System

Abstract

A system is provided.SOLUTION: A system comprising: means for analyzing and learning materials including server configuration information; means for collecting real-time data; means for detecting a failure based on the collected data; means for identifying a cause of the failure and generating an optimal recovery method; means for notifying a user of the generated recovery method; means for receiving a user's approval; and means for executing the approved recovery method.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In conventional server operations, responding to a failure required a lot of manual work and time. Furthermore, identifying the cause of the failure and selecting an appropriate recovery method required advanced expertise, making it difficult to respond quickly and accurately. As a result, there was a risk of prolonged system downtime and a decline in service reliability. The purpose of this invention is to solve these problems and automate a fast and accurate response to server failures. [Means for solving the problem]

[0005] This invention is a system that includes a means for analyzing and learning from documents containing server configuration information, a means for collecting real-time data, a means for detecting failures based on the collected data, a means for identifying the cause of the failure and generating an optimal recovery method, a means for notifying the user of the generated recovery method, a means for accepting the user's approval, and a means for executing the approved recovery method. Before the server begins operation, the AI ​​learns from the server configuration diagram and design documents to understand the system configuration and the role of each component. During operation, the server collects data in real time, the AI ​​detects anomalies, identifies the cause of the failure, generates an optimal recovery method, and notifies the user. The user confirms and approves the proposed recovery method, and the server automatically executes the recovery method, quickly resolving the failure. This invention can improve the efficiency of server operation and the reliability of services.

[0006] "Materials containing server configuration information" refers to all documents that contain information about the physical and logical configuration of a server, such as server wiring diagrams, design documents, and configuration files.

[0007] "Means for analyzing and learning" refers to a mechanism that automatically reads and understands server configuration information, stores the configuration information in a database, and allows an AI model to learn that information.

[0008] "Real-time data" refers to the most up-to-date data that shows the current operation status of the server, including log files and resource metrics (CPU usage, memory usage, network traffic, etc.).

[0009] "Means for detecting faults based on data" refers to AI algorithms and processing procedures for analyzing collected real-time data and detecting abnormalities.

[0010] "Means to identify the cause of the failure and generate the optimal recovery method" refers to AI or algorithms that quickly analyze the cause of the detected failure and automatically select and generate the optimal recovery method based on that analysis.

[0011] "Means for notifying users of recovery methods" refers to a notification system for informing users of the generated recovery methods, which sends an alert via the terminal and displays the suggested content.

[0012] The "means for receiving user approval" refers to an interface that allows the user to check the proposed recovery method and input instructions for approval or rejection.

[0013] "Means for executing approved recovery methods" refers to the server's ability to automatically execute specified recovery procedures upon user approval, including restarting services, changing configuration, and redistributing resources. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The present invention is a system that analyzes and learns from materials including server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval.

[0036] System Overview

[0037] Learning server configuration information

[0038] Before a server begins operation, users upload server configuration diagrams, design documents, and other documents to the server using a terminal. The server analyzes these documents, stores the server configuration information in a database, and trains an AI model. This process allows the server to understand its own structure and the role of each component.

[0039] Fault Monitoring and Detection

[0040] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.) The server's built-in AI applies anomaly detection algorithms to this data to detect failures in real time.

[0041] Identifying the cause of the problem and presenting recovery methods

[0042] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. Next, the AI ​​generates the optimal recovery method based on learned data and past failure cases. The server notifies the user of this recovery method via their device.

[0043] Confirm and approve the recovery method

[0044] The user checks the recovery method presented on the terminal. The recovery method includes specific procedures and risk assessments. If the user is satisfied with the recovery method, they click the approval button to send instructions to the server.

[0045] Implementing an automatic recovery process

[0046] With user approval, the server automatically executes recovery procedures, which can include restarting the overloaded process, changing configuration settings, or redistributing resources. The server again logs the results of the recovery and notifies the user.

[0047] Specific examples

[0048] For example, consider a situation where a server's CPU usage suddenly increases and the service becomes unresponsive. In this situation, the server detects the anomaly and, by analyzing logs and resource metrics, discovers that a specific process is using excessive resources.

[0049] Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. This proposal is notified to the user via their device. The user checks the proposal and clicks the approval button. Upon approval, the server restarts the high-load process, and CPU usage returns to normal range.

[0050] The above is the overall flow of the automated operation process realized by the system of the present invention. This system makes it possible to improve the efficiency of server operation and the reliability of services.

[0051] The processing flow will be explained below.

[0052] Step 1: Upload the server configuration information

[0053] The terminal sends the server configuration diagram and design documents to the server through a dedicated upload interface.

[0054] Step 2: Analyze and learn server configuration information

[0055] The server analyzes the uploaded data, stores the server configuration information in a database, and trains an AI model to understand the server's structure and the role of each component.

[0056] Step 3: Collect real-time data

[0057] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.).

[0058] Step 4: Detecting failures

[0059] The AI ​​in the server applies an anomaly detection algorithm to the collected data and determines whether there are any abnormalities in real time.

[0060] Step 5: Identify the cause of the problem

[0061] When a failure is detected, the server performs further analysis of log files and resource metrics to identify the specific cause of the failure.

[0062] Step 6: Generate recovery methods

[0063] The AI ​​in the server generates the optimal recovery method based on the learned data and past failure cases. The generated recovery method includes specific steps and necessary commands.

[0064] Step 7: Notification of restoration proposal

[0065] The server notifies the user of the generated recovery method by sending an alert to the terminal and displaying the proposed method.

[0066] Step 8: Check the recovery method

[0067] The user can then view the recovery proposal from the server via their device, which includes specific recovery procedures, an estimate of the time required, and an assessment of the risks.

[0068] Step 9: Send approval

[0069] After the user confirms that there are no problems with the proposed recovery method, he or she clicks the approval button on the terminal and sends instructions to the server.

[0070] Step 10: Perform recovery procedures

[0071] The server receives approval from the user and automatically executes the proposed recovery steps, which may include restarting services, changing configuration, or redistributing resources.

[0072] Step 11: Logging the recovery results and resuming monitoring

[0073] The server logs the recovery steps it took and their results, collects new data, and re-monitors the system status to see if the problem has been resolved.

[0074] Step 12: Notification of results

[0075] The server will notify the user of the final recovery result and inform them that recovery is complete.

[0076] Example 1

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

[0078] Modern server operations require the ability to grasp server configuration information and monitor failures in real time, but there is a lack of methods for managing these efficiently and recovering quickly and accurately. In particular, identifying the cause of complex failures and creating optimal recovery methods requires advanced technology, placing a heavy burden on users. For this reason, improving the efficiency and reliability of server operations has become a challenge.

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

[0080] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting failures based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying the user of the generated recovery method, means for receiving user approval, means for executing the approved recovery method, means for analyzing log files and resource metrics to identify the cause of the failure, means for training an AI model to learn the server configuration information, means for using an anomaly detection algorithm, and means for including specific procedures and risk assessments in the recovery method, thereby enabling the efficiency and reliability of server operation to be improved.

[0081] "Server configuration information" is information that indicates details such as the layout, settings, and linkage relationships of the server's hardware and software.

[0082] "Documents" refers to documents and data files that contain server configuration information, such as server configuration diagrams and design documents.

[0083] "Real-time data" refers to data that is continuously collected and processed immediately while the server is running, including resource metrics such as CPU usage, memory usage, and network traffic.

[0084] "Failure" refers to a condition that prevents the normal operation of a server or an event that causes the provision of service to cease.

[0085] "Recovery method" refers to the procedures and actions taken to resolve the detected failure and restore normal operation of the server.

[0086] "User" refers to the person or organization that operates and manages the server.

[0087] An "AI model" is an algorithm or system that uses data to learn and has the ability to help detect faults and generate recovery methods.

[0088] A "log file" refers to a file that records the server's operation history, error messages, etc.

[0089] "Resource metrics" is data that indicates the usage of server resources, such as CPU usage, memory usage, and network traffic.

[0090] "Approval" refers to the action of the user agreeing to the presented recovery method and allowing it to be carried out.

[0091] An "anomaly detection algorithm" is a method for analyzing collected data and detecting abnormal behavior or conditions.

[0092] "Risk assessment" refers to the process of assessing the potential risks involved in executing a recovery method and presenting them to the user.

[0093] This invention is a system that analyzes and learns from materials including server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval. Specific embodiments of this system are described below.

[0094] Learning server configuration information

[0095] Before the server begins operation, the user uses a terminal to upload documents such as server configuration diagrams and design documents to the server. The server automatically analyzes these documents and obtains server configuration information. The analyzed information is stored in a database and fed to an AI model for learning. This learning allows the server to understand its own structure and the role of each component.

[0096] Fault Monitoring and Detection

[0097] During operation, the server periodically collects log files and resource metrics (e.g., CPU usage, memory usage, network traffic, etc.). The collected data is analyzed in real time by the server's built-in AI using anomaly detection algorithms. This process allows the server to quickly detect failures.

[0098] Identifying the cause of the problem and presenting recovery methods

[0099] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. The AI ​​model then generates an optimal recovery plan based on the learned data and past failure cases. This recovery plan includes specific steps and risk assessments, and the server notifies the user via the terminal.

[0100] Confirm and approve the recovery method

[0101] The user checks the recovery method presented on the terminal, confirms the procedures and risk assessment displayed on the screen, and if there are no problems, clicks the approval button to send the instructions to the server.

[0102] Implementing an automatic recovery process

[0103] The server receives approval from the user and automatically executes recovery procedures, which may include restarting high-load processes, changing configurations, redistributing resources, etc. Once recovery is complete, the server logs the results and notifies the user again.

[0104] Specific examples

[0105] For example, consider a situation where a server's CPU usage suddenly rises and the service stops responding. In this situation, the server detects the anomaly and, after analyzing logs and resource metrics, discovers that a specific process is using excessive resources. Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. This proposal is notified to the user via their terminal. The user confirms the proposal and clicks the approval button. With approval, the server restarts the high-load process, and CPU usage returns to the normal range.

[0106] Prompt Sentence Examples

[0107] By inputting prompts like the following into the generative AI model, you can get detailed information about the system and its specific processing:

[0108] What resource metrics does the server collect while it is running?

[0109]

[0110] What are the specific steps to train AI to learn server configuration information?

[0111]

[0112] What risk assessment factors should users consider when approving a recovery method?

[0113] The above is a specific embodiment of the system of the present invention, which aims to improve the efficiency and reliability of server operation.

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1: Collect and analyze server configuration information

[0116] Users use their devices to upload documents such as server configuration diagrams and design documents to the server. The server receives the uploaded documents as input and analyzes them. During this analysis process, text information from the documents is extracted and components and settings are identified. The server configuration information obtained as a result of the analysis is stored in a database. This information is used for subsequent AI model training.

[0117] Step 2: Learn the server configuration information

[0118] The server supplies the server configuration information obtained in step 1 as input to the AI ​​model for learning. During this learning process, data calculations are performed to understand the relationships between the server's components and the role of each component. As a result of learning, the AI ​​model gains a deeper understanding of the server configuration and improves its ability to generate appropriate countermeasures in the event of a failure.

[0119] Step 3: Collect real-time data

[0120] During operation, the server periodically collects log files and resource metrics (e.g., CPU usage, memory usage, network traffic, etc.). This data is continuously input by the server's internal monitoring system. The collected data is stored as the basis for real-time analysis.

[0121] Step 4: Applying anomaly detection algorithms

[0122] The server takes the real-time data collected in step 3 as input and applies an anomaly detection algorithm. This algorithm performs data analysis and statistical processing to identify deviations from normal operating patterns. If an anomaly is detected, the information is flagged as a fault.

[0123] Step 5: Identify the cause of the problem

[0124] When a failure is detected, the server analyzes log files and resource metrics in detail and uses that data as input to identify the cause of the failure. Specifically, it performs a comparative analysis by comparing the log data immediately before the anomaly was detected with past failure cases. This analysis identifies the cause of the failure, such as a process using excessive resources or a configuration error.

[0125] Step 6: Generate optimal recovery method

[0126] The server uses the AI ​​model to input the identified cause of the failure and generate the optimal recovery method. In this process, a recovery method including optimal procedures and risk assessment is proposed by referencing past failure data and learned data. The generated recovery method is notified to the user as a proposal.

[0127] Step 7: Notification of recovery method

[0128] The server notifies the user of the recovery method generated in step 6 via the terminal. The user confirms the information presented on the terminal. This notification includes specific recovery procedures and a risk assessment.

[0129] Step 8: Review and approve the recovery method

[0130] The user checks the proposed recovery method on the terminal, and if they find it satisfactory, they click the approval button to send the instruction to the server. After receiving the user's approval as input, the server proceeds to the next recovery procedure.

[0131] Step 9: Implementing the Automated Recovery Process

[0132] The server receives user approval as input and automatically executes recovery procedures, which may include restarting high-load processes, changing configurations, redistributing resources, etc. Once recovery is complete, the server again logs the results and notifies the user.

[0133] (Application example 1)

[0134] 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."

[0135] Sensor and computer system failures can occur in autonomous vehicles. Such failures directly affect the safety and reliability of the vehicle, so a rapid and accurate response is required. However, with current technology, failure detection and recovery are often performed manually, which is inefficient. It is also difficult to identify the cause of the failure and propose the optimal recovery method.

[0136] 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.

[0137] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting failures based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying a user of the generated recovery method, means for receiving user approval, means for executing the approved recovery method, means for collecting vehicle sensor data and resource metrics, and means for detecting anomalies in the autonomous vehicle and proposing a recovery method. This enables efficient and reliable failure response, such as quickly detecting system failures in the autonomous vehicle and automatically generating and executing an optimal recovery method.

[0138] "Server configuration information" refers to information that indicates the server's role, connection relationships, placement, etc., and refers to materials included in server configuration diagrams and design documents.

[0139] "Real-time data" refers to log files and resource metrics (CPU usage, memory usage, network traffic, etc.) generated during system operation.

