uploaded data using an artificial intelligence model and extracts data structures and patterns.

[1093] The "means for generating a system configuration diagram" is a function that creates a diagram that visually represents the relationships between each component of the system based on the results of the analyzed data.

[1094] The "means for visualizing the system configuration diagram" is a function that allows the user to interactively display the generated system configuration diagram and operate it.

[1095] "Means for monitoring the system's operational status and notifying users if an abnormality is detected" refers to a function that monitors the system's operation in real time and sends an alert to users if an abnormality occurs.

[1096] MODE FOR CARRYING OUT THE INVENTION

[1097] The present invention provides a system that efficiently visualizes the operation of factory robots, enabling early detection of abnormalities and real-time operation monitoring. Hereinafter, embodiments of the present invention will be described.

[1098] System configuration

[1099] The system primarily consists of the following major components:

[1100] 1. Server

[1101] 2. User device (smartphone, etc.)

[1102] 3. Operational data collection device for factory robots

[1103] System Features

[1104] 1. Means of receiving uploaded data:

[1105] The user terminal receives the factory robot's operational data (e.g., log files and operation history data) from the collection device and uploads it to the cloud server, which receives and stores this data.

[1106] 2. Means of analyzing received data using a generative AI model:

[1107] The server inputs the uploaded data into a generative AI model and begins analysis. The AI ​​model uses a high-performance language model such as GPT-4. Through analysis, patterns and anomalies are identified within the operational data.

[1108] 3. How to generate a system diagram based on the analysis results:

[1109] Based on the analysis results, the server generates a system configuration diagram that shows the operational status and dependencies of each robot in the factory. The system configuration diagram visually displays the location, communication paths, and operational status of each robot.

[1110] 4. A way to visualize the generated system diagram:

[1111] The generated system configuration diagram is sent to the user's device and displayed in an interactive format, allowing the user to tap and zoom to view detailed information.

[1112] 5. Monitoring the system's operational status and notifying you if an abnormality is detected:

[1113] The server monitors operational data in real time, and if an abnormality is detected, it sends an alert via push notification to the user's device, allowing the user to respond promptly without missing the timing of the abnormality.

[1114] Specific examples of hardware and software used

[1115] Server: Cloud server (e.g. Amazon Web Services)

[1116] User device: Smartphone (iOS or Android)

[1117] Generative AI model: GPT-4 (OpenAI)

[1118] Specific examples

[1119] 1. Data Collection Example:

[1120] The user device receives the latest factory robot operation data (e.g., robot_log.txt) and uploads it to the cloud server.

[1121] 2. Data analysis example:

[1122] The server receives robot_log.txt and begins analyzing it with GPT-4, which extracts dependencies between specific functions and abnormal patterns.

[1123] 3. Example of system configuration diagram generation:

[1124] The server generates a system configuration diagram based on the analysis results, visually representing the operational status and dependencies of each robot.

[1125] 4. Visualization example:

[1126] The system configuration diagram is sent to the user's device and displayed in an interactive format on the device screen, where the user can tap on a specific robot to view more information.

[1127] 5. Monitoring and Notification Examples:

[1128] The server monitors in real time and sends a push notification to the user's device if an abnormality is detected. Example: "Robot 123's memory usage is increasing rapidly. Please check immediately."

[1129] Prompt Sentence Examples

[1130] "Please analyze the following robot operation log data and clearly indicate the dependencies between functions and the location of the error. Log data: [Part of the detailed log data]"

[1131] In this way, it becomes possible to efficiently monitor the operation of factory robots and quickly detect abnormalities.

[1132] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1133] Step 1:

[1134] Data collection

[1135] The user uploads the operation data (e.g., log files) of the factory robot to the user terminal. The uploaded data includes operation history data, error logs, performance data, etc. The user terminal sends this data to the cloud server. The input is the robot operation data (in file format), and the output is the data stored on the cloud server.

[1136] Step 2:

[1137] Data reception

[1138] The server receives data sent from the user's device and stores it in a database. In particular, it checks whether the received data has been uploaded correctly and converts it into the required data format. During this process, detailed log information and error messages are entered, and this is converted into an internal database format and stored.

[1139] Step 3:

[1140] Data analysis preparation

[1141] The server prepares the received data for input to a generative AI model for analysis. Specifically, it converts the data into an appropriate format and generates a prompt. For example, it prepares a prompt such as, "Analyze this robot log and extract behavior patterns and dependencies." The input is the converted log information, and the output is the prompt and converted data that are input to the generative AI model.

[1142] Step 4:

[1143] Data analysis

[1144] The server analyzes the data using a generative AI model (e.g., GPT-4). Here, the prompt sentence and the converted data are input into the AI ​​model, and as a result, the robot's behavior patterns, dependencies, error patterns, etc. are extracted. The input for the analysis is the prompt sentence and data, and the output is the analysis results, such as a dependency list and error log patterns.

[1145] Step 5:

[1146] System configuration diagram generation

[1147] The server generates a system configuration diagram based on the analysis results. This configuration diagram is designed to visually show the placement of each robot, their dependencies, and the locations of abnormalities. The input is a dependency list from the analysis results, and the output is a system configuration diagram.

[1148] Step 6:

[1149] Configuration visualization

[1150] The server sends the generated system configuration diagram to the user's device. The device displays the diagram in an interactive format, allowing the user to zoom, tap, and view detailed information. The input is the system configuration diagram data, and the output is interactive visual information displayed on the device.

[1151] Step 7:

[1152] Operational status monitoring and notification

[1153] The server monitors the system's operational status in real time and sends a notification to the user's device if it detects an abnormality. For example, if the robot's memory usage increases sharply, an alert is sent via push notification. The input to this process is real-time monitoring data, and the output is an alert notification sent to the user when an abnormality occurs.

[1154] 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.

[1155] This invention combines a system that uses a generative AI model to analyze system codes and logs, visualizes and monitors system configuration diagrams, and an emotion engine that recognizes user emotions. This system not only enables users to quickly understand the overall system and maintain proper operating conditions, but also adjusts the interface based on the user's emotions, further improving usability.

[1156] System Overview

[1157] The system includes the following key features:

[1158] 1. Data Collection

[1159] The user uploads the code file, log file, specification, or manual that he / she wants to analyze to the server.

[1160] 2. Data Analysis

[1161] The server analyzes the received files using a generative AI model to extract code structure, log patterns, and specification contents.

[1162] 3. System configuration diagram generation

[1163] Based on the analysis results, the server generates a system configuration diagram that shows the dependencies and communication paths between each component of the system.

[1164] 4. Visualization

[1165] The terminal visually displays an interactive system configuration diagram to the user, allowing the user to manipulate the diagram.

[1166] 5. Surveillance

[1167] The server monitors the system's operational status in real time and notifies the user if an abnormality is detected.

[1168] 6. Emotion recognition

[1169] The server uses an emotion engine to analyze emotions from the user's facial expressions and voice.

[1170] 7. User interface adjustments

[1171] The server adjusts the user interface based on the analyzed emotions to improve usability.

[1172] Program processing

[1173] 1. Data Collection

[1174] Users log into the system's web portal, select and upload the files they want to analyze, and the server receives the data, which can be code files, log files, specifications, or manuals.

[1175] 2. Data Analysis

[1176] The server uses a generative AI model to analyze the uploaded files, extracting the structure and dependencies of functions and classes in the code and identifying error patterns in log files.

[1177] 3. System configuration diagram generation

[1178] The server uses the analysis results to generate a system diagram that shows the relationships between each component. The system diagram visually displays how each part of the system interacts.

[1179] 4. Visualization

[1180] The device displays the generated system diagram in the user's browser. The user can click on the diagram to view detailed information about a specific module or component. For example, clicking on module A displays the functions and dependencies associated with that module.

[1181] 5. Surveillance

[1182] The server monitors the system's operational status in real time, and if any abnormal patterns or errors are detected, an alert notification is sent to the user and detailed information is displayed on the dashboard.

[1183] 6. Emotion recognition

[1184] The server uses an emotion engine to analyze the user's facial expressions and voice to recognize their current emotional state. For example, if the user is feeling stressed, that information will be analyzed.

[1185] 7. User interface adjustments

[1186] The server dynamically adjusts the user interface based on the analysis results obtained from the emotion engine. For example, if the user is feeling stressed, the interface will be simplified or appropriate support will be provided.

[1187] Specific examples

[1188] 1. Data Collection

[1189] A user logs into the system's web portal and uploads the latest application code file (e.g., app_code.py) and system log file (e.g., server_log.txt).

[1190] 2. Data Analysis

[1191] The server inputs app_code.py and server_log.txt into the generative AI model, which analyzes code dependencies and log error patterns.

[1192] 3. System configuration diagram generation

[1193] The server generates a system configuration diagram based on the analysis results and visually displays the interdependencies of each module and component.

[1194] 4. Visualization

[1195] The terminal displays a system configuration diagram on the user's screen, and the user can click on the diagram to view detailed information about a specific module.

[1196] 5. Surveillance

[1197] The server monitors the system in real time and issues an alert when it detects an abnormality. Information such as sudden increases in memory usage and CPU overload is displayed on the dashboard.