[0140] "Failure" refers to an abnormality or malfunction that occurs in a server or autonomous vehicle system, including an event that interferes with normal operation.

[0141] "Cause of failure" refers to the specific factor or problem that caused the detected failure.

[0142] "Recovery method" refers to the procedures and measures to resolve a detected failure and restore normal system operation.

[0143] "User" refers to the person or computer program that manages, monitors, or operates the server or autonomous vehicle system.

[0144] "Sensor data" refers to information collected from sensors installed in autonomous vehicles, including location information, speed, surrounding conditions, etc.

[0145] "Resource metrics" are indicators that show the resource usage status of a system, and include CPU usage, memory usage, network traffic, etc.

[0146] "Abnormality" refers to any deviation from normal operating conditions or unexpected occurrence, including any malfunction that may adversely affect system performance or operation.

[0147] This invention is a system that analyzes and learns server configuration information, collects real-time data to detect faults, identifies the cause of the fault, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval. This system is particularly useful for improving the safety and reliability of autonomous vehicles. Specific embodiments of this system are described below.

[0148] This system has a means of analyzing and learning from server configuration information. The server uses a terminal to upload documents such as server configuration diagrams and design documents. The server analyzes these documents, stores the server configuration information in a database, and trains a generative AI model. This process allows the server to understand its own structure and the role of each component.

[0149] Next, it has a means of collecting real-time data. The server periodically collects log files and resource metrics (e.g., CPU usage, memory usage, network traffic, etc.) during operation. The server's built-in anomaly detection algorithm analyzes this data and detects failures in real time.

[0150] When a failure is detected, the server identifies the cause and generates the optimal recovery method. The server analyzes detailed log files and resource metrics, and derives appropriate countermeasures based on past failure cases and learned data. The server then notifies the user of the generated recovery method.

[0151] The user checks the recovery method presented on the terminal. The recovery method includes specific steps and risk assessment. If the user determines that there are no problems with the recovery method, they click the approval button to send instructions to the server.

[0152] The server automatically executes recovery procedures after receiving approval from the user, for example, restarting the heavily loaded process, changing the configuration, or redistributing resources. The server again logs the recovery results and notifies the user.

[0153] This system can also be applied to the monitoring and recovery of autonomous vehicles. It collects data from sensors and computer systems installed in autonomous vehicles, detects faults based on anomaly detection algorithms, and generates and proposes optimal recovery methods. Users (in this case, the operation manager or system administrator) can approve and execute recovery operations.

[0154] Specific examples

[0155] For example, consider a situation where the CPU usage of an autonomous vehicle suddenly increases. In this situation, the server detects the anomaly and, after analyzing logs and resource metrics, discovers that a specific high-load process is the cause. Based on this information, the server's AI model proposes the optimal recovery method and notifies the user of the details via their device. If the user confirms the proposal and clicks the approval button, the server will restart the high-load process, and CPU usage will return to the normal range.

[0156] Prompt Sentence Examples

[0157] "In a self-driving car system, detect an anomaly when CPU usage suddenly increases, and propose the optimal recovery method. After the user approves the proposal, implement a system in Python that automatically executes the recovery method."

[0158] As described above, by implementing the present invention, it becomes possible to quickly detect system failures in autonomous vehicles and automatically generate and execute optimal recovery methods, thereby enabling advanced failure response.

[0159] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0160] Step 1:

[0161] The server analyzes and learns from uploaded documents (server configuration diagrams and design documents) to understand its own structure and the role of each component.

[0162] Input: Server configuration diagram and design document (configuration information document)

[0163] Output: Analyzed server configuration information, trained generative AI model

[0164] Specific operation: The server reads the configuration diagrams and design documents, stores the structural information in a database, and trains the generative AI model.

[0165] Step 2:

[0166] The server collects log files and resource metrics (such as CPU usage, memory usage, and network traffic) in real time, allowing you to monitor the current state of the system.

[0167] Input: System log files, resource metrics (real-time data)

[0168] Output: Collected data

[0169] Specific operation: The server periodically collects data from sensors and system logs and stores it in a designated database.

[0170] Step 3:

[0171] The server applies an anomaly detection algorithm based on the collected real-time data to detect faults.

[0172] Input: Collected data (system log files, resource metrics)

[0173] Output: Fault detection result (abnormal occurrence status)

[0174] Specific operation: The server runs an anomaly detection algorithm, analyzes patterns in the data, and detects anomalies.

[0175] Step 4:

[0176] The server identifies the cause of the detected failure and generates the optimal recovery method based on past cases and learned data.

[0177] Input: fault detection results, log files, resource metrics, past fault cases

[0178] Output: Generated recovery methods

[0179] How it works: The server performs detailed analysis of the data and uses a generative AI model to suggest the optimal recovery method.

[0180] Step 5:

[0181] The server notifies the user of the generated recovery method, and the user can check the details of the recovery method using the terminal.

[0182] Input: Generated recovery method

[0183] Output: Recovery method notified to the user

[0184] Specific operation: The server notifies the user via the terminal of details of how to recover.

[0185] Step 6:

[0186] The user checks the presented recovery method and clicks the approval button to send approval to the server.

[0187] Input: User confirmation and approval

[0188] Output: Approved recovery methods

[0189] Specific operation: The user checks the proposal on the device and clicks the approval button to send instructions to the server.

[0190] Step 7:

[0191] The server automatically executes recovery procedures approved by the user.

[0192] Input: Approved recovery method

[0193] Output: Recovery steps taken, normalized system state

[0194] Specific Action: The server executes authorized recovery procedures to restore system performance.

[0195] 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.

[0196] This invention combines an emotion engine with a system that analyzes and learns from materials including server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of that recovery method, and executes the recovery method after receiving the user's approval. The emotion engine has the function of recognizing the user's emotions and adjusting the notification content and recovery process accordingly.

[0197] System Overview

[0198] Learning server configuration information

[0199] Before a server begins operation, users upload server configuration diagrams, design documents, and other documents to the server using a terminal. The server analyzes these documents, stores the server configuration information in a database, and trains an AI model. This process allows the server to understand its own structure and the role of each component.

[0200] Fault Monitoring and Detection

[0201] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.) The server's built-in AI applies anomaly detection algorithms to this data to detect failures in real time.

[0202] Identifying the cause of the failure and generating a recovery method

[0203] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. Next, the AI ​​generates the optimal recovery method based on learned data and past failure cases. The server notifies the user of this recovery method via their device.

[0204] Adjusting notification content with an emotion engine

[0205] The emotion engine analyzes the user's facial expressions, voice tone, and other biometric signals to recognize the user's emotions. The server uses the emotion engine to adjust the notification content based on the user's emotions. For example, if the user is feeling stressed, the server can make the notification content clearer and more concise.

[0206] Confirm and approve the recovery method

[0207] The user confirms the recovery method presented on the device, which includes specific steps and risk assessments. The emotion engine also works during this process, utilizing the user's emotional data to assist in reducing the psychological burden. If the user is satisfied with the recovery method, they click the approve button to send instructions to the server.

[0208] Implementing an automatic recovery process

[0209] With user approval, the server automatically executes recovery procedures, which can include restarting the overloaded process, changing configuration settings, or redistributing resources. The server again logs the results of the recovery and notifies the user.

[0210] Specific examples

[0211] For example, consider a situation where a server's CPU usage suddenly increases and the service becomes unresponsive. In this situation, the server detects the anomaly and, by analyzing logs and resource metrics, discovers that a specific process is using excessive resources.

[0212] Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. The server then uses an emotion engine to analyze the user's emotions, and if signs of stress are detected, the server notifies the user of the proposal in a more understandable and concise manner. The user checks the proposal, agrees, and clicks the approval button. Upon receiving approval, the server restarts the high-load process, and CPU usage returns to normal.

[0213] This system not only improves the efficiency of server operations and the reliability of services, but also reduces the psychological burden on users. In this way, incorporating emotional engineering will enable more advanced server operation management.

[0214] The processing flow will be explained below.

[0215] Step 1: Upload the server configuration information

[0216] The terminal sends the server configuration diagram and design documents to the server through a dedicated upload interface.

[0217] Step 2: Analyze and learn server configuration information

[0218] The server analyzes the uploaded data, stores the server configuration information in a database, and trains an AI model to understand the server's structure and the role of each component.

[0219] Step 3: Collect real-time data

[0220] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.).

[0221] Step 4: Detecting failures

[0222] The AI ​​in the server applies an anomaly detection algorithm to the collected data and determines whether there are any abnormalities in real time.

[0223] Step 5: Identify the cause of the problem

[0224] When a failure is detected, the server performs further analysis of log files and resource metrics to identify the specific cause of the failure.

[0225] Step 6: Generate recovery methods

[0226] The AI ​​in the server generates the optimal recovery method based on the learned data and past failure cases. The generated recovery method includes specific steps and necessary commands.

[0227] Step 7: Notification of restoration proposal

[0228] The server notifies the user of the generated recovery method by sending an alert to the terminal and displaying the proposed method.

[0229] Step 8: Adjusting notification content with the emotion engine

[0230] The server runs an emotion engine that analyzes the user's facial expressions, voice tone, and other biometric signals to recognize the user's emotions. If the user is feeling stressed, the notification content will be adjusted to be more clear and concise.

[0231] Step 9: Check the recovery method

[0232] The user can then view the recovery proposal from the server via their device, which includes specific recovery procedures, an estimate of the time required, and an assessment of the risks.

[0233] Step 10: Assisting the user with an emotion engine

[0234] The server's emotion engine assists users in understanding the suggestions, for example by adding reassuring explanations and support messages if the user is feeling anxious.

[0235] Step 11: Send Approval

[0236] After the user confirms that there are no problems with the proposed recovery method, he or she clicks the approval button on the terminal and sends instructions to the server.

[0237] Step 12: Perform recovery procedures

[0238] The server receives approval from the user and automatically executes the proposed recovery steps, which may include restarting services, changing configuration, or redistributing resources.

[0239] Step 13: Logging the recovery results and resuming monitoring

[0240] The server logs the recovery steps it took and their results, collects new data, and re-monitors the system status to see if the problem has been resolved.

[0241] Step 14: Notification of results

[0242] The server notifies the user of the final recovery result, letting them know that recovery is complete, and uses an emotion engine to provide reassuring feedback to the user.

[0243] Example 2

[0244] 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."

[0245] In modern information systems, server operation and management is a complex and advanced task. When a failure occurs, it is extremely difficult to quickly identify the cause and take appropriate action, placing significant stress on users. Furthermore, traditional systems often provide notifications and instructions without considering the user's emotional state, making it difficult for users to understand and respond to the information. This can lead to issues such as reduced service reliability and operational efficiency.

[0246] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0247] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting failures based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying the user of the generated recovery method, means for analyzing the user's emotions, means for adjusting the notification content according to the user's emotions, means for accepting the user's approval, and means for executing the approved recovery method. This improves the efficiency of server operation management and service reliability, reduces the psychological burden on users, and enables quick and appropriate failure response.

[0248] "Server configuration information" is information that indicates the physical and logical layout of the server, the network configuration, and the role and design principles of each component.

[0249] "Real-time data" refers to data that is updated regularly, such as log files, CPU usage, memory usage, and network traffic, that the server collects to understand its current status.

[0250] A "failure" is an abnormal behavior or error that occurs during server operation, which disrupts the normal functioning of the system.

[0251] A "recovery method" refers to specific procedures and measures to resolve the cause of a failure when it occurs and to restore the server to normal operating status.

[0252] The "emotion engine" is a system that analyzes a user's facial expressions, voice tone, and biometric signals to recognize their emotional state.

[0253] "Adjusting notification content" is the process of changing the format and content of the information or instructions provided depending on the user's emotional state.

[0254] "Approval" is the act of the user agreeing with the proposed recovery method and allowing its execution.

[0255] An "automatic recovery process" is a series of specific actions based on a recovery method that are automatically executed by the server after receiving user approval.

[0256] This invention is a system that analyzes and learns from server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval. Furthermore, by combining it with an emotion engine, it has the function of adjusting the notification content and recovery process according to the user's emotional state.

[0257] Learning server configuration information

[0258] Before the server begins operation, documents such as server configuration diagrams and design documents are uploaded to the server using a terminal. The server analyzes these documents using natural language processing (NLP) technology and stores the server configuration information in a database. For example, the analysis uses SpaCy as an NLP library and TENSORFLOW (registered trademark) or PyTorch as an AI model. This allows the server to understand its own structure and the role of each component.

[0259] Fault Monitoring and Detection

[0260] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.). The AI ​​in the server applies anomaly detection algorithms such as Isolation Forest and LSTM (Long Short-Term Memory) to analyze the collected data in real time to detect anomalies. For example, it can be configured to issue an alert if CPU usage exceeds 80%.

[0261] Identifying the cause of the failure and generating a recovery method

[0262] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. Based on the analysis results, the AI ​​refers to learned data and past failure cases to generate the optimal recovery method. The generated recovery method includes specific steps and risk assessments. This information is notified to the user via their device.

[0263] Adjusting notification content with an emotion engine

[0264] The emotion engine recognizes the user's emotions by analyzing their facial expressions (collected by a webcam), voice tone (collected by a microphone), and other biometric signals (such as heart rate and galvanic skin response). The server uses the emotion engine to tailor the notification content based on the user's emotions. For example, if the user is feeling stressed, the server can respond by making the notification content more understandable and concise. Examples of prompts input to the generative AI model include: "Please give a short, clear explanation of the suggestion to restart a high-load process."

[0265] Confirm and approve the recovery method

[0266] The user confirms the recovery method presented on the device, which includes specific steps and risk assessments. The emotion engine also works during this process, utilizing the user's emotional data to assist in reducing the psychological burden. If the user is satisfied with the recovery method, they click the approve button to send instructions to the server.