[1198] 6. Emotion recognition

[1199] The server uses an emotion engine to analyze the user's facial expressions and voice to understand their emotional state. For example, if the user is irritated, that emotional data will be analyzed.

[1200] 7. User interface adjustments

[1201] The server adjusts the interface based on the user's emotional data. If the user is feeling stressed, the system automatically simplifies operation and reduces the amount of information presented to the user.

[1202] As described above, the system of the present invention combines a generative AI model and an emotion engine, allowing users to quickly understand the overall system and maintain appropriate operation. Furthermore, usability is improved by adjusting the interface according to the user's emotions.

[1203] The processing flow will be explained below.

[1204] Step 1:

[1205] The user logs into the system's web portal and clicks the "Upload analysis file" button.

[1206] Step 2:

[1207] The user selects the files they want to analyze (e.g., source code files, log files, specifications, or manuals) and uploads them to the server.

[1208] Step 3:

[1209] The server receives the uploaded file and automatically identifies the file format and content, for example, checking whether it is a code file, log file, or specification document.

[1210] Step 4:

[1211] The server inputs the received files into a generative AI model, which analyzes the code structure, function call relationships, and dependencies. For example, it verifies that function A calls function B, or that module X depends on library Y.

[1212] Step 5:

[1213] The server analyzes the log file entries to identify the frequency and occurrence patterns of errors and warnings, for example, by counting the frequency of the error message "ERROR" and the warning message "WARNING."

[1214] Step 6:

[1215] The server analyzes the text of specifications and manuals and extracts important points and constraints of the system specifications.

[1216] Step 7:

[1217] Based on the analysis results, the server generates a data structure that shows the dependencies and communication paths between components. For example, it represents the dependencies and API call relationships between modules using nodes and edges.

[1218] Step 8:

[1219] The server generates a system configuration diagram based on the generated data structure. This diagram includes the relationships between modules and components, the locations of errors, and so on.

[1220] Step 9:

[1221] The terminal displays the system configuration diagram in the user's browser, and the user can interactively click on each node or edge to display detailed information.

[1222] Step 10:

[1223] Users can explore the diagram and learn more about specific modules and components. For example, clicking on Module A displays the functions and dependencies associated with that module.

[1224] Step 11:

[1225] The server monitors the system's operation in real time, checking for new log entries and changes in system state, and running algorithms to detect abnormal patterns and errors.

[1226] Step 12:

[1227] If the server detects an abnormality, it will send an alert to the user, providing them with a notification containing detailed information about the abnormality and the extent of its impact.

[1228] Step 13:

[1229] Users receive alerts and can view detailed information on a dashboard, such as memory usage spikes or CPU overloads.

[1230] Step 14:

[1231] The server uses an emotion engine to analyze the user's facial expressions and voice to recognize their current emotional state. For example, if the user is feeling stressed, that information is obtained.

[1232] Step 15:

[1233] The server adjusts the interface based on the analyzed emotions. For example, if the user is feeling stressed, the server sets the interface to be simpler.

[1234] Step 16:

[1235] The server collects user feedback and accumulates data to improve the system's usability, such as recording the user's operation history and changes in emotional state.

[1236] In this way, the user can understand the overall structure and operational status of the system, and can use an interface that is adapted to his or her emotional state.

[1237] Example 2

[1238] 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."

[1239] Conventional system analysis tools were capable of visualizing the analysis results of system code and logs, but they did not adjust the interface to take user emotions into consideration. As a result, when users felt stressed or dissatisfied with the interface, they were unable to respond appropriately, which sometimes resulted in usability issues. In addition, they lacked the ability to monitor the system's operational status in real time, making it difficult to detect abnormalities early and respond appropriately.

[1240] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, means for monitoring the operation status of the system, means for recognizing user emotions, and means for adjusting the user interface based on the user emotions. This makes it possible to appropriately monitor the operation status of the system and quickly respond to abnormal situations while improving usability.

[1241] "Means for receiving uploaded data" refers to the function of receiving data in the process of a user selecting a file and transferring it to the server.

[1242] "Means for analysis using generative AI models" refers to a function that uses artificial intelligence to analyze code structure and patterns based on uploaded data.

[1243] "Means for generating a system configuration diagram based on the analysis results" refers to the function of creating a diagram that visually shows the configuration of the entire system from the analysis results of the generative AI model.

[1244] "Means for visualizing the generated system configuration diagram" refers to a function that displays the generated system configuration diagram on the user's terminal and allows the user to interactively manipulate the diagram.

[1245] "Means for monitoring the operational status of the system" refers to the function of checking in real time whether the system is operating normally or if any abnormalities have occurred, and sending alerts as necessary.

[1246] "Means for recognizing the user's emotions" refers to a function that analyzes the user's facial expressions and voice data to identify their current emotional state.

[1247] "Means for adjusting the user interface based on the user's emotions" refers to a function that dynamically changes the interface in response to the detected user's emotions, thereby improving usability.

[1248] This invention is a system that uses a generative AI model to analyze code files and log files uploaded by users, and generates, visualizes, and monitors system configuration diagrams. It also aims to improve usability by recognizing user emotions and dynamically adjusting the interface.

[1249] Program Generation and Processing

[1250] Hardware and software used

[1251] Hardware

[1252] Server: a computer with a powerful processor and a large amount of memory

[1253] User device: PC or tablet with internet access

[1254] Webcam: A camera for capturing the user's facial expressions

[1255] Microphone: A microphone for capturing the user's voice

[1256] software

[1257] Generative AI models: e.g., GPT-3

[1258] Emotion recognition engine: For example, Amazon Rekognition

[1259] Web server: A server that provides file upload functionality and analysis result display functionality

[1260] Log Analysis Tools: Tools for analyzing log files

[1261] System processing flow

[1262] 1. Data Collection

[1263] A user logs into the system's web portal and uploads the code file (e.g., app_code.py) and log file (e.g., server_log.txt) they want to analyze.

[1264] The server receives the uploaded file and stores it in storage.

[1265] 2. Data Analysis

[1266] The server reads the file and enters a prompt sentence into the generative AI model to begin analysis.

[1267] For example: "Analyze the following code file and identify the structure and dependencies of functions and classes."

[1268] The server also passes the contents of the log file to the generative AI model to analyze error patterns.

[1269] For example: "Please analyze the following log files and identify any error patterns or anomalies."

[1270] 3. System configuration diagram generation

[1271] Based on the analysis results of the AI ​​model generated by the server, a system configuration diagram is created showing the dependencies and communication paths between each component.

[1272] A configuration diagram visually represents the interactions between modules and components.

[1273] 4. Visualization

[1274] The terminal displays the system configuration diagram on the user's browser.

[1275] The user can navigate the diagram and view detailed information about specific modules and components.

[1276] For example, when a user clicks on module A, it displays the functions and dependencies associated with that module.

[1277] 5. Surveillance

[1278] The server monitors the system's operational status in real time, and if it detects an abnormality, it generates an alert and notifies the user.

[1279] For example, it will notify you if an abnormal pattern such as a sudden increase in memory usage or CPU overload is detected.

[1280] 6. Emotion recognition

[1281] The server acquires the user's facial expressions and voice data and analyzes them using an emotion recognition engine.

[1282] Example: "Analyze whether the user is feeling stressed."

[1283] The server identifies the user's emotion based on the acquired emotion data.

[1284] 7. User interface adjustments

[1285] The server dynamically adjusts the user interface based on the emotion recognition results.

[1286] Example: If the user is stressed, simplify the interface or provide appropriate support features.

[1287] By combining a generative AI model and an emotion recognition engine, the system of this invention improves usability and enables appropriate monitoring and management of system operations, allowing users to quickly understand the overall system and respond quickly to abnormal situations.

[1288] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1289] Step 1: Data collection

[1290] A user logs into the system's web portal, selects and uploads the code file (e.g., app_code.py) and log file (e.g., server_log.txt) they want to analyze.

[1291] The server receives these files and stores them in storage.

[1292] Input: User-uploaded code and log files

[1293] Output: File saved on the server

[1294] Step 2: Data analysis

[1295] The server reads the saved file and inputs a prompt to the generative AI model (e.g., GPT-3) to begin analysis.

[1296] Specifically, the server inputs the following prompts into the generative AI model:

[1297] Prompt: "Analyze the following code file and identify the structure and dependencies of functions and classes."

[1298] The server obtains the analysis results from the output of the generative AI model.

[1299] Do the same for the log files:

[1300] Prompt: "Analyze the following log files and identify any error patterns or anomalies."

[1301] Input: Code files and log files stored on the server

[1302] Data processing: Performing analysis using generative AI models

[1303] Output: Analysis results of code structure and dependencies, and error patterns in logs

[1304] Step 3: Generate a system configuration diagram

[1305] The server generates a system configuration diagram based on the analysis results of the generated AI model.

[1306] Create a visual diagram showing the dependencies and communication paths of each component.

[1307] Input: Analysis results (code structure, dependencies, log error patterns)

[1308] Data processing: Create a system configuration diagram using a system configuration diagram generation algorithm

[1309] Output: System configuration diagram

[1310] Step 4: Visualization

[1311] The terminal creates an HTML page for displaying the system configuration diagram on the user's browser.

[1312] The terminal displays the system configuration diagram on the user's browser, allowing interactive operation.

[1313] The user can navigate the diagram and view detailed information about specific modules and components.

[1314] Input: System configuration diagram

[1315] Data processing: HTML page generation and diagram display

[1316] Output: System diagram displayed in the user's browser

[1317] Step 5: Monitoring

[1318] The server runs a script that monitors the system's operational status in real time.

[1319] If an anomaly is detected, the server generates an alert and notifies the user.

[1320] For example, abnormal patterns such as sudden increases in memory usage and CPU overloads are detected.

[1321] Input: Real-time data from the system

[1322] Data calculation: Identify anomalies using anomaly detection algorithms

[1323] Output: Alert notification sent to user

[1324] Step 6: Emotion Recognition

[1325] The server captures the user's webcam video and audio data.

[1326] The server analyzes the user's emotions using an emotion recognition engine (e.g., Amazon Rekognition).

[1327] As a specific example, the server identifies stress or irritation from the user's facial expression.

[1328] Input: Webcam video and audio data

[1329] Data calculation: Emotion analysis using emotion recognition engine

[1330] Output: User emotion data

[1331] Step 7: Adjust the user interface

[1332] The server dynamically adjusts the user interface based on the emotion recognition results.

[1333] For example, if a user is feeling stressed, the interface can be simplified and appropriate support functions provided.

[1334] Input: User emotion data

[1335] Data processing: Using interface adjustment algorithms

[1336] Output: A tailored user interface

[1337] At each step, specific data processing or calculations are performed based on the input data, resulting in an output that is used in the next step, enabling the system to achieve real-time monitoring and anomaly detection while improving usability.

[1338] (Application example 2)

[1339] 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."

[1340] Factory robots are required to reduce operator stress and improve operability while providing efficient operation and real-time monitoring. However, current systems make it difficult to visually grasp the robot's operating status, and they do not dynamically adjust the interface to take into account the operator's emotional state. This increases operator stress and reduces productivity.

[1341] 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.

[1342] In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, means for monitoring the operation status of the system, means for recognizing a user's emotion, and means for adjusting the user interface based on the recognized emotion, thereby enabling an operator to visually grasp the operation status of a factory robot in real time and adjust the interface according to the operator's emotional state.

[1343] The "means for receiving uploaded data" is a function that allows factory operators to send data such as robot operation logs and operating programs to a server, and for the server to receive it.

[1344] "Means of analysis using generative AI models" refers to the use of AI technology to analyze patterns and trends within collected data.

[1345] The "means for generating a system configuration diagram" is a function for creating a diagram that visually represents the relationships and operating status between robots within a factory based on the analysis results.

[1346] "Means for visualizing the generated system configuration diagram" is a function that displays the generated system configuration diagram on the operator's terminal, making it visually easy to understand.

[1347] The "means for monitoring the system's operational status" is a function that continuously monitors the operating status and errors of factory robots in real time, and detects and notifies users if an abnormality occurs.

[1348] "Means for recognizing user emotions" refers to a function that uses devices such as cameras and microphones to analyze the operator's facial expressions and voice to understand their emotional state.

[1349] The "means for adjusting the user interface based on the recognized emotion" is a function that dynamically changes the interface to improve usability in accordance with the recognized emotional state of the operator.

[1350] MODE FOR CARRYING OUT THE INVENTION

[1351] This invention is a system for improving the efficiency of factory robot operations and monitoring them in real time. Furthermore, it aims to reduce operator stress and improve productivity by recognizing the emotions of factory operators and dynamically adjusting the operation interface. This system is composed of the following main hardware and software:

[1352] Hardware

[1353] Device: Any device that can connect to the internet (e.g. smartphone, tablet, PC)

[1354] Camera and microphone: Sensor devices for capturing the operator's facial expressions and voice.

[1355] software

[1356] Generative AI model (e.g., GPT-4): AI technology used to analyze uploaded data

[1357] Emotion recognition engine (e.g. Microsoft Azure Face API): An engine for analyzing the emotional state of the operator

[1358] Database (e.g. MySQL): A database system for storing analysis results and log data.

[1359] Web server (e.g. Apache): A server that hosts the core programs of the system

[1360] Real-time monitoring tools (e.g., Elasticsearch, Kibana): Tools for monitoring system operation status

[1361] System program processing

[1362] 1. Data Collection

[1363] Users log in to a dedicated web portal and upload the factory robot's operation log and operating program (e.g., robot_log.txt, robot_program.py).

[1364] 2. Data Analysis

[1365] The server inputs the received data into a generative AI model (e.g., GPT-4) and analyzes the data for patterns and errors.

[1366] 3. System configuration diagram generation

[1367] Based on the analysis results, the server generates a system configuration diagram showing the operational status of the robots within the factory.

[1368] 4. Visualization

[1369] The terminal interactively displays the generated system configuration diagram, allowing the operator to visually check detailed information about each robot.

[1370] 5. Surveillance

[1371] The server monitors the operational status of factory robots in real time and sends an alert to the operator if an abnormality is detected. For example, information on sudden increases in memory usage or CPU overload is displayed on the dashboard.

[1372] 6. Emotion recognition

[1373] The server uses an emotion recognition engine (e.g., Microsoft Azure Face API) to analyze data obtained from the camera and microphone to understand the operator's emotional state. For example, if the operator is feeling stressed, that information will be analyzed.

[1374] 7. User interface adjustments

[1375] The server dynamically adjusts the user interface based on the analysis results obtained from the emotion recognition engine. For example, if the operator is feeling stressed, the interface will be simplified and the displayed information will be reduced, improving usability.

[1376] Specific examples

[1377] 1. Example prompt

[1378] Data Analysis prompt:

[1379] "Analyze the following robot operation log to identify errors and visualize behavioral patterns. Log data: robot_log.txt"

[1380] System configuration diagram generation prompt:

[1381] "Please generate a system configuration diagram for the factory robot based on the analysis results below. Analysis data: analysis results.json"

[1382] Through a series of processes

[1383] This system allows operators to visually grasp the operating status of factory robots in real time and adjusts the interface according to their emotional state, reducing operator stress and improving productivity and usability.

[1384] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1385] Step 1:

[1386] Data collection

[1387] The user logs in to a dedicated web portal and uploads the factory robot's operation log (e.g., robot_log.txt) and operation program (e.g., robot_program.py). The input is the operation log and operation program files, and the server receives these files as output. Specifically, the user accesses the web portal in a browser and uploads the required files using the file selection dialog.

[1388] Step 2:

[1389] Data analysis

[1390] The server inputs the received data into a generative AI model (e.g., GPT-4) and analyzes patterns and errors within the data. The input is the uploaded log file and operation program, and the analysis results are obtained as output. Specifically, the server sends the received data to the GPT-4 interface and enters a data analysis prompt: "Analyze the following robot operation log, identify errors, and visualize behavioral patterns. Log data: robot_log.txt."

[1391] Step 3:

[1392] System configuration diagram generation

[1393] Based on the analysis results, the server generates a system configuration diagram showing the operational status of the factory robots. The input is the analysis results, and the output is an interactive system configuration diagram. Specifically, the server uses a JavaScript library (e.g., D3.js) to generate the configuration diagram. "Please generate a system configuration diagram for the factory robots based on the following analysis results. Analysis data: Analysis results.json"

[1394] Step 4:

[1395] Visualization

[1396] The terminal interactively displays the generated system configuration diagram, allowing the operator to visually check detailed information about each robot. The input is the generated configuration diagram, and the output is visual information displayed on the operator's terminal. Specifically, the terminal displays the configuration diagram in a web browser, and the user can click to check detailed information.

[1397] Step 5:

[1398] Monitoring

[1399] The server monitors the operational status of factory robots in real time and sends an alert to the operator if an abnormality is detected. The input is real-time log data, and the output is an alert that an abnormality has been detected. Specifically, the server monitors the log data using Elasticsearch and Kibana, and if an abnormality is detected, it notifies the operator via Slack or email.

[1400] Step 6:

[1401] emotion recognition

[1402] The server uses an emotion recognition engine (e.g., Microsoft Azure Face API) to analyze data acquired from the camera and microphone to understand the operator's emotional state. The input is real-time data from the camera and microphone, and the output is an evaluation of the operator's emotional state. Specifically, the server sends real-time data to the emotion recognition engine and inputs a prompt such as "Please analyze the operator's emotional state."

[1403] Step 7:

[1404] User Interface Adjustments

[1405] The server dynamically adjusts the user interface based on the analysis results obtained from the emotion recognition engine. The input is the emotion analysis results, and the output is an adjusted user interface displayed on the terminal. Specifically, the server uses JavaScript and React.js to change the interface and adjust the displayed information appropriately according to the operator's stress level.

[1406] 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.

[1407] 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.

[1408] 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.

[1409] [Fourth embodiment]

[1410] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1411] 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.

[1412] 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).

[1413] 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.

[1414] 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.

[1415] 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).

[1416] 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. 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.

[1417] 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.

[1418] 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.

[1419] 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.

[1420] 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.

[1421] 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.