[0267] Implementing an automatic recovery process

[0268] With user approval, the server automatically executes recovery procedures, such as restarting high-load processes, changing configurations, reallocating resources, etc. The server logs the results of these operations and notifies the user.

[0269] As a concrete example, consider a case where a server's CPU usage suddenly rises and the service becomes unresponsive. In this situation, the server detects the anomaly and, after analyzing logs and resource metrics, discovers that a specific process is using excessive resources. Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. The server then uses an emotion engine to analyze the user's emotions, and if signs of stress are detected, the server notifies the user of the proposal in a more understandable and concise manner. The user confirms the proposal, agrees, and clicks the approval button. With approval, the server restarts the high-load process, and CPU usage returns to normal range.

[0270] This system not only improves the efficiency of server operations and the reliability of services, but also reduces the psychological burden on users. In this way, incorporating emotional engineering will enable more advanced server operation management.

[0271] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0272] Step 1:

[0273] The user uploads server configuration information using a terminal. The user sends documents such as server configuration diagrams and design documents to the server via the terminal. The server configuration diagram and design document files are provided as input, and these documents are uploaded to the server as output.

[0274] Specific behavior:

[0275] The user selects the file "server_diagram.pdf" from the folder and clicks the upload button displayed on the terminal. The server receives the file and prepares it for analysis.

[0276] Step 2:

[0277] The server analyzes the uploaded materials. The server uses natural language processing (NLP) technology to analyze the files to extract server configuration information. The input is the server configuration diagram or design document to be analyzed, and the analysis results are stored in a database as output.

[0278] Specific behavior:

[0279] The server uses an NLP library (e.g., SpaCy) to analyze the uploaded "server_diagram.pdf" and extract the network structure and the role of each component. The extracted information is stored in a database.

[0280] Step 3:

[0281] The server uses the configuration information stored in the database to train the AI ​​model. Data is input into the AI ​​model (e.g., TensorFlow or PyTorch), and the server understands its own structure and the role of each component. The server configuration information is provided as input, and a trained model is obtained as output.

[0282] Specific behavior:

[0283] The server provides the configuration information saved in the previous step to the AI ​​model and starts the learning process. Once learning is complete, the server saves the model and prepares it for future fault detection.

[0284] Step 4:

[0285] The server periodically collects real-time data. During operation, the server collects log files and resource metrics such as CPU usage, memory usage, and network traffic. Various resource data is provided as input, and a periodically updated collection of data is obtained as output.

[0286] Specific behavior:

[0287] The server records CPU usage every five minutes and collects memory usage and network traffic data, which is then stored in a log file.

[0288] Step 5:

[0289] The server applies an anomaly detection algorithm to detect faults. The AI ​​in the server uses an anomaly detection algorithm such as Isolation Forest or LSTM on the collected real-time data. The real-time data is provided as input, and the anomaly detection results are obtained as output.

[0290] Specific behavior:

[0291] The server periodically analyzes the collected data and issues an alert if CPU usage exceeds 80%. Data patterns that are deemed abnormal are recorded.

[0292] Step 6:

[0293] The server identifies the cause of the failure and generates the optimal recovery method. The server performs detailed analysis of the detected anomaly to identify the cause of the failure. Next, it uses an AI model to generate the optimal recovery method. The failure detection results and past failure case data are provided as input, and the recovery method is generated as output.

[0294] Specific behavior:

[0295] The server analyzes the log files and extracts events before and after the abnormality occurred. AI proposes the optimal recovery method based on past data and automatically generates the procedure.

[0296] Step 7:

[0297] The generated recovery method is notified to the user. The server notifies the user of the proposed recovery method through the terminal. The generated recovery method is provided as input, and a notification displayed to the user is obtained as output.

[0298] Specific behavior:

[0299] The server sends the provided recovery method to the user's terminal and displays a message saying "The high-load process will be restarted."

[0300] Step 8:

[0301] The server analyzes the user's emotions using an emotion engine. The user's facial expressions, voice tone, and biometric signals are collected and analyzed by the emotion engine. Data from the webcam, microphone, and biometric sensors are provided as input, and the user's emotional state is obtained as output.

[0302] Specific behavior:

[0303] The user sits in front of the camera, and the server collects facial expressions and tone of voice. The emotion engine analyzes these and determines whether the user is feeling stressed.

[0304] Step 9:

[0305] The server adjusts the notification content according to the user's emotions. Based on the collected emotional data, the server adjusts the notification content appropriately. The user's emotional state is provided as input, and the adjusted notification content is obtained as output.

[0306] Specific behavior:

[0307] If the user is stressed, the server will try to make the notification message as clear and concise as possible. For example, it will send a simple message such as "Please restart the high-load process."

[0308] Step 10:

[0309] The user checks and approves the recovery method presented on the terminal. The user checks the recovery method via the terminal and clicks the approve button. The details of the recovery method are provided as input, and the click of the "Approve" button is obtained as output.

[0310] Specific behavior:

[0311] The user checks the recovery procedure displayed on the screen and, if there are no problems, clicks the "Approve" button.

[0312] Step 11:

[0313] The server automatically executes recovery procedures after receiving approval from the user. Based on the approved recovery method, the server automatically initiates a response. The user's approval is provided as input, and the executed recovery operation is obtained as output.

[0314] Specific behavior:

[0315] The server will automatically take action such as restarting high-load processes, changing settings, and reallocating resources.

[0316] Step 12:

[0317] The server logs the recovery results and notifies the user. The server logs the recovery results and notifies the user of successful recovery. The input is the result of the performed recovery operation, and the output is the logged data and a notification.

[0318] Specific behavior:

[0319] The server logs the results of the recovery operation and sends a message to the user saying, "The high-load process was successfully restarted. CPU usage has returned to normal."

[0320] (Application example 2)

[0321] 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."

[0322] In conventional systems, when a server or robot failure occurs, there are limited ways to respond quickly and appropriately, which places a significant psychological burden on on-site maintenance staff. Furthermore, it is difficult to collect and notify real-time data on-site, which often means that staff are unable to respond immediately. Therefore, there is a need for more efficient fault response and a reduction in the psychological burden on staff.

[0323] 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.

[0324] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting a failure based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying a user of the generated recovery method, means for receiving user approval, means for executing the approved recovery method, means for recognizing the user's emotions using an emotion engine and adjusting the notification content, and means for displaying real-time data using smart glasses and monitoring the user's emotions. This enables a quick and appropriate response when a failure occurs and reduces the psychological burden on maintenance staff.

[0325] "Server configuration information" is information that describes the structure of the server, the layout of each component, and the settings.

[0326] "Documents" refers to all documents necessary for server operation, such as server configuration diagrams and design documents.

[0327] "Real-time data" refers to data collected at any time while a server or robot is operating, and includes CPU usage, memory usage, network traffic, etc.

[0328] "Failure" refers to an abnormal situation that prevents a server or robot from operating normally.

[0329] "Cause of failure" refers to the direct cause or factor of the failure that occurred.

[0330] "Recovery methods" are procedures and measures for resolving a failure and restoring the system to normal operating condition.

[0331] An "emotion engine" refers to technology that recognizes emotions by analyzing a user's facial expressions, voice tone, biometric signals, etc.

[0332] "Smart glasses" are a wearable eyeglass-type device equipped with technologies such as augmented reality, and are used to display and collect information.

[0333] "User emotion" refers to the emotional state that a user feels when responding to a problem.

[0334] "Adjusting notification content" is the process of changing the content and format of a notification message based on the user's emotions recognized by the emotion engine.

[0335] To specifically implement this invention, the following system configuration and processes are required: The roles of the server, terminal, and user are clarified, and technical details are described.

[0336] Cloud server and real-time data collection

[0337] The server is deployed on the cloud and learns by analyzing documents such as server configuration diagrams and design documents. After uploading these documents, the server analyzes them using an AI model and stores the server configuration information in a database. This process primarily uses the Python programming language and the TensorFlow library.

[0338] During operation, the server collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.) in real time, using ElasticSearch (registered trademark) as a log management system and Apache Kafka (registered trademark) for real-time processing.

[0339] Implementing fault detection and recovery processes

[0340] The server detects anomalies based on the collected data. Specifically, it uses the PyCaret anomaly detection algorithm to detect failures in real time. When an anomaly is detected, the server performs a detailed analysis of log files and resource metrics and identifies the cause of the failure using a generative AI model. It then generates and proposes the optimal recovery method.

[0341] At this time, the server notifies the user of the generated recovery method. This notification is displayed in real time on the device, such as smart glasses, so the user can confirm and approve it. For example, you can use 'React Native' to build an application for smart glasses that displays the necessary information.

[0342] Smart glasses and emotion engine operation

[0343] The smart glasses are equipped with an emotion engine that recognizes the user's emotions by analyzing their facial expressions, voice tone, and biometric signals. This uses libraries such as OpenCV and Dlib, and adjusts the notification content according to the user's emotions. For example, if the user is feeling stressed, the notification message will be changed to a simpler and more understandable one.

[0344] Specific examples

[0345] As a concrete example of setting the subject to the server, consider a case where a maintenance staff member at a factory is wearing smart glasses when the motor of a robot in the factory starts making an abnormal noise. The server collects data on the robot in real time and detects the abnormality. In this case, the server analyzes the abnormal sound data and identifies that the problem is with a specific motor part. The server then generates an appropriate recovery method (e.g., restarting the motor) and uses an emotion engine to display a notification on the smart glasses based on the user's emotional state. Once the user confirms and approves the recovery method, the server immediately executes the procedure and returns the motor to normal.

[0346] Prompt Sentence Examples

[0347] An example of a prompt when a failure occurs could be the following text:

[0348] Based on server log data and resource metrics, the following anomalies were detected:

[0349] CPU usage is 85%.

[0350] Memory usage is 78%.

[0351] Network traffic is 50%.

[0352] Use this information to identify the cause of the anomaly and suggest the best way to recover.

[0353] Please include specific steps and risk assessments in your proposal.

[0354] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0355] Step 1:

[0356] The server uploads documents such as server configuration diagrams and design documents, analyzes them, and learns. The server configuration information (documents) is used as input, and the server configuration information is saved in a database as an analysis result, which is then trained by the AI ​​model. This makes it possible to understand the server configuration and the role of each component.

[0357] Step 2:

[0358] During operation, the server collects real-time data such as log files and resource metrics (CPU usage, memory usage, network traffic, etc.) using Elasticsearch and Apache Kafka. The input is operational data from servers and robots, which is stored as time-series data.

[0359] Step 3:

[0360] The server applies an anomaly detection algorithm to the collected real-time data to detect faults. This process uses the "PyCaret" anomaly detection algorithm. The input is real-time data, and the output is a check for the presence or absence of an abnormality and generates notification information if an abnormality is detected.

[0361] Step 4:

[0362] The server uses a generative AI model to identify the cause of the detected anomaly and generate an optimal recovery method. The input is the log file and resource metrics when the anomaly is detected, and the output is the identified cause of the failure and a proposed recovery method.

[0363] Step 5:

[0364] The server sends the generated recovery method to a device such as smart glasses to notify the user. An emotion engine is running and adjusts the notification content according to the user's emotional state. The input is the generated recovery method and the user's emotion analysis data, and the output is an appropriate notification message for the user.

[0365] Step 6:

[0366] The user checks the notification content using the smart glasses and approves the recovery method. The input is the recovery method displayed on the smart glasses, and the output is the user's approval action (clicking the approval button).

[0367] Step 7:

[0368] The server executes recovery procedures upon receiving approval from the user. The input is the approval data from the user, and the output is the recovery procedures to be executed (for example, restarting a high-load process or redistributing resources). This process restores normal operation of the server or robot, and the recovery results are recorded in the log again.

[0369] Step 8:

[0370] The server again logs the recovery result and notifies the user. The input is the result data of the recovery process, and the output is the log of the result and a final notification to the user.

[0371] 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.

[0372] 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.

[0373] 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.

[0374] [Second embodiment]

[0375] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0376] 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.

[0377] 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).

[0378] 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.

[0379] 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.

[0380] 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).

[0381] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] 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.

[0386] 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."

[0387] The present invention is a system that analyzes and learns from materials including server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval.

[0388] System Overview

[0389] Learning server configuration information

[0390] Before a server begins operation, users upload server configuration diagrams, design documents, and other documents to the server using a terminal. The server analyzes these documents, stores the server configuration information in a database, and trains an AI model. This process allows the server to understand its own structure and the role of each component.

[0391] Fault Monitoring and Detection

[0392] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.) The server's built-in AI applies anomaly detection algorithms to this data to detect failures in real time.

[0393] Identifying the cause of the problem and presenting recovery methods

[0394] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. Next, the AI ​​generates the optimal recovery method based on learned data and past failure cases. The server notifies the user of this recovery method via their device.

[0395] Confirm and approve the recovery method

[0396] The user checks the recovery method presented on the terminal. The recovery method includes specific procedures and risk assessments. If the user is satisfied with the recovery method, they click the approval button to send instructions to the server.

[0397] Implementing an automatic recovery process

[0398] With user approval, the server automatically executes recovery procedures, which can include restarting the overloaded process, changing configuration settings, or redistributing resources. The server again logs the results of the recovery and notifies the user.

[0399] Specific examples

[0400] For example, consider a situation where a server's CPU usage suddenly increases and the service becomes unresponsive. In this situation, the server detects the anomaly and, by analyzing logs and resource metrics, discovers that a specific process is using excessive resources.

[0401] Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. This proposal is notified to the user via their device. The user checks the proposal and clicks the approval button. Upon approval, the server restarts the high-load process, and CPU usage returns to normal range.

[0402] The above is the overall flow of the automated operation process realized by the system of the present invention. This system makes it possible to improve the efficiency of server operation and the reliability of services.

[0403] The processing flow will be explained below.

[0404] Step 1: Upload the server configuration information

[0405] The terminal sends the server configuration diagram and design documents to the server through a dedicated upload interface.

[0406] Step 2: Analyze and learn server configuration information

[0407] The server analyzes the uploaded data, stores the server configuration information in a database, and trains an AI model to understand the server's structure and the role of each component.

[0408] Step 3: Collect real-time data

[0409] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.).

[0410] Step 4: Detecting failures

[0411] The AI ​​in the server applies an anomaly detection algorithm to the collected data and determines whether there are any abnormalities in real time.

[0412] Step 5: Identify the cause of the problem

[0413] When a failure is detected, the server performs further analysis of log files and resource metrics to identify the specific cause of the failure.

[0414] Step 6: Generate recovery methods

[0415] The AI ​​in the server generates the optimal recovery method based on the learned data and past failure cases. The generated recovery method includes specific steps and necessary commands.

[0416] Step 7: Notification of restoration proposal

[0417] The server notifies the user of the generated recovery method by sending an alert to the terminal and displaying the proposed method.

[0418] Step 8: Check the recovery method

[0419] The user can then view the recovery proposal from the server via their device, which includes specific recovery procedures, an estimate of the time required, and an assessment of the risks.

[0420] Step 9: Send approval

[0421] After the user confirms that there are no problems with the proposed recovery method, he or she clicks the approval button on the terminal and sends instructions to the server.

[0422] Step 10: Perform recovery procedures

[0423] The server receives approval from the user and automatically executes the proposed recovery steps, which may include restarting services, changing configuration, or redistributing resources.

[0424] Step 11: Logging the recovery results and resuming monitoring

[0425] The server logs the recovery steps it took and their results, collects new data, and re-monitors the system status to see if the problem has been resolved.

[0426] Step 12: Notification of results

[0427] The server will notify the user of the final recovery result and inform them that recovery is complete.

[0428] Example 1

[0429] 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."

[0430] Modern server operations require the ability to grasp server configuration information and monitor failures in real time, but there is a lack of methods for managing these efficiently and recovering quickly and accurately. In particular, identifying the cause of complex failures and creating optimal recovery methods requires advanced technology, placing a heavy burden on users. For this reason, improving the efficiency and reliability of server operations has become a challenge.

[0431] 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.

[0432] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting failures based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying the user of the generated recovery method, means for receiving user approval, means for executing the approved recovery method, means for analyzing log files and resource metrics to identify the cause of the failure, means for training an AI model to learn the server configuration information, means for using an anomaly detection algorithm, and means for including specific procedures and risk assessments in the recovery method, thereby enabling the efficiency and reliability of server operation to be improved.

[0433] "Server configuration information" is information that indicates details such as the layout, settings, and linkage relationships of the server's hardware and software.

[0434] "Documents" refers to documents and data files that contain server configuration information, such as server configuration diagrams and design documents.

[0435] "Real-time data" refers to data that is continuously collected and processed immediately while the server is running, including resource metrics such as CPU usage, memory usage, and network traffic.

[0436] "Failure" refers to a condition that prevents the normal operation of a server or an event that causes the provision of service to cease.

[0437] "Recovery method" refers to the procedures and actions taken to resolve the detected failure and restore normal operation of the server.

[0438] "User" refers to the person or organization that operates and manages the server.

[0439] An "AI model" is an algorithm or system that uses data to learn and has the ability to help detect faults and generate recovery methods.

[0440] A "log file" refers to a file that records the server's operation history, error messages, etc.

[0441] "Resource metrics" is data that indicates the usage of server resources, such as CPU usage, memory usage, and network traffic.

[0442] "Approval" refers to the action of the user agreeing to the presented recovery method and allowing it to be carried out.

[0443] An "anomaly detection algorithm" is a method for analyzing collected data and detecting abnormal behavior or conditions.

[0444] "Risk assessment" refers to the process of assessing the potential risks involved in executing a recovery method and presenting them to the user.

[0445] This invention is a system that analyzes and learns from materials including server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval. Specific embodiments of this system are described below.

[0446] Learning server configuration information

[0447] Before the server begins operation, the user uses a terminal to upload documents such as server configuration diagrams and design documents to the server. The server automatically analyzes these documents and obtains server configuration information. The analyzed information is stored in a database and fed to an AI model for learning. This learning allows the server to understand its own structure and the role of each component.

[0448] Fault Monitoring and Detection

[0449] During operation, the server periodically collects log files and resource metrics (e.g., CPU usage, memory usage, network traffic, etc.). The collected data is analyzed in real time by the server's built-in AI using anomaly detection algorithms. This process allows the server to quickly detect failures.

[0450] Identifying the cause of the problem and presenting recovery methods

[0451] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. The AI ​​model then generates an optimal recovery plan based on the learned data and past failure cases. This recovery plan includes specific steps and risk assessments, and the server notifies the user via the terminal.

[0452] Confirm and approve the recovery method

[0453] The user checks the recovery method presented on the terminal, confirms the procedures and risk assessment displayed on the screen, and if there are no problems, clicks the approval button to send the instructions to the server.

[0454] Implementing an automatic recovery process

[0455] The server receives approval from the user and automatically executes recovery procedures, which may include restarting high-load processes, changing configurations, redistributing resources, etc. Once recovery is complete, the server logs the results and notifies the user again.

[0456] Specific examples

[0457] For example, consider a situation where a server's CPU usage suddenly rises and the service stops responding. In this situation, the server detects the anomaly and, after analyzing logs and resource metrics, discovers that a specific process is using excessive resources. Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. This proposal is notified to the user via their terminal. The user confirms the proposal and clicks the approval button. With approval, the server restarts the high-load process, and CPU usage returns to the normal range.

[0458] Prompt Sentence Examples

[0459] By inputting prompts like the following into the generative AI model, you can get detailed information about the system and its specific processing:

[0460] What resource metrics does the server collect while it is running?

[0461]

[0462] What are the specific steps to train AI to learn server configuration information?

[0463]

[0464] What risk assessment factors should users consider when approving a recovery method?

[0465] The above is a specific embodiment of the system of the present invention, which aims to improve the efficiency and reliability of server operation.

[0466] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0467] Step 1: Collect and analyze server configuration information

[0468] Users use their devices to upload documents such as server configuration diagrams and design documents to the server. The server receives the uploaded documents as input and analyzes them. During this analysis process, text information from the documents is extracted and components and settings are identified. The server configuration information obtained as a result of the analysis is stored in a database. This information is used for subsequent AI model training.

[0469] Step 2: Learn the server configuration information

[0470] The server supplies the server configuration information obtained in step 1 as input to the AI ​​model for learning. During this learning process, data calculations are performed to understand the relationships between the server's components and the role of each component. As a result of learning, the AI ​​model gains a deeper understanding of the server configuration and improves its ability to generate appropriate countermeasures in the event of a failure.

[0471] Step 3: Collect real-time data

[0472] During operation, the server periodically collects log files and resource metrics (e.g., CPU usage, memory usage, network traffic, etc.). This data is continuously input by the server's internal monitoring system. The collected data is stored as the basis for real-time analysis.

[0473] Step 4: Applying anomaly detection algorithms

[0474] The server takes the real-time data collected in step 3 as input and applies an anomaly detection algorithm. This algorithm performs data analysis and statistical processing to identify deviations from normal operating patterns. If an anomaly is detected, the information is flagged as a fault.

[0475] Step 5: Identify the cause of the problem

[0476] When a failure is detected, the server analyzes log files and resource metrics in detail and uses that data as input to identify the cause of the failure. Specifically, it performs a comparative analysis by comparing the log data immediately before the anomaly was detected with past failure cases. This analysis identifies the cause of the failure, such as a process using excessive resources or a configuration error.

[0477] Step 6: Generate optimal recovery method

[0478] The server uses the AI ​​model to input the identified cause of the failure and generate the optimal recovery method. In this process, a recovery method including optimal procedures and risk assessment is proposed by referencing past failure data and learned data. The generated recovery method is notified to the user as a proposal.

[0479] Step 7: Notification of recovery method

[0480] The server notifies the user of the recovery method generated in step 6 via the terminal. The user confirms the information presented on the terminal. This notification includes specific recovery procedures and a risk assessment.

[0481] Step 8: Review and approve the recovery method

[0482] The user checks the proposed recovery method on the terminal, and if they find it satisfactory, they click the approval button to send the instruction to the server. After receiving the user's approval as input, the server proceeds to the next recovery procedure.

[0483] Step 9: Implementing the Automated Recovery Process

[0484] The server receives user approval as input and automatically executes recovery procedures, which may include restarting high-load processes, changing configurations, redistributing resources, etc. Once recovery is complete, the server again logs the results and notifies the user.

[0485] (Application example 1)

[0486] 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."

[0487] Sensor and computer system failures can occur in autonomous vehicles. Such failures directly affect the safety and reliability of the vehicle, so a rapid and accurate response is required. However, with current technology, failure detection and recovery are often performed manually, which is inefficient. It is also difficult to identify the cause of the failure and propose the optimal recovery method.

[0488] 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.

[0489] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting failures based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying a user of the generated recovery method, means for receiving user approval, means for executing the approved recovery method, means for collecting vehicle sensor data and resource metrics, and means for detecting anomalies in the autonomous vehicle and proposing a recovery method. This enables efficient and reliable failure response, such as quickly detecting system failures in the autonomous vehicle and automatically generating and executing an optimal recovery method.

[0490] "Server configuration information" refers to information that indicates the server's role, connection relationships, placement, etc., and refers to materials included in server configuration diagrams and design documents.

[0491] "Real-time data" refers to log files and resource metrics (CPU usage, memory usage, network traffic, etc.) generated during system operation.

[0492] "Failure" refers to an abnormality or malfunction that occurs in a server or autonomous vehicle system, including an event that interferes with normal operation.

[0493] "Cause of failure" refers to the specific factor or problem that caused the detected failure.

[0494] "Recovery method" refers to the procedures and measures to resolve a detected failure and restore normal system operation.

[0495] "User" refers to the person or computer program that manages, monitors, or operates the server or autonomous vehicle system.

[0496] "Sensor data" refers to information collected from sensors installed in autonomous vehicles, including location information, speed, surrounding conditions, etc.

[0497] "Resource metrics" are indicators that show the resource usage status of a system, and include CPU usage, memory usage, network traffic, etc.

[0498] "Abnormality" refers to any deviation from normal operating conditions or unexpected occurrence, including any malfunction that may adversely affect system performance or operation.

[0499] This invention is a system that analyzes and learns server configuration information, collects real-time data to detect faults, identifies the cause of the fault, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval. This system is particularly useful for improving the safety and reliability of autonomous vehicles. Specific embodiments of this system are described below.

[0500] This system has a means of analyzing and learning from server configuration information. The server uses a terminal to upload documents such as server configuration diagrams and design documents. The server analyzes these documents, stores the server configuration information in a database, and trains a generative AI model. This process allows the server to understand its own structure and the role of each component.

[0501] Next, it has a means of collecting real-time data. The server periodically collects log files and resource metrics (e.g., CPU usage, memory usage, network traffic, etc.) during operation. The server's built-in anomaly detection algorithm analyzes this data and detects failures in real time.

[0502] When a failure is detected, the server identifies the cause and generates the optimal recovery method. The server analyzes detailed log files and resource metrics, and derives appropriate countermeasures based on past failure cases and learned data. The server then notifies the user of the generated recovery method.

[0503] The user checks the recovery method presented on the terminal. The recovery method includes specific steps and risk assessment. If the user determines that there are no problems with the recovery method, they click the approval button to send instructions to the server.

[0504] The server automatically executes recovery procedures after receiving approval from the user, for example, restarting the heavily loaded process, changing the configuration, or redistributing resources. The server again logs the recovery results and notifies the user.

[0505] This system can also be applied to the monitoring and recovery of autonomous vehicles. It collects data from sensors and computer systems installed in autonomous vehicles, detects faults based on anomaly detection algorithms, and generates and proposes optimal recovery methods. Users (in this case, the operation manager or system administrator) can approve and execute recovery operations.

[0506] Specific examples

[0507] For example, consider a situation where the CPU usage of an autonomous vehicle suddenly increases. In this situation, the server detects the anomaly and, after analyzing logs and resource metrics, discovers that a specific high-load process is the cause. Based on this information, the server's AI model proposes the optimal recovery method and notifies the user of the details via their device. If the user confirms the proposal and clicks the approval button, the server will restart the high-load process, and CPU usage will return to the normal range.

[0508] Prompt Sentence Examples

[0509] "In a self-driving car system, detect an anomaly when CPU usage suddenly increases, and propose the optimal recovery method. After the user approves the proposal, implement a system in Python that automatically executes the recovery method."

[0510] As described above, by implementing the present invention, it becomes possible to quickly detect system failures in autonomous vehicles and automatically generate and execute optimal recovery methods, thereby enabling advanced failure response.

[0511] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0512] Step 1:

[0513] The server analyzes and learns from uploaded documents (server configuration diagrams and design documents) to understand its own structure and the role of each component.

[0514] Input: Server configuration diagram and design document (configuration information document)

[0515] Output: Analyzed server configuration information, trained generative AI model

[0516] Specific operation: The server reads the configuration diagrams and design documents, stores the structural information in a database, and trains the generative AI model.

[0517] Step 2:

[0518] The server collects log files and resource metrics (such as CPU usage, memory usage, and network traffic) in real time, allowing you to monitor the current state of the system.

[0519] Input: System log files, resource metrics (real-time data)

[0520] Output: Collected data

[0521] Specific operation: The server periodically collects data from sensors and system logs and stores it in a designated database.

[0522] Step 3:

[0523] The server applies an anomaly detection algorithm based on the collected real-time data to detect faults.

[0524] Input: Collected data (system log files, resource metrics)

[0525] Output: Fault detection result (abnormal occurrence status)

[0526] Specific operation: The server runs an anomaly detection algorithm, analyzes patterns in the data, and detects anomalies.

[0527] Step 4:

[0528] The server identifies the cause of the detected failure and generates the optimal recovery method based on past cases and learned data.