[1422] 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."

[1423] The present invention provides a system for visualizing and monitoring the configuration of a system that has been in operation for a long period of time, thereby supporting efficient analysis, modification, and operation of the system.

[1424] System Overview

[1425] The system includes the following key features:

[1426] 1. Data Collection

[1427] The user uploads the code file, log file, specification, or manual that he / she wants to analyze to the server.

[1428] 2. Data Analysis

[1429] The server analyzes the received files using a generative AI model to extract code structure, log patterns, and specification contents.

[1430] 3. System configuration diagram generation

[1431] Based on the analysis results, the server generates a system configuration diagram that shows the dependencies and communication paths between each component of the system.

[1432] 4. Visualization

[1433] The terminal visually displays an interactive system configuration diagram to the user, allowing the user to manipulate the diagram.

[1434] 5. Surveillance

[1435] The server monitors the system's operational status in real time and notifies the user if an abnormality is detected.

[1436] Program processing

[1437] 1. Data Collection

[1438] Users log in to the system's web portal and select and upload the files they want to analyze, which can be in a variety of formats, including source code, log files, specifications, and manuals.

[1439] 2. Data Analysis

[1440] The server receives the uploaded files and identifies their data format. It uses a generative AI model to analyze the code structure and extract dependencies between functions, classes, and modules. For log files, it analyzes entries and identifies patterns of errors and warnings.

[1441] 3. System configuration diagram generation

[1442] The server aggregates the analysis results and generates a data structure that illustrates the relationships between components. This data structure is then used to generate a system diagram, which visually shows how the parts of the system interact with each other.

[1443] 4. Visualization

[1444] The terminal displays the generated system diagram in the user's browser. The user can interact with the diagram and view detailed information. For example, clicking on a specific module displays details about its dependencies and functions.

[1445] 5. Surveillance

[1446] The server monitors the system's operational status in real time and detects abnormal patterns and errors. If an abnormality is detected, the user is notified and a warning message is displayed on the dashboard. At the same time, detailed information about the abnormality and the scope of its impact are also reported to the user.

[1447] Specific examples

[1448] 1. Data Collection

[1449] A user logs into the system's web portal and uploads the latest application code file (e.g., app_code.py) and system log file (e.g., server_log.txt).

[1450] 2. Data Analysis

[1451] The server receives app_code.py and server_log.txt, inputs these files into the AI ​​model, and begins analysis. The AI ​​model extracts function dependencies within the code and identifies error patterns from the log file.

[1452] 3. System configuration diagram generation

[1453] Based on the analysis results, the server generates a system configuration diagram showing the relationships between functions, classes, and modules. This configuration diagram visually displays dependencies between modules and error locations.

[1454] 4. Visualization

[1455] The device displays a system diagram in the user's browser. The user can click on the diagram to view details of specific modules or functions. For example, clicking on Module A displays the associated functions and dependencies.

[1456] 5. Surveillance

[1457] The server performs real-time monitoring of the system and displays a warning on the dashboard if it detects any abnormal behavior. For example, if memory usage spikes, an alert is generated, showing the affected module and how to address it.

[1458] In this way, the system of the present invention enables the user to quickly understand the entire system and appropriately monitor the operational status, thereby supporting efficient system modification and operation.

[1459] The processing flow will be explained below.

[1460] Step 1:

[1461] The user logs into the system's web portal and clicks the "Upload analysis file" button.

[1462] Step 2:

[1463] The user selects the files they want to analyze (e.g., source code files, log files, specifications, or manuals) and uploads them to the server.

[1464] Step 3:

[1465] The server receives the uploaded file and automatically identifies the file format and content, for example, checking whether it is a code file, log file, or specification document.

[1466] Step 4:

[1467] The server inputs the received files into a generative AI model, which analyzes the code structure, function call relationships, and dependencies. For example, it extracts that function A calls function B, or that module X depends on library Y.

[1468] Step 5:

[1469] The server analyzes the log file entries to identify the frequency and occurrence patterns of errors and warnings, for example, the frequency of occurrence of the error message "ERROR" and the warning message "WARNING".

[1470] Step 6:

[1471] The server analyzes the text of specifications and manuals and extracts important points and constraints of the system specifications.

[1472] Step 7:

[1473] Based on the analysis results, the server generates a data structure that shows the dependencies and communication paths between each component. The dependencies and API call relationships between each module are represented by nodes and edges.

[1474] Step 8:

[1475] The server generates a system configuration diagram based on the generated data structure. This diagram includes the relationships between modules and components, the locations of errors, and so on.

[1476] Step 9:

[1477] The terminal displays the system configuration diagram in the user's browser, and the user can interactively click on each node or edge to display detailed information.

[1478] Step 10:

[1479] Users can explore the diagram and learn more about specific modules and components. For example, clicking on Module A displays the functions and dependencies associated with that module.

[1480] Step 11:

[1481] The server monitors the system's operation in real time, checking for new log entries and changes in system state, and running algorithms to detect abnormal patterns and errors.

[1482] Step 12:

[1483] If the server detects an abnormality, it will send an alert to the user, providing them with a notification containing detailed information about the abnormality and the extent of its impact.

[1484] Step 13:

[1485] Users receive alerts and can view detailed information in a dashboard, such as memory usage spikes or CPU overloads.

[1486] As described above, by performing specific processing for each step, the user can easily grasp the overall structure and operational status of the system, enabling efficient modification and operation.

[1487] Example 1

[1488] 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."

[1489] With existing systems, it is difficult to quickly grasp the overall picture of the system and efficiently monitor and modify it. In particular, in complex systems that have been in operation for a long time, it is important to visualize the dependencies and communication paths between components and monitor the operational status in real time, but there are currently no easy ways to achieve this. A notification system is also needed to respond instantly when an abnormality occurs.

[1490] 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.

[1491] In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, means for monitoring the system's operational status, means for selecting uploaded data after user authentication, means for interactively displaying details of the configuration diagram to the user, and means for notifying the user when an abnormality is detected. This allows the user to quickly grasp the overall picture of the system and efficiently analyze, repair, and operate it. Real-time monitoring of the system's operational status and immediate notification of abnormalities enable early detection and response to problems.

[1492] "Uploaded Data" refers to electronic data such as source code, log files, specifications, or manuals that a user sends to the system.

[1493] "Means of receiving" refers to the functions and processes by which the server obtains uploaded data.

[1494] "Generative AI models" refer to artificial intelligence algorithms used to automate the analysis of data and extract advanced information.

[1495] "Means for analyzing" refers to the functions or processes used to analyze received data and extract meaningful information or patterns.

[1496] A "system configuration diagram" is a diagram that visually shows the dependencies and communication paths between each component within a system.

[1497] "Visualization means" refers to the functions and processes for visually displaying the generated system configuration diagram to the user.

[1498] "Means for monitoring the operational status of the system" refers to functions and processes for monitoring in real time whether the system is operating normally and detecting abnormalities.

[1499] "Means for selecting uploaded data after authentication" refers to the functionality or process for selecting and using data within the system after a user has provided valid authentication information.

[1500] "Means for interactively displaying details of the configuration diagram" refers to functions and processes that allow a user to manipulate the system configuration diagram and dynamically view detailed information.

[1501] "Means for notifying users when an abnormality is detected" refers to functions and processes for quickly notifying users of an abnormality when it is discovered during system monitoring.

[1502] This invention relates to a system for visualizing and monitoring system configurations. This system receives uploaded data and analyzes it using a generative AI model. It then generates a system configuration diagram based on the analysis results and provides it visually to the user. It also includes a function to monitor the system's operational status in real time and notify the user when an abnormality is detected.

[1503] 1. Data Collection and Reception

[1504] Users log in to the system through a web portal and upload the source code, log files, specifications, or manuals they want to analyze. For example, a user can select and upload files named app_code.py and server_log.txt. These data are then transferred to the server.

[1505] 2. Data Analysis

[1506] The server receives the uploaded data and feeds it into a generative AI model that extracts function dependencies in the code and identifies error patterns in log files. The hardware used is a dedicated server, and the software includes a deep learning framework.

[1507] Example: The server generates a prompt statement saying "Start code analysis" and sends it to the generative AI model.

[1508] 3. Generating a system configuration diagram

[1509] The server generates a data structure for a system configuration diagram based on the results of the data analysis. This configuration diagram includes dependencies and communication paths between each component of the system. The server then draws a visual system configuration diagram based on this data structure.

[1510] 4. Visualization

[1511] The terminal displays the generated system diagram in the user's browser. The user can click on the diagram to interactively view the details of a specific module or component. For example, when the user clicks on module A, a pop-up appears with details of its functions and dependencies.

[1512] 5. Real-time monitoring and notifications

[1513] The server continuously monitors the system's operational status. If it detects abnormal behavior or an error pattern, it notifies the user and displays a warning message on the dashboard. The hardware used is a module dedicated to monitoring, and the software includes a monitoring tool. For example, if the server detects a sudden increase in memory usage, it displays a warning message on the dashboard saying, "Memory usage has increased sharply, affecting module A."

[1514] In this way, this system allows users to quickly grasp the overall picture of the system and efficiently analyze, repair, and operate it.In addition, real-time monitoring of the system's operating status and immediate notification of abnormalities enable early detection and response to problems.