[0529] Input: fault detection results, log files, resource metrics, past fault cases

[0530] Output: Generated recovery methods

[0531] How it works: The server performs detailed analysis of the data and uses a generative AI model to suggest the optimal recovery method.

[0532] Step 5:

[0533] The server notifies the user of the generated recovery method, and the user can check the details of the recovery method using the terminal.

[0534] Input: Generated recovery method

[0535] Output: Recovery method notified to the user

[0536] Specific operation: The server notifies the user via the terminal of details of how to recover.

[0537] Step 6:

[0538] The user checks the presented recovery method and clicks the approval button to send approval to the server.

[0539] Input: User confirmation and approval

[0540] Output: Approved recovery methods

[0541] Specific operation: The user checks the proposal on the device and clicks the approval button to send instructions to the server.

[0542] Step 7:

[0543] The server automatically executes recovery procedures approved by the user.

[0544] Input: Approved recovery method

[0545] Output: Recovery steps taken, normalized system state

[0546] Specific Action: The server executes authorized recovery procedures to restore system performance.

[0547] 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.

[0548] This invention combines an emotion engine with a system that analyzes and learns from materials including server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of that recovery method, and executes the recovery method after receiving the user's approval. The emotion engine has the function of recognizing the user's emotions and adjusting the notification content and recovery process accordingly.

[0549] System Overview

[0550] Learning server configuration information

[0551] Before a server begins operation, users upload server configuration diagrams, design documents, and other documents to the server using a terminal. The server analyzes these documents, stores the server configuration information in a database, and trains an AI model. This process allows the server to understand its own structure and the role of each component.

[0552] Fault Monitoring and Detection

[0553] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.) The server's built-in AI applies anomaly detection algorithms to this data to detect failures in real time.

[0554] Identifying the cause of the failure and generating a recovery method

[0555] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. Next, the AI ​​generates the optimal recovery method based on learned data and past failure cases. The server notifies the user of this recovery method via their device.

[0556] Adjusting notification content with an emotion engine

[0557] The emotion engine analyzes the user's facial expressions, voice tone, and other biometric signals to recognize the user's emotions. The server uses the emotion engine to adjust the notification content based on the user's emotions. For example, if the user is feeling stressed, the server can make the notification content clearer and more concise.

[0558] Confirm and approve the recovery method

[0559] The user confirms the recovery method presented on the device, which includes specific steps and risk assessments. The emotion engine also works during this process, utilizing the user's emotional data to assist in reducing the psychological burden. If the user is satisfied with the recovery method, they click the approve button to send instructions to the server.

[0560] Implementing an automatic recovery process

[0561] With user approval, the server automatically executes recovery procedures, which can include restarting the overloaded process, changing configuration settings, or redistributing resources. The server again logs the results of the recovery and notifies the user.

[0562] Specific examples

[0563] For example, consider a situation where a server's CPU usage suddenly increases and the service becomes unresponsive. In this situation, the server detects the anomaly and, by analyzing logs and resource metrics, discovers that a specific process is using excessive resources.

[0564] Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. The server then uses an emotion engine to analyze the user's emotions, and if signs of stress are detected, the server notifies the user of the proposal in a more understandable and concise manner. The user checks the proposal, agrees, and clicks the approval button. Upon receiving approval, the server restarts the high-load process, and CPU usage returns to normal.

[0565] This system not only improves the efficiency of server operations and the reliability of services, but also reduces the psychological burden on users. In this way, incorporating emotional engineering will enable more advanced server operation management.

[0566] The processing flow will be explained below.

[0567] Step 1: Upload the server configuration information

[0568] The terminal sends the server configuration diagram and design documents to the server through a dedicated upload interface.

[0569] Step 2: Analyze and learn server configuration information

[0570] The server analyzes the uploaded data, stores the server configuration information in a database, and trains an AI model to understand the server's structure and the role of each component.

[0571] Step 3: Collect real-time data

[0572] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.).

[0573] Step 4: Detecting failures

[0574] The AI ​​in the server applies an anomaly detection algorithm to the collected data and determines whether there are any abnormalities in real time.

[0575] Step 5: Identify the cause of the problem

[0576] When a failure is detected, the server performs further analysis of log files and resource metrics to identify the specific cause of the failure.

[0577] Step 6: Generate recovery methods

[0578] The AI ​​in the server generates the optimal recovery method based on the learned data and past failure cases. The generated recovery method includes specific steps and necessary commands.

[0579] Step 7: Notification of restoration proposal

[0580] The server notifies the user of the generated recovery method by sending an alert to the terminal and displaying the proposed method.

[0581] Step 8: Adjusting notification content with the emotion engine

[0582] The server runs an emotion engine that analyzes the user's facial expressions, voice tone, and other biometric signals to recognize the user's emotions. If the user is feeling stressed, the notification content will be adjusted to be more clear and concise.

[0583] Step 9: Check the recovery method

[0584] The user can then view the recovery proposal from the server via their device, which includes specific recovery procedures, an estimate of the time required, and an assessment of the risks.

[0585] Step 10: Assisting the user with an emotion engine

[0586] The server's emotion engine assists users in understanding the suggestions, for example by adding reassuring explanations and support messages if the user is feeling anxious.

[0587] Step 11: Send Approval

[0588] After the user confirms that there are no problems with the proposed recovery method, he or she clicks the approval button on the terminal and sends instructions to the server.

[0589] Step 12: Perform recovery procedures

[0590] The server receives approval from the user and automatically executes the proposed recovery steps, which may include restarting services, changing configuration, or redistributing resources.

[0591] Step 13: Logging the recovery results and resuming monitoring

[0592] The server logs the recovery steps it took and their results, collects new data, and re-monitors the system status to see if the problem has been resolved.

[0593] Step 14: Notification of results

[0594] The server notifies the user of the final recovery result, letting them know that recovery is complete, and uses an emotion engine to provide reassuring feedback to the user.

[0595] Example 2

[0596] 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."

[0597] In modern information systems, server operation and management is a complex and advanced task. When a failure occurs, it is extremely difficult to quickly identify the cause and take appropriate action, placing significant stress on users. Furthermore, traditional systems often provide notifications and instructions without considering the user's emotional state, making it difficult for users to understand and respond to the information. This can lead to issues such as reduced service reliability and operational efficiency.

[0598] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0599] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting failures based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying the user of the generated recovery method, means for analyzing the user's emotions, means for adjusting the notification content according to the user's emotions, means for accepting the user's approval, and means for executing the approved recovery method. This improves the efficiency of server operation management and service reliability, reduces the psychological burden on users, and enables quick and appropriate failure response.

[0600] "Server configuration information" is information that indicates the physical and logical layout of the server, the network configuration, and the role and design principles of each component.

[0601] "Real-time data" refers to data that is updated regularly, such as log files, CPU usage, memory usage, and network traffic, that the server collects to understand its current status.

[0602] A "failure" is an abnormal behavior or error that occurs during server operation, which disrupts the normal functioning of the system.

[0603] A "recovery method" refers to specific procedures and measures to resolve the cause of a failure when it occurs and to restore the server to normal operating status.

[0604] The "emotion engine" is a system that analyzes a user's facial expressions, voice tone, and biometric signals to recognize their emotional state.

[0605] "Adjusting notification content" is the process of changing the format and content of the information or instructions provided depending on the user's emotional state.

[0606] "Approval" is the act of the user agreeing with the proposed recovery method and allowing its execution.

[0607] An "automatic recovery process" is a series of specific actions based on a recovery method that are automatically executed by the server after receiving user approval.

[0608] This invention is a system that analyzes and learns from server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval. Furthermore, by combining it with an emotion engine, it has the function of adjusting the notification content and recovery process according to the user's emotional state.

[0609] Learning server configuration information

[0610] Before the server begins operation, documents such as server configuration diagrams and design documents are uploaded to the server using a terminal. The server analyzes these documents using natural language processing (NLP) technology and stores the server configuration information in a database. For example, the analysis uses SpaCy as an NLP library and TensorFlow or PyTorch as an AI model. This allows the server to understand its own structure and the role of each component.

[0611] Fault Monitoring and Detection

[0612] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.). The AI ​​in the server applies anomaly detection algorithms such as Isolation Forest and LSTM (Long Short-Term Memory) to analyze the collected data in real time to detect anomalies. For example, it can be configured to issue an alert if CPU usage exceeds 80%.

[0613] Identifying the cause of the failure and generating a recovery method

[0614] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. Based on the analysis results, the AI ​​refers to learned data and past failure cases to generate the optimal recovery method. The generated recovery method includes specific steps and risk assessments. This information is notified to the user via their device.

[0615] Adjusting notification content with an emotion engine

[0616] The emotion engine recognizes the user's emotions by analyzing their facial expressions (collected by a webcam), voice tone (collected by a microphone), and other biometric signals (such as heart rate and galvanic skin response). The server uses the emotion engine to tailor the notification content based on the user's emotions. For example, if the user is feeling stressed, the server can respond by making the notification content more understandable and concise. Examples of prompts input to the generative AI model include: "Please give a short, clear explanation of the suggestion to restart a high-load process."

[0617] Confirm and approve the recovery method

[0618] The user confirms the recovery method presented on the device, which includes specific steps and risk assessments. The emotion engine also works during this process, utilizing the user's emotional data to assist in reducing the psychological burden. If the user is satisfied with the recovery method, they click the approve button to send instructions to the server.

[0619] Implementing an automatic recovery process

[0620] With user approval, the server automatically executes recovery procedures, such as restarting high-load processes, changing configurations, reallocating resources, etc. The server logs the results of these operations and notifies the user.

[0621] As a concrete example, consider a case where a server's CPU usage suddenly rises and the service becomes unresponsive. In this situation, the server detects the anomaly and, after analyzing logs and resource metrics, discovers that a specific process is using excessive resources. Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. The server then uses an emotion engine to analyze the user's emotions, and if signs of stress are detected, the server notifies the user of the proposal in a more understandable and concise manner. The user confirms the proposal, agrees, and clicks the approval button. With approval, the server restarts the high-load process, and CPU usage returns to normal range.

[0622] This system not only improves the efficiency of server operations and the reliability of services, but also reduces the psychological burden on users. In this way, incorporating emotional engineering will enable more advanced server operation management.

[0623] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0624] Step 1:

[0625] The user uploads server configuration information using a terminal. The user sends documents such as server configuration diagrams and design documents to the server via the terminal. The server configuration diagram and design document files are provided as input, and these documents are uploaded to the server as output.

[0626] Specific behavior:

[0627] The user selects the file "server_diagram.pdf" from the folder and clicks the upload button displayed on the terminal. The server receives the file and prepares it for analysis.

[0628] Step 2:

[0629] The server analyzes the uploaded materials. The server uses natural language processing (NLP) technology to analyze the files to extract server configuration information. The input is the server configuration diagram or design document to be analyzed, and the analysis results are stored in a database as output.

[0630] Specific behavior:

[0631] The server uses an NLP library (e.g., SpaCy) to analyze the uploaded "server_diagram.pdf" and extract the network structure and the role of each component. The extracted information is stored in a database.

[0632] Step 3:

[0633] The server uses the configuration information stored in the database to train the AI ​​model. Data is input into the AI ​​model (e.g., TensorFlow or PyTorch), and the server understands its own structure and the role of each component. The server configuration information is provided as input, and a trained model is obtained as output.

[0634] Specific behavior:

[0635] The server provides the configuration information saved in the previous step to the AI ​​model and starts the learning process. Once learning is complete, the server saves the model and prepares it for future fault detection.

[0636] Step 4:

[0637] The server periodically collects real-time data. During operation, the server collects log files and resource metrics such as CPU usage, memory usage, and network traffic. Various resource data is provided as input, and a periodically updated collection of data is obtained as output.

[0638] Specific behavior:

[0639] The server records CPU usage every five minutes and collects memory usage and network traffic data, which is then stored in a log file.

[0640] Step 5:

[0641] The server applies an anomaly detection algorithm to detect faults. The AI ​​in the server uses an anomaly detection algorithm such as Isolation Forest or LSTM on the collected real-time data. The real-time data is provided as input, and the anomaly detection results are obtained as output.

[0642] Specific behavior:

[0643] The server periodically analyzes the collected data and issues an alert if CPU usage exceeds 80%. Data patterns that are deemed abnormal are recorded.

[0644] Step 6:

[0645] The server identifies the cause of the failure and generates the optimal recovery method. The server performs detailed analysis of the detected anomaly to identify the cause of the failure. Next, it uses an AI model to generate the optimal recovery method. The failure detection results and past failure case data are provided as input, and the recovery method is generated as output.

[0646] Specific behavior:

[0647] The server analyzes the log files and extracts events before and after the abnormality occurred. AI proposes the optimal recovery method based on past data and automatically generates the procedure.

[0648] Step 7:

[0649] The generated recovery method is notified to the user. The server notifies the user of the proposed recovery method through the terminal. The generated recovery method is provided as input, and a notification displayed to the user is obtained as output.

[0650] Specific behavior:

[0651] The server sends the provided recovery method to the user's terminal and displays a message saying "The high-load process will be restarted."

[0652] Step 8:

[0653] The server analyzes the user's emotions using an emotion engine. The user's facial expressions, voice tone, and biometric signals are collected and analyzed by the emotion engine. Data from the webcam, microphone, and biometric sensors are provided as input, and the user's emotional state is obtained as output.

[0654] Specific behavior:

[0655] The user sits in front of the camera, and the server collects facial expressions and tone of voice. The emotion engine analyzes these and determines whether the user is feeling stressed.

[0656] Step 9:

[0657] The server adjusts the notification content according to the user's emotions. Based on the collected emotional data, the server adjusts the notification content appropriately. The user's emotional state is provided as input, and the adjusted notification content is obtained as output.

[0658] Specific behavior:

[0659] If the user is stressed, the server will try to make the notification message as clear and concise as possible. For example, it will send a simple message such as "Please restart the high-load process."