[1515] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1516] Step 1:

[1517] The user accesses the web portal and enters their credentials. If the correct credentials are entered, the user is able to access the dashboard.

[1518] Input: Username, Password

[1519] Output: Authentication token, dashboard screen

[1520] Specific operation: The user accesses "example.com", enters their username and password, and presses the "Login" button.

[1521] Step 2:

[1522] The user clicks the upload button on the dashboard, selects the file they want to analyze, and uploads it. This file is then sent to the server.

[1523] Input: File to be analyzed (e.g. app_code.py, server_log.txt)

[1524] Output: A confirmation message for the uploaded file

[1525] Specific behavior: The user clicks the "File Upload" button, selects app_code.py and server_log.txt, and then clicks the "Upload" button.

[1526] Step 3:

[1527] The server receives the uploaded files, identifies the data format of each file, and inputs these files into a generative AI model to perform data analysis.

[1528] Input: Uploaded file

[1529] Output: Analysis results (code dependencies, log error patterns)

[1530] Specific operation: The server passes app_code.py and server_log.txt to the generated AI model, generates a prompt statement saying "Start code analysis", and sends it to the AI ​​model.

[1531] Step 4:

[1532] Based on the results of the data analysis, the server generates a data structure for a system configuration diagram, which includes dependencies and communication paths between components.

[1533] Input: Analysis results (code dependencies, log error patterns)

[1534] Output: System configuration diagram data structure

[1535] Specific operation: The server executes the "process for generating configuration diagram data," registers dependencies and communication paths in a database, and draws a system configuration diagram.

[1536] Step 5:

[1537] The terminal visually displays the generated system configuration diagram in the user's browser, and the user can click on the diagram to view detailed information.

[1538] Input: System configuration diagram data structure

[1539] Output: System configuration diagram on browser

[1540] Specific operation: The terminal displays a system configuration diagram on the browser, and when the user clicks on a specific module, detailed information related to that module will be displayed in a pop-up.

[1541] Step 6:

[1542] The server monitors the system's operational status in real time, detecting abnormal behavior and error patterns. If an abnormality occurs, it notifies the user and displays a warning message on the dashboard.

[1543] Input: Real-time system data

[1544] Output: Anomaly detection, warning message

[1545] Specific operation: When the server performs "real-time monitoring" and detects a sudden increase in memory usage, a warning message will be displayed on the dashboard stating "Memory usage has increased sharply, affecting module A."

[1546] This allows users to efficiently understand the system configuration and operational status, and to respond quickly when a problem occurs.

[1547] (Application example 1)

[1548] 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."

[1549] With conventional systems, it is difficult to efficiently visualize and analyze the configuration of systems that have been in operation for a long time, which has resulted in the problem of system operation and modification taking a great deal of time and effort.In addition, early detection of abnormalities and real-time operational monitoring are insufficient, resulting in problems such as a decline in system stability and reliability.

[1550] 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.

[1551] In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, and means for monitoring the system's operational status and notifying when an abnormality is detected. This enables efficient visualization and analysis of the system configuration, and real-time operational monitoring and abnormality detection.

[1552] The "means for receiving uploaded data" is a function for importing data sent by a user into the server.

[1553] "Means for analysis using a generative AI model" refers to a function that analyzes uploaded data using an artificial intelligence model and extracts data structures and patterns.

[1554] The "means for generating a system configuration diagram" is a function that creates a diagram that visually represents the relationships between each component of the system based on the results of the analyzed data.

[1555] The "means for visualizing the system configuration diagram" is a function that allows the user to interactively display the generated system configuration diagram and operate it.

[1556] "Means for monitoring the system's operational status and notifying users if an abnormality is detected" refers to a function that monitors the system's operation in real time and sends an alert to users if an abnormality occurs.

[1557] MODE FOR CARRYING OUT THE INVENTION

[1558] The present invention provides a system that efficiently visualizes the operation of factory robots, enabling early detection of abnormalities and real-time operation monitoring. Hereinafter, embodiments of the present invention will be described.

[1559] System configuration

[1560] The system primarily consists of the following major components:

[1561] 1. Server

[1562] 2. User device (smartphone, etc.)

[1563] 3. Operational data collection device for factory robots

[1564] System Features

[1565] 1. Means of receiving uploaded data:

[1566] The user terminal receives the factory robot's operational data (e.g., log files and operation history data) from the collection device and uploads it to the cloud server, which receives and stores this data.

[1567] 2. Means of analyzing received data using a generative AI model:

[1568] The server inputs the uploaded data into a generative AI model and begins analysis. The AI ​​model uses a high-performance language model such as GPT-4. Through analysis, patterns and anomalies are identified within the operational data.

[1569] 3. How to generate a system diagram based on the analysis results:

[1570] Based on the analysis results, the server generates a system configuration diagram that shows the operational status and dependencies of each robot in the factory. The system configuration diagram visually displays the location, communication paths, and operational status of each robot.

[1571] 4. A way to visualize the generated system diagram:

[1572] The generated system configuration diagram is sent to the user's device and displayed in an interactive format, allowing the user to tap and zoom to view detailed information.

[1573] 5. Monitoring the system's operational status and notifying you if an abnormality is detected:

[1574] The server monitors operational data in real time, and if an abnormality is detected, it sends an alert via push notification to the user's device, allowing the user to respond promptly without missing the timing of the abnormality.

[1575] Specific examples of hardware and software used

[1576] Server: Cloud server (e.g. Amazon Web Services)

[1577] User device: Smartphone (iOS or Android)

[1578] Generative AI model: GPT-4 (OpenAI)

[1579] Specific examples

[1580] 1. Data Collection Example:

[1581] The user device receives the latest factory robot operation data (e.g., robot_log.txt) and uploads it to the cloud server.

[1582] 2. Data analysis example:

[1583] The server receives robot_log.txt and begins analyzing it with GPT-4, which extracts dependencies between specific functions and abnormal patterns.

[1584] 3. Example of system configuration diagram generation:

[1585] The server generates a system configuration diagram based on the analysis results, visually representing the operational status and dependencies of each robot.

[1586] 4. Visualization example:

[1587] The system configuration diagram is sent to the user's device and displayed in an interactive format on the device screen, where the user can tap on a specific robot to view more information.

[1588] 5. Monitoring and Notification Examples:

[1589] The server monitors in real time and sends a push notification to the user's device if an abnormality is detected. Example: "Robot 123's memory usage is increasing rapidly. Please check immediately."

[1590] Prompt Sentence Examples

[1591] "Please analyze the following robot operation log data and clearly indicate the dependencies between functions and the location of the error. Log data: [Part of the detailed log data]"

[1592] In this way, it becomes possible to efficiently monitor the operation of factory robots and quickly detect abnormalities.

[1593] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1594] Step 1:

[1595] Data collection

[1596] The user uploads the operation data (e.g., log files) of the factory robot to the user terminal. The uploaded data includes operation history data, error logs, performance data, etc. The user terminal sends this data to the cloud server. The input is the robot operation data (in file format), and the output is the data stored on the cloud server.

[1597] Step 2:

[1598] Data reception

[1599] The server receives data sent from the user's device and stores it in a database. In particular, it checks whether the received data has been uploaded correctly and converts it into the required data format. During this process, detailed log information and error messages are entered, and this is converted into an internal database format and stored.

[1600] Step 3:

[1601] Data analysis preparation

[1602] The server prepares the received data for input to a generative AI model for analysis. Specifically, it converts the data into an appropriate format and generates a prompt. For example, it prepares a prompt such as, "Analyze this robot log and extract behavior patterns and dependencies." The input is the converted log information, and the output is the prompt and converted data that are input to the generative AI model.

[1603] Step 4:

[1604] Data analysis

[1605] The server analyzes the data using a generative AI model (e.g., GPT-4). Here, the prompt sentence and the converted data are input into the AI ​​model, and as a result, the robot's behavior patterns, dependencies, error patterns, etc. are extracted. The input for the analysis is the prompt sentence and data, and the output is the analysis results, such as a dependency list and error log patterns.

[1606] Step 5:

[1607] System configuration diagram generation

[1608] The server generates a system configuration diagram based on the analysis results. This configuration diagram is designed to visually show the placement of each robot, their dependencies, and the locations of abnormalities. The input is a dependency list from the analysis results, and the output is a system configuration diagram.

[1609] Step 6:

[1610] Configuration visualization

[1611] The server sends the generated system configuration diagram to the user's device. The device displays the diagram in an interactive format, allowing the user to zoom, tap, and view detailed information. The input is the system configuration diagram data, and the output is interactive visual information displayed on the device.

[1612] Step 7:

[1613] Operational status monitoring and notification

[1614] The server monitors the system's operational status in real time and sends a notification to the user's device if it detects an abnormality. For example, if the robot's memory usage increases sharply, an alert is sent via push notification. The input to this process is real-time monitoring data, and the output is an alert notification sent to the user when an abnormality occurs.

[1615] 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.

[1616] This invention combines a system that uses a generative AI model to analyze system codes and logs, visualizes and monitors system configuration diagrams, and an emotion engine that recognizes user emotions. This system not only enables users to quickly understand the overall system and maintain proper operating conditions, but also adjusts the interface based on the user's emotions, further improving usability.

[1617] System Overview

[1618] The system includes the following key features:

[1619] 1. Data Collection

[1620] The user uploads the code file, log file, specification, or manual that he / she wants to analyze to the server.

[1621] 2. Data Analysis

[1622] The server analyzes the received files using a generative AI model to extract code structure, log patterns, and specification contents.

[1623] 3. System configuration diagram generation

[1624] Based on the analysis results, the server generates a system configuration diagram that shows the dependencies and communication paths between each component of the system.

[1625] 4. Visualization

[1626] The terminal visually displays an interactive system configuration diagram to the user, allowing the user to manipulate the diagram.

[1627] 5. Surveillance

[1628] The server monitors the system's operational status in real time and notifies the user if an abnormality is detected.

[1629] 6. Emotion recognition

[1630] The server uses an emotion engine to analyze emotions from the user's facial expressions and voice.

[1631] 7. User interface adjustments

[1632] The server adjusts the user interface based on the analyzed emotions to improve usability.

[1633] Program processing

[1634] 1. Data Collection

[1635] Users log into the system's web portal, select and upload the files they want to analyze, and the server receives the data, which can be code files, log files, specifications, or manuals.

[1636] 2. Data Analysis

[1637] The server uses a generative AI model to analyze the uploaded files, extracting the structure and dependencies of functions and classes in the code and identifying error patterns in log files.

[1638] 3. System configuration diagram generation

[1639] The server uses the analysis results to generate a system diagram that shows the relationships between each component. The system diagram visually displays how each part of the system interacts.

[1640] 4. Visualization

[1641] The device displays the generated system diagram in the user's browser. The user can click on the diagram to view detailed information about a specific module or component. For example, clicking on module A displays the functions and dependencies associated with that module.

[1642] 5. Surveillance

[1643] The server monitors the system's operational status in real time, and if any abnormal patterns or errors are detected, an alert notification is sent to the user and detailed information is displayed on the dashboard.

[1644] 6. Emotion recognition

[1645] The server uses an emotion engine to analyze the user's facial expressions and voice to recognize their current emotional state. For example, if the user is feeling stressed, that information will be analyzed.

[1646] 7. User interface adjustments

[1647] The server dynamically adjusts the user interface based on the analysis results obtained from the emotion engine. For example, if the user is feeling stressed, the interface will be simplified or appropriate support will be provided.

[1648] Specific examples

[1649] 1. Data Collection

[1650] A user logs into the system's web portal and uploads the latest application code file (e.g., app_code.py) and system log file (e.g., server_log.txt).

[1651] 2. Data Analysis

[1652] The server inputs app_code.py and server_log.txt into the generative AI model, which analyzes code dependencies and log error patterns.

[1653] 3. System configuration diagram generation

[1654] The server generates a system configuration diagram based on the analysis results and visually displays the interdependencies of each module and component.

[1655] 4. Visualization

[1656] The terminal displays a system configuration diagram on the user's screen, and the user can click on the diagram to view detailed information about a specific module.

[1657] 5. Surveillance

[1658] The server monitors the system in real time and issues an alert when it detects an abnormality. Information such as sudden increases in memory usage and CPU overload is displayed on the dashboard.

[1659] 6. Emotion recognition

[1660] The server uses an emotion engine to analyze the user's facial expressions and voice to understand their emotional state. For example, if the user is irritated, that emotional data will be analyzed.

[1661] 7. User interface adjustments

[1662] The server adjusts the interface based on the user's emotional data. If the user is feeling stressed, the system automatically simplifies operation and reduces the amount of information presented to the user.

[1663] As described above, the system of the present invention combines a generative AI model and an emotion engine, allowing users to quickly understand the overall system and maintain appropriate operation. Furthermore, usability is improved by adjusting the interface according to the user's emotions.

[1664] The processing flow will be explained below.

[1665] Step 1:

[1666] The user logs into the system's web portal and clicks the "Upload analysis file" button.

[1667] Step 2:

[1668] The user selects the files they want to analyze (e.g., source code files, log files, specifications, or manuals) and uploads them to the server.

[1669] Step 3:

[1670] The server receives the uploaded file and automatically identifies the file format and content, for example, checking whether it is a code file, log file, or specification document.

[1671] Step 4:

[1672] The server inputs the received files into a generative AI model, which analyzes the code structure, function call relationships, and dependencies. For example, it verifies that function A calls function B, or that module X depends on library Y.

[1673] Step 5:

[1674] The server analyzes the log file entries to identify the frequency and occurrence patterns of errors and warnings, for example, by counting the frequency of the error message "ERROR" and the warning message "WARNING."

[1675] Step 6:

[1676] The server analyzes the text of specifications and manuals and extracts important points and constraints of the system specifications.

[1677] Step 7:

[1678] Based on the analysis results, the server generates a data structure that shows the dependencies and communication paths between components. For example, it represents the dependencies and API call relationships between modules using nodes and edges.

[1679] Step 8:

[1680] The server generates a system configuration diagram based on the generated data structure. This diagram includes the relationships between modules and components, the locations of errors, and so on.

[1681] Step 9:

[1682] The terminal displays the system configuration diagram in the user's browser, and the user can interactively click on each node or edge to display detailed information.

[1683] Step 10:

[1684] Users can explore the diagram and learn more about specific modules and components. For example, clicking on Module A displays the functions and dependencies associated with that module.

[1685] Step 11:

[1686] The server monitors the system's operation in real time, checking for new log entries and changes in system state, and running algorithms to detect abnormal patterns and errors.

[1687] Step 12:

[1688] If the server detects an abnormality, it will send an alert to the user, providing them with a notification containing detailed information about the abnormality and the extent of its impact.

[1689] Step 13:

[1690] Users receive alerts and can view detailed information on a dashboard, such as memory usage spikes or CPU overloads.

[1691] Step 14:

[1692] The server uses an emotion engine to analyze the user's facial expressions and voice to recognize their current emotional state. For example, if the user is feeling stressed, that information is obtained.

[1693] Step 15:

[1694] The server adjusts the interface based on the analyzed emotions. For example, if the user is feeling stressed, the server sets the interface to be simpler.

[1695] Step 16:

[1696] The server collects user feedback and accumulates data to improve the system's usability, such as recording the user's operation history and changes in emotional state.

[1697] In this way, the user can understand the overall structure and operational status of the system, and can use an interface that is adapted to his or her emotional state.

[1698] Example 2

[1699] 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."

[1700] Conventional system analysis tools were capable of visualizing the analysis results of system code and logs, but they did not adjust the interface to take user emotions into consideration. As a result, when users felt stressed or dissatisfied with the interface, they were unable to respond appropriately, which sometimes resulted in usability issues. In addition, they lacked the ability to monitor the system's operational status in real time, making it difficult to detect abnormalities early and respond appropriately.

[1701] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, means for monitoring the operation status of the system, means for recognizing user emotions, and means for adjusting the user interface based on the user emotions. This makes it possible to appropriately monitor the operation status of the system and quickly respond to abnormal situations while improving usability.

[1702] "Means for receiving uploaded data" refers to the function of receiving data in the process of a user selecting a file and transferring it to the server.

[1703] "Means for analysis using generative AI models" refers to a function that uses artificial intelligence to analyze code structure and patterns based on uploaded data.

[1704] "Means for generating a system configuration diagram based on the analysis results" refers to the function of creating a diagram that visually shows the configuration of the entire system from the analysis results of the generative AI model.

[1705] "Means for visualizing the generated system configuration diagram" refers to a function that displays the generated system configuration diagram on the user's terminal and allows the user to interactively manipulate the diagram.

[1706] "Means for monitoring the operational status of the system" refers to the function of checking in real time whether the system is operating normally or if any abnormalities have occurred, and sending alerts as necessary.

[1707] "Means for recognizing the user's emotions" refers to a function that analyzes the user's facial expressions and voice data to identify their current emotional state.

[1708] "Means for adjusting the user interface based on the user's emotions" refers to a function that dynamically changes the interface in response to the detected user's emotions, thereby improving usability.

[1709] This invention is a system that uses a generative AI model to analyze code files and log files uploaded by users, and generates, visualizes, and monitors system configuration diagrams. It also aims to improve usability by recognizing user emotions and dynamically adjusting the interface.

[1710] Program Generation and Processing

[1711] Hardware and software used

[1712] Hardware

[1713] Server: a computer with a powerful processor and a large amount of memory

[1714] User device: PC or tablet with internet access

[1715] Webcam: A camera for capturing the user's facial expressions

[1716] Microphone: A microphone for capturing the user's voice

[1717] software

[1718] Generative AI models: e.g., GPT-3

[1719] Emotion recognition engine: For example, Amazon Rekognition

[1720] Web server: A server that provides file upload functionality and analysis result display functionality

[1721] Log Analysis Tools: Tools for analyzing log files

[1722] System processing flow

[1723] 1. Data Collection

[1724] A user logs into the system's web portal and uploads the code file (e.g., app_code.py) and log file (e.g., server_log.txt) they want to analyze.