[0660] Step 10:

[0661] The user checks and approves the recovery method presented on the terminal. The user checks the recovery method via the terminal and clicks the approve button. The details of the recovery method are provided as input, and the click of the "Approve" button is obtained as output.

[0662] Specific behavior:

[0663] The user checks the recovery procedure displayed on the screen and, if there are no problems, clicks the "Approve" button.

[0664] Step 11:

[0665] The server automatically executes recovery procedures after receiving approval from the user. Based on the approved recovery method, the server automatically initiates a response. The user's approval is provided as input, and the executed recovery operation is obtained as output.

[0666] Specific behavior:

[0667] The server will automatically take action such as restarting high-load processes, changing settings, and reallocating resources.

[0668] Step 12:

[0669] The server logs the recovery results and notifies the user. The server logs the recovery results and notifies the user of successful recovery. The input is the result of the performed recovery operation, and the output is the logged data and a notification.

[0670] Specific behavior:

[0671] The server logs the results of the recovery operation and sends a message to the user saying, "The high-load process was successfully restarted. CPU usage has returned to normal."

[0672] (Application example 2)

[0673] 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."

[0674] In conventional systems, when a server or robot failure occurs, there are limited ways to respond quickly and appropriately, which places a significant psychological burden on on-site maintenance staff. Furthermore, it is difficult to collect and notify real-time data on-site, which often means that staff are unable to respond immediately. Therefore, there is a need for more efficient fault response and a reduction in the psychological burden on staff.

[0675] 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.

[0676] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting a failure based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying a user of the generated recovery method, means for receiving user approval, means for executing the approved recovery method, means for recognizing the user's emotions using an emotion engine and adjusting the notification content, and means for displaying real-time data using smart glasses and monitoring the user's emotions. This enables a quick and appropriate response when a failure occurs and reduces the psychological burden on maintenance staff.

[0677] "Server configuration information" is information that describes the structure of the server, the layout of each component, and the settings.

[0678] "Documents" refers to all documents necessary for server operation, such as server configuration diagrams and design documents.

[0679] "Real-time data" refers to data collected at any time while a server or robot is operating, and includes CPU usage, memory usage, network traffic, etc.

[0680] "Failure" refers to an abnormal situation that prevents a server or robot from operating normally.

[0681] "Cause of failure" refers to the direct cause or factor of the failure that occurred.

[0682] "Recovery methods" are procedures and measures for resolving a failure and restoring the system to normal operating condition.

[0683] An "emotion engine" refers to technology that recognizes emotions by analyzing a user's facial expressions, voice tone, biometric signals, etc.

[0684] "Smart glasses" are a wearable eyeglass-type device equipped with technologies such as augmented reality, and are used to display and collect information.

[0685] "User emotion" refers to the emotional state that a user feels when responding to a problem.

[0686] "Adjusting notification content" is the process of changing the content and format of a notification message based on the user's emotions recognized by the emotion engine.

[0687] To specifically implement this invention, the following system configuration and processes are required: The roles of the server, terminal, and user are clarified, and technical details are described.

[0688] Cloud server and real-time data collection

[0689] The server is deployed on the cloud and learns by analyzing documents such as server configuration diagrams and design documents. After uploading these documents, the server analyzes them using an AI model and stores the server configuration information in a database. This process primarily uses the Python programming language and the TensorFlow library.

[0690] During operation, the server collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.) in real time, using Elasticsearch as a log management system and Apache Kafka for real-time processing.

[0691] Implementing fault detection and recovery processes

[0692] The server detects anomalies based on the collected data. Specifically, it uses the PyCaret anomaly detection algorithm to detect failures in real time. When an anomaly is detected, the server performs a detailed analysis of log files and resource metrics and identifies the cause of the failure using a generative AI model. It then generates and proposes the optimal recovery method.

[0693] At this time, the server notifies the user of the generated recovery method. This notification is displayed in real time on the device, such as smart glasses, so the user can confirm and approve it. For example, you can use 'React Native' to build an application for smart glasses that displays the necessary information.

[0694] Smart glasses and emotion engine operation

[0695] The smart glasses are equipped with an emotion engine that recognizes the user's emotions by analyzing their facial expressions, voice tone, and biometric signals. This uses libraries such as OpenCV and Dlib, and adjusts the notification content according to the user's emotions. For example, if the user is feeling stressed, the notification message will be changed to a simpler and more understandable one.

[0696] Specific examples

[0697] As a concrete example of setting the subject to the server, consider a case where a maintenance staff member at a factory is wearing smart glasses when the motor of a robot in the factory starts making an abnormal noise. The server collects data on the robot in real time and detects the abnormality. In this case, the server analyzes the abnormal sound data and identifies that the problem is with a specific motor part. The server then generates an appropriate recovery method (e.g., restarting the motor) and uses an emotion engine to display a notification on the smart glasses based on the user's emotional state. Once the user confirms and approves the recovery method, the server immediately executes the procedure and returns the motor to normal.

[0698] Prompt Sentence Examples

[0699] An example of a prompt when a failure occurs could be the following text:

[0700] Based on server log data and resource metrics, the following anomalies were detected:

[0701] CPU usage is 85%.

[0702] Memory usage is 78%.

[0703] Network traffic is 50%.

[0704] Use this information to identify the cause of the anomaly and suggest the best way to recover.

[0705] Please include specific steps and risk assessments in your proposal.

[0706] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0707] Step 1:

[0708] The server uploads documents such as server configuration diagrams and design documents, analyzes them, and learns. The server configuration information (documents) is used as input, and the server configuration information is saved in a database as an analysis result, which is then trained by the AI ​​model. This makes it possible to understand the server configuration and the role of each component.

[0709] Step 2:

[0710] During operation, the server collects real-time data such as log files and resource metrics (CPU usage, memory usage, network traffic, etc.) using Elasticsearch and Apache Kafka. The input is operational data from servers and robots, which is stored as time-series data.

[0711] Step 3:

[0712] The server applies an anomaly detection algorithm to the collected real-time data to detect faults. This process uses the "PyCaret" anomaly detection algorithm. The input is real-time data, and the output is a check for the presence or absence of an abnormality and generates notification information if an abnormality is detected.

[0713] Step 4:

[0714] The server uses a generative AI model to identify the cause of the detected anomaly and generate an optimal recovery method. The input is the log file and resource metrics when the anomaly is detected, and the output is the identified cause of the failure and a proposed recovery method.

[0715] Step 5:

[0716] The server sends the generated recovery method to a device such as smart glasses to notify the user. An emotion engine is running and adjusts the notification content according to the user's emotional state. The input is the generated recovery method and the user's emotion analysis data, and the output is an appropriate notification message for the user.

[0717] Step 6:

[0718] The user checks the notification content using the smart glasses and approves the recovery method. The input is the recovery method displayed on the smart glasses, and the output is the user's approval action (clicking the approval button).

[0719] Step 7:

[0720] The server executes recovery procedures upon receiving approval from the user. The input is the approval data from the user, and the output is the recovery procedures to be executed (for example, restarting a high-load process or redistributing resources). This process restores normal operation of the server or robot, and the recovery results are recorded in the log again.

[0721] Step 8:

[0722] The server again logs the recovery result and notifies the user. The input is the result data of the recovery process, and the output is the log of the result and a final notification to the user.

[0723] 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.

[0724] 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.

[0725] 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.

[0726] [Third embodiment]

[0727] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0728] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0729] 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).

[0730] 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.

[0731] 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.

[0732] 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).

[0733] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0734] 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.

[0735] 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.

[0736] 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.

[0737] 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.

[0738] 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."

[0739] The present invention is a system that analyzes and learns from materials including server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval.

[0740] System Overview

[0741] Learning server configuration information

[0742] Before a server begins operation, users upload server configuration diagrams, design documents, and other documents to the server using a terminal. The server analyzes these documents, stores the server configuration information in a database, and trains an AI model. This process allows the server to understand its own structure and the role of each component.

[0743] Fault Monitoring and Detection

[0744] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.) The server's built-in AI applies anomaly detection algorithms to this data to detect failures in real time.

[0745] Identifying the cause of the problem and presenting recovery methods

[0746] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. Next, the AI ​​generates the optimal recovery method based on learned data and past failure cases. The server notifies the user of this recovery method via their device.

[0747] Confirm and approve the recovery method

[0748] The user checks the recovery method presented on the terminal. The recovery method includes specific procedures and risk assessments. If the user is satisfied with the recovery method, they click the approval button to send instructions to the server.

[0749] Implementing an automatic recovery process

[0750] With user approval, the server automatically executes recovery procedures, which can include restarting the overloaded process, changing configuration settings, or redistributing resources. The server again logs the results of the recovery and notifies the user.

[0751] Specific examples

[0752] For example, consider a situation where a server's CPU usage suddenly increases and the service becomes unresponsive. In this situation, the server detects the anomaly and, by analyzing logs and resource metrics, discovers that a specific process is using excessive resources.

[0753] Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. This proposal is notified to the user via their device. The user checks the proposal and clicks the approval button. Upon approval, the server restarts the high-load process, and CPU usage returns to normal range.

[0754] The above is the overall flow of the automated operation process realized by the system of the present invention. This system makes it possible to improve the efficiency of server operation and the reliability of services.

[0755] The processing flow will be explained below.

[0756] Step 1: Upload the server configuration information

[0757] The terminal sends the server configuration diagram and design documents to the server through a dedicated upload interface.

[0758] Step 2: Analyze and learn server configuration information

[0759] The server analyzes the uploaded data, stores the server configuration information in a database, and trains an AI model to understand the server's structure and the role of each component.

[0760] Step 3: Collect real-time data

[0761] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.).

[0762] Step 4: Detecting failures

[0763] The AI ​​in the server applies an anomaly detection algorithm to the collected data and determines whether there are any abnormalities in real time.

[0764] Step 5: Identify the cause of the problem

[0765] When a failure is detected, the server performs further analysis of log files and resource metrics to identify the specific cause of the failure.

[0766] Step 6: Generate recovery methods

[0767] The AI ​​in the server generates the optimal recovery method based on the learned data and past failure cases. The generated recovery method includes specific steps and necessary commands.

[0768] Step 7: Notification of restoration proposal

[0769] The server notifies the user of the generated recovery method by sending an alert to the terminal and displaying the proposed method.

[0770] Step 8: Check the recovery method

[0771] The user can then view the recovery proposal from the server via their device, which includes specific recovery procedures, an estimate of the time required, and an assessment of the risks.

[0772] Step 9: Send approval

[0773] After the user confirms that there are no problems with the proposed recovery method, he or she clicks the approval button on the terminal and sends instructions to the server.

[0774] Step 10: Perform recovery procedures

[0775] The server receives approval from the user and automatically executes the proposed recovery steps, which may include restarting services, changing configuration, or redistributing resources.

[0776] Step 11: Logging the recovery results and resuming monitoring

[0777] The server logs the recovery steps it took and their results, collects new data, and re-monitors the system status to see if the problem has been resolved.

[0778] Step 12: Notification of results

[0779] The server will notify the user of the final recovery result and inform them that recovery is complete.

[0780] Example 1

[0781] 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."

[0782] Modern server operations require the ability to grasp server configuration information and monitor failures in real time, but there is a lack of methods for managing these efficiently and recovering quickly and accurately. In particular, identifying the cause of complex failures and creating optimal recovery methods requires advanced technology, placing a heavy burden on users. For this reason, improving the efficiency and reliability of server operations has become a challenge.

[0783] 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.

[0784] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting failures based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying the user of the generated recovery method, means for receiving user approval, means for executing the approved recovery method, means for analyzing log files and resource metrics to identify the cause of the failure, means for training an AI model to learn the server configuration information, means for using an anomaly detection algorithm, and means for including specific procedures and risk assessments in the recovery method, thereby enabling the efficiency and reliability of server operation to be improved.

[0785] "Server configuration information" is information that indicates details such as the layout, settings, and linkage relationships of the server's hardware and software.

[0786] "Documents" refers to documents and data files that contain server configuration information, such as server configuration diagrams and design documents.

[0787] "Real-time data" refers to data that is continuously collected and processed immediately while the server is running, including resource metrics such as CPU usage, memory usage, and network traffic.

[0788] "Failure" refers to a condition that prevents the normal operation of a server or an event that causes the provision of service to cease.

[0789] "Recovery method" refers to the procedures and actions taken to resolve the detected failure and restore normal operation of the server.

[0790] "User" refers to the person or organization that operates and manages the server.

[0791] An "AI model" is an algorithm or system that uses data to learn and has the ability to help detect faults and generate recovery methods.

[0792] A "log file" refers to a file that records the server's operation history, error messages, etc.

[0793] "Resource metrics" is data that indicates the usage of server resources, such as CPU usage, memory usage, and network traffic.

[0794] "Approval" refers to the action of the user agreeing to the presented recovery method and allowing it to be carried out.

[0795] An "anomaly detection algorithm" is a method for analyzing collected data and detecting abnormal behavior or conditions.

[0796] "Risk assessment" refers to the process of assessing the potential risks involved in executing a recovery method and presenting them to the user.

[0797] This invention is a system that analyzes and learns from materials including server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval. Specific embodiments of this system are described below.

[0798] Learning server configuration information

[0799] Before the server begins operation, the user uses a terminal to upload documents such as server configuration diagrams and design documents to the server. The server automatically analyzes these documents and obtains server configuration information. The analyzed information is stored in a database and fed to an AI model for learning. This learning allows the server to understand its own structure and the role of each component.

[0800] Fault Monitoring and Detection

[0801] During operation, the server periodically collects log files and resource metrics (e.g., CPU usage, memory usage, network traffic, etc.). The collected data is analyzed in real time by the server's built-in AI using anomaly detection algorithms. This process allows the server to quickly detect failures.

[0802] Identifying the cause of the problem and presenting recovery methods

[0803] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. The AI ​​model then generates an optimal recovery plan based on the learned data and past failure cases. This recovery plan includes specific steps and risk assessments, and the server notifies the user via the terminal.

[0804] Confirm and approve the recovery method

[0805] The user checks the recovery method presented on the terminal, confirms the procedures and risk assessment displayed on the screen, and if there are no problems, clicks the approval button to send the instructions to the server.

[0806] Implementing an automatic recovery process

[0807] The server receives approval from the user and automatically executes recovery procedures, which may include restarting high-load processes, changing configurations, redistributing resources, etc. Once recovery is complete, the server logs the results and notifies the user again.

[0808] Specific examples

[0809] For example, consider a situation where a server's CPU usage suddenly rises and the service stops responding. In this situation, the server detects the anomaly and, after analyzing logs and resource metrics, discovers that a specific process is using excessive resources. Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. This proposal is notified to the user via their terminal. The user confirms the proposal and clicks the approval button. With approval, the server restarts the high-load process, and CPU usage returns to the normal range.

[0810] Prompt Sentence Examples

[0811] By inputting prompts like the following into the generative AI model, you can get detailed information about the system and its specific processing:

[0812] What resource metrics does the server collect while it is running?

[0813]

[0814] What are the specific steps to train AI to learn server configuration information?

[0815]

[0816] What risk assessment factors should users consider when approving a recovery method?

[0817] The above is a specific embodiment of the system of the present invention, which aims to improve the efficiency and reliability of server operation.

[0818] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0819] Step 1: Collect and analyze server configuration information

[0820] Users use their devices to upload documents such as server configuration diagrams and design documents to the server. The server receives the uploaded documents as input and analyzes them. During this analysis process, text information from the documents is extracted and components and settings are identified. The server configuration information obtained as a result of the analysis is stored in a database. This information is used for subsequent AI model training.

[0821] Step 2: Learn the server configuration information

[0822] The server supplies the server configuration information obtained in step 1 as input to the AI ​​model for learning. During this learning process, data calculations are performed to understand the relationships between the server's components and the role of each component. As a result of learning, the AI ​​model gains a deeper understanding of the server configuration and improves its ability to generate appropriate countermeasures in the event of a failure.

[0823] Step 3: Collect real-time data

[0824] During operation, the server periodically collects log files and resource metrics (e.g., CPU usage, memory usage, network traffic, etc.). This data is continuously input by the server's internal monitoring system. The collected data is stored as the basis for real-time analysis.

[0825] Step 4: Applying anomaly detection algorithms

[0826] The server takes the real-time data collected in step 3 as input and applies an anomaly detection algorithm. This algorithm performs data analysis and statistical processing to identify deviations from normal operating patterns. If an anomaly is detected, the information is flagged as a fault.

[0827] Step 5: Identify the cause of the problem

[0828] When a failure is detected, the server analyzes log files and resource metrics in detail and uses that data as input to identify the cause of the failure. Specifically, it performs a comparative analysis by comparing the log data immediately before the anomaly was detected with past failure cases. This analysis identifies the cause of the failure, such as a process using excessive resources or a configuration error.

[0829] Step 6: Generate optimal recovery method

[0830] The server uses the AI ​​model to input the identified cause of the failure and generate the optimal recovery method. In this process, a recovery method including optimal procedures and risk assessment is proposed by referencing past failure data and learned data. The generated recovery method is notified to the user as a proposal.

[0831] Step 7: Notification of recovery method

[0832] The server notifies the user of the recovery method generated in step 6 via the terminal. The user confirms the information presented on the terminal. This notification includes specific recovery procedures and a risk assessment.

[0833] Step 8: Review and approve the recovery method

[0834] The user checks the proposed recovery method on the terminal, and if they find it satisfactory, they click the approval button to send the instruction to the server. After receiving the user's approval as input, the server proceeds to the next recovery procedure.

[0835] Step 9: Implementing the Automated Recovery Process

[0836] The server receives user approval as input and automatically executes recovery procedures, which may include restarting high-load processes, changing configurations, redistributing resources, etc. Once recovery is complete, the server again logs the results and notifies the user.

[0837] (Application example 1)

[0838] 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."

[0839] Sensor and computer system failures can occur in autonomous vehicles. Such failures directly affect the safety and reliability of the vehicle, so a rapid and accurate response is required. However, with current technology, failure detection and recovery are often performed manually, which is inefficient. It is also difficult to identify the cause of the failure and propose the optimal recovery method.

[0840] 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.

[0841] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting failures based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying a user of the generated recovery method, means for receiving user approval, means for executing the approved recovery method, means for collecting vehicle sensor data and resource metrics, and means for detecting anomalies in the autonomous vehicle and proposing a recovery method. This enables efficient and reliable failure response, such as quickly detecting system failures in the autonomous vehicle and automatically generating and executing an optimal recovery method.

[0842] "Server configuration information" refers to information that indicates the server's role, connection relationships, placement, etc., and refers to materials included in server configuration diagrams and design documents.

[0843] "Real-time data" refers to log files and resource metrics (CPU usage, memory usage, network traffic, etc.) generated during system operation.

[0844] "Failure" refers to an abnormality or malfunction that occurs in a server or autonomous vehicle system, including an event that interferes with normal operation.

[0845] "Cause of failure" refers to the specific factor or problem that caused the detected failure.

[0846] "Recovery method" refers to the procedures and measures to resolve a detected failure and restore normal system operation.

[0847] "User" refers to the person or computer program that manages, monitors, or operates the server or autonomous vehicle system.

[0848] "Sensor data" refers to information collected from sensors installed in autonomous vehicles, including location information, speed, surrounding conditions, etc.

[0849] "Resource metrics" are indicators that show the resource usage status of a system, and include CPU usage, memory usage, network traffic, etc.

[0850] "Abnormality" refers to any deviation from normal operating conditions or unexpected occurrence, including any malfunction that may adversely affect system performance or operation.

[0851] This invention is a system that analyzes and learns server configuration information, collects real-time data to detect faults, identifies the cause of the fault, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval. This system is particularly useful for improving the safety and reliability of autonomous vehicles. Specific embodiments of this system are described below.

[0852] This system has a means of analyzing and learning from server configuration information. The server uses a terminal to upload documents such as server configuration diagrams and design documents. The server analyzes these documents, stores the server configuration information in a database, and trains a generative AI model. This process allows the server to understand its own structure and the role of each component.

[0853] Next, it has a means of collecting real-time data. The server periodically collects log files and resource metrics (e.g., CPU usage, memory usage, network traffic, etc.) during operation. The server's built-in anomaly detection algorithm analyzes this data and detects failures in real time.

[0854] When a failure is detected, the server identifies the cause and generates the optimal recovery method. The server analyzes detailed log files and resource metrics, and derives appropriate countermeasures based on past failure cases and learned data. The server then notifies the user of the generated recovery method.

[0855] The user checks the recovery method presented on the terminal. The recovery method includes specific steps and risk assessment. If the user determines that there are no problems with the recovery method, they click the approval button to send instructions to the server.

[0856] The server automatically executes recovery procedures after receiving approval from the user, for example, restarting the heavily loaded process, changing the configuration, or redistributing resources. The server again logs the recovery results and notifies the user.

[0857] This system can also be applied to the monitoring and recovery of autonomous vehicles. It collects data from sensors and computer systems installed in autonomous vehicles, detects faults based on anomaly detection algorithms, and generates and proposes optimal recovery methods. Users (in this case, the operation manager or system administrator) can approve and execute recovery operations.

[0858] Specific examples

[0859] For example, consider a situation where the CPU usage of an autonomous vehicle suddenly increases. In this situation, the server detects the anomaly and, after analyzing logs and resource metrics, discovers that a specific high-load process is the cause. Based on this information, the server's AI model proposes the optimal recovery method and notifies the user of the details via their device. If the user confirms the proposal and clicks the approval button, the server will restart the high-load process, and CPU usage will return to the normal range.

[0860] Prompt Sentence Examples

[0861] "In a self-driving car system, detect an anomaly when CPU usage suddenly increases, and propose the optimal recovery method. After the user approves the proposal, implement a system in Python that automatically executes the recovery method."

[0862] As described above, by implementing the present invention, it becomes possible to quickly detect system failures in autonomous vehicles and automatically generate and execute optimal recovery methods, thereby enabling advanced failure response.

[0863] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0864] Step 1:

[0865] The server analyzes and learns from uploaded documents (server configuration diagrams and design documents) to understand its own structure and the role of each component.

[0866] Input: Server configuration diagram and design document (configuration information document)

[0867] Output: Analyzed server configuration information, trained generative AI model

[0868] Specific operation: The server reads the configuration diagrams and design documents, stores the structural information in a database, and trains the generative AI model.

[0869] Step 2:

[0870] The server collects log files and resource metrics (such as CPU usage, memory usage, and network traffic) in real time, allowing you to monitor the current state of the system.

[0871] Input: System log files, resource metrics (real-time data)

[0872] Output: Collected data

[0873] Specific operation: The server periodically collects data from sensors and system logs and stores it in a designated database.

[0874] Step 3:

[0875] The server applies an anomaly detection algorithm based on the collected real-time data to detect faults.

[0876] Input: Collected data (system log files, resource metrics)

[0877] Output: Fault detection result (abnormal occurrence status)

[0878] Specific operation: The server runs an anomaly detection algorithm, analyzes patterns in the data, and detects anomalies.

[0879] Step 4:

[0880] The server identifies the cause of the detected failure and generates the optimal recovery method based on past cases and learned data.

[0881] Input: fault detection results, log files, resource metrics, past fault cases

[0882] Output: Generated recovery methods

[0883] How it works: The server performs detailed analysis of the data and uses a generative AI model to suggest the optimal recovery method.

[0884] Step 5:

[0885] The server notifies the user of the generated recovery method, and the user can check the details of the recovery method using the terminal.

[0886] Input: Generated recovery method

[0887] Output: Recovery method notified to the user

[0888] Specific operation: The server notifies the user via the terminal of details of how to recover.

[0889] Step 6:

[0890] The user checks the presented recovery method and clicks the approval button to send approval to the server.

[0891] Input: User confirmation and approval

[0892] Output: Approved recovery methods

[0893] Specific operation: The user checks the proposal on the device and clicks the approval button to send instructions to the server.

[0894] Step 7:

[0895] The server automatically executes recovery procedures approved by the user.

[0896] Input: Approved recovery method

[0897] Output: Recovery steps taken, normalized system state

[0898] Specific Action: The server executes authorized recovery procedures to restore system performance.

[0899] 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.

[0900] This invention combines an emotion engine with a system that analyzes and learns from materials including server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of that recovery method, and executes the recovery method after receiving the user's approval. The emotion engine has the function of recognizing the user's emotions and adjusting the notification content and recovery process accordingly.

[0901] System Overview

[0902] Learning server configuration information

[0903] Before a server begins operation, users upload server configuration diagrams, design documents, and other documents to the server using a terminal. The server analyzes these documents, stores the server configuration information in a database, and trains an AI model. This process allows the server to understand its own structure and the role of each component.

[0904] Fault Monitoring and Detection

[0905] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.) The server's built-in AI applies anomaly detection algorithms to this data to detect failures in real time.

[0906] Identifying the cause of the failure and generating a recovery method

[0907] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. Next, the AI ​​generates the optimal recovery method based on learned data and past failure cases. The server notifies the user of this recovery method via their device.

[0908] Adjusting notification content with an emotion engine

[0909] The emotion engine analyzes the user's facial expressions, voice tone, and other biometric signals to recognize the user's emotions. The server uses the emotion engine to adjust the notification content based on the user's emotions. For example, if the user is feeling stressed, the server can make the notification content clearer and more concise.

[0910] Confirm and approve the recovery method

[0911] The user confirms the recovery method presented on the device, which includes specific steps and risk assessments. The emotion engine also works during this process, utilizing the user's emotional data to assist in reducing the psychological burden. If the user is satisfied with the recovery method, they click the approve button to send instructions to the server.

[0912] Implementing an automatic recovery process

[0913] With user approval, the server automatically executes recovery procedures, which can include restarting the overloaded process, changing configuration settings, or redistributing resources. The server again logs the results of the recovery and notifies the user.

[0914] Specific examples

[0915] For example, consider a situation where a server's CPU usage suddenly increases and the service becomes unresponsive. In this situation, the server detects the anomaly and, by analyzing logs and resource metrics, discovers that a specific process is using excessive resources.

[0916] Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. The server then uses an emotion engine to analyze the user's emotions, and if signs of stress are detected, the server notifies the user of the proposal in a more understandable and concise manner. The user checks the proposal, agrees, and clicks the approval button. Upon receiving approval, the server restarts the high-load process, and CPU usage returns to normal.

[0917] This system not only improves the efficiency of server operations and the reliability of services, but also reduces the psychological burden on users. In this way, incorporating emotional engineering will enable more advanced server operation management.

[0918] The processing flow will be explained below.

[0919] Step 1: Upload the server configuration information

[0920] The terminal sends the server configuration diagram and design documents to the server through a dedicated upload interface.

[0921] Step 2: Analyze and learn server configuration information

[0922] The server analyzes the uploaded data, stores the server configuration information in a database, and trains an AI model to understand the server's structure and the role of each component.

[0923] Step 3: Collect real-time data

[0924] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.).

[0925] Step 4: Detecting failures

[0926] The AI ​​in the server applies an anomaly detection algorithm to the collected data and determines whether there are any abnormalities in real time.

[0927] Step 5: Identify the cause of the problem

[0928] When a failure is detected, the server performs further analysis of log files and resource metrics to identify the specific cause of the failure.

[0929] Step 6: Generate recovery methods

[0930] The AI ​​in the server generates the optimal recovery method based on the learned data and past failure cases. The generated recovery method includes specific steps and necessary commands.

[0931] Step 7: Notification of restoration proposal

[0932] The server notifies the user of the generated recovery method by sending an alert to the terminal and displaying the proposed method.