[1725] The server receives the uploaded file and stores it in storage.

[1726] 2. Data Analysis

[1727] The server reads the file and enters a prompt sentence into the generative AI model to begin analysis.

[1728] For example: "Analyze the following code file and identify the structure and dependencies of functions and classes."

[1729] The server also passes the contents of the log file to the generative AI model to analyze error patterns.

[1730] For example: "Please analyze the following log files and identify any error patterns or anomalies."

[1731] 3. System configuration diagram generation

[1732] Based on the analysis results of the AI ​​model generated by the server, a system configuration diagram is created showing the dependencies and communication paths between each component.

[1733] A configuration diagram visually represents the interactions between modules and components.

[1734] 4. Visualization

[1735] The terminal displays the system configuration diagram on the user's browser.

[1736] The user can navigate the diagram and view detailed information about specific modules and components.

[1737] For example, when a user clicks on module A, it displays the functions and dependencies associated with that module.

[1738] 5. Surveillance

[1739] The server monitors the system's operational status in real time, and if it detects an abnormality, it generates an alert and notifies the user.

[1740] For example, it will notify you if an abnormal pattern such as a sudden increase in memory usage or CPU overload is detected.

[1741] 6. Emotion recognition

[1742] The server acquires the user's facial expressions and voice data and analyzes them using an emotion recognition engine.

[1743] Example: "Analyze whether the user is feeling stressed."

[1744] The server identifies the user's emotion based on the acquired emotion data.

[1745] 7. User interface adjustments

[1746] The server dynamically adjusts the user interface based on the emotion recognition results.

[1747] Example: If the user is stressed, simplify the interface or provide appropriate support features.

[1748] By combining a generative AI model and an emotion recognition engine, the system of this invention improves usability and enables appropriate monitoring and management of system operations, allowing users to quickly understand the overall system and respond quickly to abnormal situations.

[1749] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1750] Step 1: Data collection

[1751] A user logs into the system's web portal, selects and uploads the code file (e.g., app_code.py) and log file (e.g., server_log.txt) they want to analyze.

[1752] The server receives these files and stores them in storage.

[1753] Input: User-uploaded code and log files

[1754] Output: File saved on the server

[1755] Step 2: Data analysis

[1756] The server reads the saved file and inputs a prompt to the generative AI model (e.g., GPT-3) to begin analysis.

[1757] Specifically, the server inputs the following prompts into the generative AI model:

[1758] Prompt: "Analyze the following code file and identify the structure and dependencies of functions and classes."

[1759] The server obtains the analysis results from the output of the generative AI model.

[1760] Do the same for the log files:

[1761] Prompt: "Analyze the following log files and identify any error patterns or anomalies."

[1762] Input: Code files and log files stored on the server

[1763] Data processing: Performing analysis using generative AI models

[1764] Output: Analysis results of code structure and dependencies, and error patterns in logs

[1765] Step 3: Generate a system configuration diagram

[1766] The server generates a system configuration diagram based on the analysis results of the generated AI model.

[1767] Create a visual diagram showing the dependencies and communication paths of each component.

[1768] Input: Analysis results (code structure, dependencies, log error patterns)

[1769] Data processing: Create a system configuration diagram using a system configuration diagram generation algorithm

[1770] Output: System configuration diagram

[1771] Step 4: Visualization

[1772] The terminal creates an HTML page for displaying the system configuration diagram on the user's browser.

[1773] The terminal displays the system configuration diagram on the user's browser, allowing interactive operation.

[1774] The user can navigate the diagram and view detailed information about specific modules and components.

[1775] Input: System configuration diagram

[1776] Data processing: HTML page generation and diagram display

[1777] Output: System diagram displayed in the user's browser

[1778] Step 5: Monitoring

[1779] The server runs a script that monitors the system's operational status in real time.

[1780] If an anomaly is detected, the server generates an alert and notifies the user.

[1781] For example, abnormal patterns such as sudden increases in memory usage and CPU overloads are detected.

[1782] Input: Real-time data from the system

[1783] Data calculation: Identify anomalies using anomaly detection algorithms

[1784] Output: Alert notification sent to user

[1785] Step 6: Emotion Recognition

[1786] The server captures the user's webcam video and audio data.

[1787] The server analyzes the user's emotions using an emotion recognition engine (e.g., Amazon Rekognition).

[1788] As a specific example, the server identifies stress or irritation from the user's facial expression.

[1789] Input: Webcam video and audio data

[1790] Data calculation: Emotion analysis using emotion recognition engine

[1791] Output: User emotion data

[1792] Step 7: Adjust the user interface

[1793] The server dynamically adjusts the user interface based on the emotion recognition results.

[1794] For example, if a user is feeling stressed, the interface can be simplified and appropriate support functions provided.

[1795] Input: User emotion data

[1796] Data processing: Using interface adjustment algorithms

[1797] Output: A tailored user interface

[1798] At each step, specific data processing or calculations are performed based on the input data, resulting in an output that is used in the next step, enabling the system to achieve real-time monitoring and anomaly detection while improving usability.

[1799] (Application example 2)

[1800] 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."

[1801] Factory robots are required to reduce operator stress and improve operability while providing efficient operation and real-time monitoring. However, current systems make it difficult to visually grasp the robot's operating status, and they do not dynamically adjust the interface to take into account the operator's emotional state. This increases operator stress and reduces productivity.

[1802] 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.

[1803] In this invention, the server includes means for receiving uploaded data, means for analyzing the received data using a generative AI model, means for generating a system configuration diagram based on the analysis results, means for visualizing the generated system configuration diagram, means for monitoring the operation status of the system, means for recognizing a user's emotion, and means for adjusting the user interface based on the recognized emotion, thereby enabling an operator to visually grasp the operation status of a factory robot in real time and adjust the interface according to the operator's emotional state.

[1804] The "means for receiving uploaded data" is a function that allows factory operators to send data such as robot operation logs and operating programs to a server, and for the server to receive it.

[1805] "Means of analysis using generative AI models" refers to the use of AI technology to analyze patterns and trends within collected data.

[1806] The "means for generating a system configuration diagram" is a function for creating a diagram that visually represents the relationships and operating status between robots within a factory based on the analysis results.

[1807] "Means for visualizing the generated system configuration diagram" is a function that displays the generated system configuration diagram on the operator's terminal, making it visually easy to understand.

[1808] The "means for monitoring the system's operational status" is a function that continuously monitors the operating status and errors of factory robots in real time, and detects and notifies users if an abnormality occurs.

[1809] "Means for recognizing user emotions" refers to a function that uses devices such as cameras and microphones to analyze the operator's facial expressions and voice to understand their emotional state.

[1810] The "means for adjusting the user interface based on the recognized emotion" is a function that dynamically changes the interface to improve usability in accordance with the recognized emotional state of the operator.

[1811] MODE FOR CARRYING OUT THE INVENTION

[1812] This invention is a system for improving the efficiency of factory robot operations and monitoring them in real time. Furthermore, it aims to reduce operator stress and improve productivity by recognizing the emotions of factory operators and dynamically adjusting the operation interface. This system is composed of the following main hardware and software:

[1813] Hardware

[1814] Device: Any device that can connect to the internet (e.g. smartphone, tablet, PC)

[1815] Camera and microphone: Sensor devices for capturing the operator's facial expressions and voice.

[1816] software

[1817] Generative AI model (e.g., GPT-4): AI technology used to analyze uploaded data

[1818] Emotion recognition engine (e.g. Microsoft Azure Face API): An engine for analyzing the emotional state of the operator

[1819] Database (e.g. MySQL): A database system for storing analysis results and log data.

[1820] Web server (e.g. Apache): A server that hosts the core programs of the system

[1821] Real-time monitoring tools (e.g., Elasticsearch, Kibana): Tools for monitoring system operation status

[1822] System program processing

[1823] 1. Data Collection

[1824] Users log in to a dedicated web portal and upload the factory robot's operation log and operating program (e.g., robot_log.txt, robot_program.py).

[1825] 2. Data Analysis

[1826] The server inputs the received data into a generative AI model (e.g., GPT-4) and analyzes the data for patterns and errors.

[1827] 3. System configuration diagram generation

[1828] Based on the analysis results, the server generates a system configuration diagram showing the operational status of the robots within the factory.

[1829] 4. Visualization

[1830] The terminal interactively displays the generated system configuration diagram, allowing the operator to visually check detailed information about each robot.

[1831] 5. Surveillance

[1832] The server monitors the operational status of factory robots in real time and sends an alert to the operator if an abnormality is detected. For example, information on sudden increases in memory usage or CPU overload is displayed on the dashboard.

[1833] 6. Emotion recognition

[1834] The server uses an emotion recognition engine (e.g., Microsoft Azure Face API) to analyze data obtained from the camera and microphone to understand the operator's emotional state. For example, if the operator is feeling stressed, that information will be analyzed.

[1835] 7. User interface adjustments

[1836] The server dynamically adjusts the user interface based on the analysis results obtained from the emotion recognition engine. For example, if the operator is feeling stressed, the interface will be simplified and the displayed information will be reduced, improving usability.

[1837] Specific examples

[1838] 1. Example prompt

[1839] Data Analysis prompt:

[1840] "Analyze the following robot operation log to identify errors and visualize behavioral patterns. Log data: robot_log.txt"

[1841] System configuration diagram generation prompt:

[1842] "Please generate a system configuration diagram for the factory robot based on the analysis results below. Analysis data: analysis results.json"

[1843] Through a series of processes

[1844] This system allows operators to visually grasp the operating status of factory robots in real time and adjusts the interface according to their emotional state, reducing operator stress and improving productivity and usability.

[1845] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1846] Step 1:

[1847] Data collection

[1848] The user logs in to a dedicated web portal and uploads the factory robot's operation log (e.g., robot_log.txt) and operation program (e.g., robot_program.py). The input is the operation log and operation program files, and the server receives these files as output. Specifically, the user accesses the web portal in a browser and uploads the required files using the file selection dialog.

[1849] Step 2:

[1850] Data analysis

[1851] The server inputs the received data into a generative AI model (e.g., GPT-4) and analyzes patterns and errors within the data. The input is the uploaded log file and operation program, and the analysis results are obtained as output. Specifically, the server sends the received data to the GPT-4 interface and enters a data analysis prompt: "Analyze the following robot operation log, identify errors, and visualize behavioral patterns. Log data: robot_log.txt."

[1852] Step 3:

[1853] System configuration diagram generation

[1854] Based on the analysis results, the server generates a system configuration diagram showing the operational status of the factory robots. The input is the analysis results, and the output is an interactive system configuration diagram. Specifically, the server uses a JavaScript library (e.g., D3.js) to generate the configuration diagram. "Please generate a system configuration diagram for the factory robots based on the following analysis results. Analysis data: Analysis results.json"

[1855] Step 4:

[1856] Visualization

[1857] The terminal interactively displays the generated system configuration diagram, allowing the operator to visually check detailed information about each robot. The input is the generated configuration diagram, and the output is visual information displayed on the operator's terminal. Specifically, the terminal displays the configuration diagram in a web browser, and the user can click to check detailed information.

[1858] Step 5:

[1859] Monitoring

[1860] The server monitors the operational status of factory robots in real time and sends an alert to the operator if an abnormality is detected. The input is real-time log data, and the output is an alert that an abnormality has been detected. Specifically, the server monitors the log data using Elasticsearch and Kibana, and if an abnormality is detected, it notifies the operator via Slack or email.

[1861] Step 6:

[1862] emotion recognition

[1863] The server uses an emotion recognition engine (e.g., Microsoft Azure Face API) to analyze data acquired from the camera and microphone to understand the operator's emotional state. The input is real-time data from the camera and microphone, and the output is an evaluation of the operator's emotional state. Specifically, the server sends real-time data to the emotion recognition engine and inputs a prompt such as "Please analyze the operator's emotional state."

[1864] Step 7:

[1865] User Interface Adjustments

[1866] The server dynamically adjusts the user interface based on the analysis results obtained from the emotion recognition engine. The input is the emotion analysis results, and the output is an adjusted user interface displayed on the terminal. Specifically, the server uses JavaScript and React.js to change the interface and adjust the displayed information appropriately according to the operator's stress level.

[1867] 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.

[1868] 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.

[1869] 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.

[1870] 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.

[1871] 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.

[1872] 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.

[1873] 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).

[1874] 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.

[1875] 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."

[1876] 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.

[1877] 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).

[1878] 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.

[1879] 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.

[1880] 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.

[1881] 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.

[1882] 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.

[1883] 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.

[1884] 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.

[1885] 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.

[1886] 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.

[1887] 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.

[1888] The following is further disclosed regarding the above embodiment.

[1889] Understood. I have prepared the draft claims below.

[1890] (Claim 1)

[1891] means for receiving the uploaded data;

[1892] means for analyzing the received data using a generative AI model;

[1893] means for generating a system configuration diagram based on the analysis results;

[1894] A means for visualizing the generated system configuration diagram;

[1895] A system that includes a means for monitoring the operational status of the system.

[1896] (Claim 2)

[1897] 2. The system of claim 1, wherein the uploaded data is a code file, a log file, a specification, or a manual.

[1898] (Claim 3)

[1899] 2. The system of claim 1, wherein the uploaded data is received by a user terminal.

[1900] (Claim 4)

[1901] 10. The system of claim 1, further comprising means for extracting structure and dependencies within the code using a generative AI model.

[1902] (Claim 5)

[1903] 2. The system according to claim 1, further comprising means for interactively displaying the generated system configuration diagram.

[1904] (Claim 6)

[1905] 2. The system according to claim 1, further comprising means for monitoring the operational status of the system in real time.

[1906] (Claim 7)

[1907] 10. The system of claim 1, further comprising means for detecting and notifying abnormalities to maintain system suitability.

[1908] (Claim 8)

[1909] 10. The system of claim 1, further comprising means for providing detailed information of anomaly detection in real time.

[1910] (Claim 9)

[1911] 2. The system according to claim 1, further comprising means for indicating dependencies and communication paths between components based on the analysis results.

[1912] (Claim 10)

[1913] 2. The system according to claim 1, further comprising means for grasping the structure of the system and the positional relationship of each part based on the generated system configuration diagram.

[1914] "Example 1"

[1915] (Claim 1)

[1916] means for receiving the uploaded data;

[1917] means for analyzing the received data using a generative AI model;

[1918] means for generating a system configuration diagram based on the analysis results;

[1919] A means for visualizing the generated system configuration diagram;

[1920] a means for monitoring the operation of the system;

[1921] means for selecting the uploaded data after being authenticated by the user;

[1922] means for interactively displaying details of the configuration diagram to a user;

[1923] A system that includes a means for notifying the user when an abnormality is detected.

[1924] (Claim 2)

[1925] 2. The system of claim 1, wherein the uploaded data is source code, a log file, a specification, or a manual.

[1926] (Claim 3)

[1927] 2. The system of claim 1, wherein the uploaded data is received by a user terminal.

[1928] "Application Example 1"

[1929] (Claim 1)

[1930] means for receiving the uploaded data;

[1931] means for analyzing the received data using a generative AI model;

[1932] means for generating a system configuration diagram based on the analysis results;

[1933] A means for visualizing the generated system configuration diagram;

[1934] A system that includes a means to monitor the system's operational status and notify if an abnormality is detected.

[1935] (Claim 2)

[1936] 2. The system of claim 1, wherein the uploaded data is a software file, operational history data, specification document, or procedure summary.

[1937] (Claim 3)

[1938] 2. The system of claim 1, wherein the uploaded data is received by a mobile information terminal.

[1939] "Example 2: Combining Emotion Engines"

[1940] (Claim 1)

[1941] means for receiving the uploaded data;

[1942] means for analyzing the received data using a generative AI model;

[1943] means for generating a system configuration diagram based on the analysis results;

[1944] A means for visualizing the generated system configuration diagram;

[1945] a means for monitoring the operation of the system;

[1946] means for recognizing a user's emotion;

[1947] A system including means for adjusting a user interface based on a user's emotion.

[1948] (Claim 2)

[1949] 2. The system of claim 1, wherein the uploaded data is a code file, a log file, a specification, or a manual.

[1950] (Claim 3)

[1951] 2. The system of claim 1, wherein the uploaded data is received by a user terminal.

[1952] "Application example 2 when combining emotion engines"

[1953] (Claim 1)

[1954] means for receiving the uploaded data;

[1955] means for analyzing the received data using a generative AI model;

[1956] means for generating a system configuration diagram based on the analysis results;

[1957] A means for visualizing the generated system configuration diagram;

[1958] a means for monitoring the operation of the system;

[1959] means for recognizing a user's emotion;

[1960] A system including means for adjusting a user interface based on a recognized emotion.

[1961] (Claim 2)

[1962] 2. The system of claim 1, wherein the uploaded data is a code file, a log file, a specification, or a manual.

[1963] (Claim 3)

[1964] 2. The system of claim 1, wherein the uploaded data is received by a user terminal. [Explanation of symbols]

[1965] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for receiving the uploaded data; means for analyzing the received data using a generative AI model; means for generating a system configuration diagram based on the analysis results; A means for visualizing the generated system configuration diagram; A system that includes a means for monitoring the operational status of the system.

2. 2. The system of claim 1, wherein the uploaded data is a code file, a log file, a specification, or a manual.

3. 10. The system of claim 1, wherein the recipient of the uploaded data is a user terminal.

4. 10. The system of claim 1, further comprising means for extracting structure and dependencies within the code using a generative AI model.

5. 2. The system according to claim 1, further comprising means for interactively displaying the generated system configuration diagram.

6. 2. The system according to claim 1, further comprising means for monitoring the operational status of the system in real time.

7. 10. The system of claim 1, further comprising means for detecting and reporting anomalies to maintain system suitability.

8. 10. The system of claim 1, further comprising means for providing detailed information on anomaly detection in real time.

9. 2. The system according to claim 1, further comprising means for indicating dependencies and communication paths between components based on the analysis results.

10. 2. The system according to claim 1, further comprising means for grasping the structure of the system and the positional relationship of each part based on the generated system configuration diagram.

Images