[0933] Step 8: Adjusting notification content with the emotion engine

[0934] The server runs an emotion engine that analyzes the user's facial expressions, voice tone, and other biometric signals to recognize the user's emotions. If the user is feeling stressed, the notification content will be adjusted to be more clear and concise.

[0935] Step 9: Check the recovery method

[0936] The user can then view the recovery proposal from the server via their device, which includes specific recovery procedures, an estimate of the time required, and an assessment of the risks.

[0937] Step 10: Assisting the user with an emotion engine

[0938] The server's emotion engine assists users in understanding the suggestions, for example by adding reassuring explanations and support messages if the user is feeling anxious.

[0939] Step 11: Send Approval

[0940] After the user confirms that there are no problems with the proposed recovery method, he or she clicks the approval button on the terminal and sends instructions to the server.

[0941] Step 12: Perform recovery procedures

[0942] The server receives approval from the user and automatically executes the proposed recovery steps, which may include restarting services, changing configuration, or redistributing resources.

[0943] Step 13: Logging the recovery results and resuming monitoring

[0944] The server logs the recovery steps it took and their results, collects new data, and re-monitors the system status to see if the problem has been resolved.

[0945] Step 14: Notification of results

[0946] The server notifies the user of the final recovery result, letting them know that recovery is complete, and uses an emotion engine to provide reassuring feedback to the user.

[0947] Example 2

[0948] 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."

[0949] In modern information systems, server operation and management is a complex and advanced task. When a failure occurs, it is extremely difficult to quickly identify the cause and take appropriate action, placing significant stress on users. Furthermore, traditional systems often provide notifications and instructions without considering the user's emotional state, making it difficult for users to understand and respond to the information. This can lead to issues such as reduced service reliability and operational efficiency.

[0950] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0951] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting failures based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying the user of the generated recovery method, means for analyzing the user's emotions, means for adjusting the notification content according to the user's emotions, means for accepting the user's approval, and means for executing the approved recovery method. This improves the efficiency of server operation management and service reliability, reduces the psychological burden on users, and enables quick and appropriate failure response.

[0952] "Server configuration information" is information that indicates the physical and logical layout of the server, the network configuration, and the role and design principles of each component.

[0953] "Real-time data" refers to data that is updated regularly, such as log files, CPU usage, memory usage, and network traffic, that the server collects to understand its current status.

[0954] A "failure" is an abnormal behavior or error that occurs during server operation, which disrupts the normal functioning of the system.

[0955] A "recovery method" refers to specific procedures and measures to resolve the cause of a failure when it occurs and to restore the server to normal operating status.

[0956] The "emotion engine" is a system that analyzes a user's facial expressions, voice tone, and biometric signals to recognize their emotional state.

[0957] "Adjusting notification content" is the process of changing the format and content of the information or instructions provided depending on the user's emotional state.

[0958] "Approval" is the act of the user agreeing with the proposed recovery method and allowing its execution.

[0959] An "automatic recovery process" is a series of specific actions based on a recovery method that are automatically executed by the server after receiving user approval.

[0960] This invention is a system that analyzes and learns from server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval. Furthermore, by combining it with an emotion engine, it has the function of adjusting the notification content and recovery process according to the user's emotional state.

[0961] Learning server configuration information

[0962] Before the server begins operation, documents such as server configuration diagrams and design documents are uploaded to the server using a terminal. The server analyzes these documents using natural language processing (NLP) technology and stores the server configuration information in a database. For example, the analysis uses SpaCy as an NLP library and TensorFlow or PyTorch as an AI model. This allows the server to understand its own structure and the role of each component.

[0963] Fault Monitoring and Detection

[0964] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.). The AI ​​in the server applies anomaly detection algorithms such as Isolation Forest and LSTM (Long Short-Term Memory) to analyze the collected data in real time to detect anomalies. For example, it can be configured to issue an alert if CPU usage exceeds 80%.

[0965] Identifying the cause of the failure and generating a recovery method

[0966] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. Based on the analysis results, the AI ​​refers to learned data and past failure cases to generate the optimal recovery method. The generated recovery method includes specific steps and risk assessments. This information is notified to the user via their device.

[0967] Adjusting notification content with an emotion engine

[0968] The emotion engine recognizes the user's emotions by analyzing their facial expressions (collected by a webcam), voice tone (collected by a microphone), and other biometric signals (such as heart rate and galvanic skin response). The server uses the emotion engine to tailor the notification content based on the user's emotions. For example, if the user is feeling stressed, the server can respond by making the notification content more understandable and concise. Examples of prompts input to the generative AI model include: "Please give a short, clear explanation of the suggestion to restart a high-load process."

[0969] Confirm and approve the recovery method

[0970] The user confirms the recovery method presented on the device, which includes specific steps and risk assessments. The emotion engine also works during this process, utilizing the user's emotional data to assist in reducing the psychological burden. If the user is satisfied with the recovery method, they click the approve button to send instructions to the server.

[0971] Implementing an automatic recovery process

[0972] With user approval, the server automatically executes recovery procedures, such as restarting high-load processes, changing configurations, reallocating resources, etc. The server logs the results of these operations and notifies the user.

[0973] As a concrete example, consider a case where a server's CPU usage suddenly rises and the service becomes unresponsive. In this situation, the server detects the anomaly and, after analyzing logs and resource metrics, discovers that a specific process is using excessive resources. Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. The server then uses an emotion engine to analyze the user's emotions, and if signs of stress are detected, the server notifies the user of the proposal in a more understandable and concise manner. The user confirms the proposal, agrees, and clicks the approval button. With approval, the server restarts the high-load process, and CPU usage returns to normal range.

[0974] This system not only improves the efficiency of server operations and the reliability of services, but also reduces the psychological burden on users. In this way, incorporating emotional engineering will enable more advanced server operation management.

[0975] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0976] Step 1:

[0977] The user uploads server configuration information using a terminal. The user sends documents such as server configuration diagrams and design documents to the server via the terminal. The server configuration diagram and design document files are provided as input, and these documents are uploaded to the server as output.

[0978] Specific behavior:

[0979] The user selects the file "server_diagram.pdf" from the folder and clicks the upload button displayed on the terminal. The server receives the file and prepares it for analysis.

[0980] Step 2:

[0981] The server analyzes the uploaded materials. The server uses natural language processing (NLP) technology to analyze the files to extract server configuration information. The input is the server configuration diagram or design document to be analyzed, and the analysis results are stored in a database as output.

[0982] Specific behavior:

[0983] The server uses an NLP library (e.g., SpaCy) to analyze the uploaded "server_diagram.pdf" and extract the network structure and the role of each component. The extracted information is stored in a database.

[0984] Step 3:

[0985] The server uses the configuration information stored in the database to train the AI ​​model. Data is input into the AI ​​model (e.g., TensorFlow or PyTorch), and the server understands its own structure and the role of each component. The server configuration information is provided as input, and a trained model is obtained as output.

[0986] Specific behavior:

[0987] The server provides the configuration information saved in the previous step to the AI ​​model and starts the learning process. Once learning is complete, the server saves the model and prepares it for future fault detection.

[0988] Step 4:

[0989] The server periodically collects real-time data. During operation, the server collects log files and resource metrics such as CPU usage, memory usage, and network traffic. Various resource data is provided as input, and a periodically updated collection of data is obtained as output.

[0990] Specific behavior:

[0991] The server records CPU usage every five minutes and collects memory usage and network traffic data, which is then stored in a log file.

[0992] Step 5:

[0993] The server applies an anomaly detection algorithm to detect faults. The AI ​​in the server uses an anomaly detection algorithm such as Isolation Forest or LSTM on the collected real-time data. The real-time data is provided as input, and the anomaly detection results are obtained as output.

[0994] Specific behavior:

[0995] The server periodically analyzes the collected data and issues an alert if CPU usage exceeds 80%. Data patterns that are deemed abnormal are recorded.

[0996] Step 6:

[0997] The server identifies the cause of the failure and generates the optimal recovery method. The server performs detailed analysis of the detected anomaly to identify the cause of the failure. Next, it uses an AI model to generate the optimal recovery method. The failure detection results and past failure case data are provided as input, and the recovery method is generated as output.

[0998] Specific behavior:

[0999] The server analyzes the log files and extracts events before and after the abnormality occurred. AI proposes the optimal recovery method based on past data and automatically generates the procedure.

[1000] Step 7:

[1001] The generated recovery method is notified to the user. The server notifies the user of the proposed recovery method through the terminal. The generated recovery method is provided as input, and a notification displayed to the user is obtained as output.

[1002] Specific behavior:

[1003] The server sends the provided recovery method to the user's terminal and displays a message saying "The high-load process will be restarted."

[1004] Step 8:

[1005] The server analyzes the user's emotions using an emotion engine. The user's facial expressions, voice tone, and biometric signals are collected and analyzed by the emotion engine. Data from the webcam, microphone, and biometric sensors are provided as input, and the user's emotional state is obtained as output.

[1006] Specific behavior:

[1007] The user sits in front of the camera, and the server collects facial expressions and tone of voice. The emotion engine analyzes these and determines whether the user is feeling stressed.

[1008] Step 9:

[1009] The server adjusts the notification content according to the user's emotions. Based on the collected emotional data, the server adjusts the notification content appropriately. The user's emotional state is provided as input, and the adjusted notification content is obtained as output.

[1010] Specific behavior:

[1011] If the user is stressed, the server will try to make the notification message as clear and concise as possible. For example, it will send a simple message such as "Please restart the high-load process."

[1012] Step 10:

[1013] The user checks and approves the recovery method presented on the terminal. The user checks the recovery method via the terminal and clicks the approve button. The details of the recovery method are provided as input, and the click of the "Approve" button is obtained as output.

[1014] Specific behavior:

[1015] The user checks the recovery procedure displayed on the screen and, if there are no problems, clicks the "Approve" button.

[1016] Step 11:

[1017] The server automatically executes recovery procedures after receiving approval from the user. Based on the approved recovery method, the server automatically initiates a response. The user's approval is provided as input, and the executed recovery operation is obtained as output.

[1018] Specific behavior:

[1019] The server will automatically take action such as restarting high-load processes, changing settings, and reallocating resources.

[1020] Step 12:

[1021] The server logs the recovery results and notifies the user. The server logs the recovery results and notifies the user of successful recovery. The input is the result of the performed recovery operation, and the output is the logged data and a notification.

[1022] Specific behavior:

[1023] The server logs the results of the recovery operation and sends a message to the user saying, "The high-load process was successfully restarted. CPU usage has returned to normal."

[1024] (Application example 2)

[1025] 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."

[1026] In conventional systems, when a server or robot failure occurs, there are limited ways to respond quickly and appropriately, which places a significant psychological burden on on-site maintenance staff. Furthermore, it is difficult to collect and notify real-time data on-site, which often means that staff are unable to respond immediately. Therefore, there is a need for more efficient fault response and a reduction in the psychological burden on staff.

[1027] 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.

[1028] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting a failure based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying a user of the generated recovery method, means for receiving user approval, means for executing the approved recovery method, means for recognizing the user's emotions using an emotion engine and adjusting the notification content, and means for displaying real-time data using smart glasses and monitoring the user's emotions. This enables a quick and appropriate response when a failure occurs and reduces the psychological burden on maintenance staff.

[1029] "Server configuration information" is information that describes the structure of the server, the layout of each component, and the settings.

[1030] "Documents" refers to all documents necessary for server operation, such as server configuration diagrams and design documents.

[1031] "Real-time data" refers to data collected at any time while a server or robot is operating, and includes CPU usage, memory usage, network traffic, etc.

[1032] "Failure" refers to an abnormal situation that prevents a server or robot from operating normally.

[1033] "Cause of failure" refers to the direct cause or factor of the failure that occurred.

[1034] "Recovery methods" are procedures and measures for resolving a failure and restoring the system to normal operating condition.

[1035] An "emotion engine" refers to technology that recognizes emotions by analyzing a user's facial expressions, voice tone, biometric signals, etc.

[1036] "Smart glasses" are a wearable eyeglass-type device equipped with technologies such as augmented reality, and are used to display and collect information.

[1037] "User emotion" refers to the emotional state that a user feels when responding to a problem.

[1038] "Adjusting notification content" is the process of changing the content and format of a notification message based on the user's emotions recognized by the emotion engine.

[1039] To specifically implement this invention, the following system configuration and processes are required: The roles of the server, terminal, and user are clarified, and technical details are described.

[1040] Cloud server and real-time data collection

[1041] The server is deployed on the cloud and learns by analyzing documents such as server configuration diagrams and design documents. After uploading these documents, the server analyzes them using an AI model and stores the server configuration information in a database. This process primarily uses the Python programming language and the TensorFlow library.

[1042] During operation, the server collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.) in real time, using Elasticsearch as a log management system and Apache Kafka for real-time processing.

[1043] Implementing fault detection and recovery processes

[1044] The server detects anomalies based on the collected data. Specifically, it uses the PyCaret anomaly detection algorithm to detect failures in real time. When an anomaly is detected, the server performs a detailed analysis of log files and resource metrics and identifies the cause of the failure using a generative AI model. It then generates and proposes the optimal recovery method.

[1045] At this time, the server notifies the user of the generated recovery method. This notification is displayed in real time on the device, such as smart glasses, so the user can confirm and approve it. For example, you can use 'React Native' to build an application for smart glasses that displays the necessary information.

[1046] Smart glasses and emotion engine operation

[1047] The smart glasses are equipped with an emotion engine that recognizes the user's emotions by analyzing their facial expressions, voice tone, and biometric signals. This uses libraries such as OpenCV and Dlib, and adjusts the notification content according to the user's emotions. For example, if the user is feeling stressed, the notification message will be changed to a simpler and more understandable one.

[1048] Specific examples

[1049] As a concrete example of setting the subject to the server, consider a case where a maintenance staff member at a factory is wearing smart glasses when the motor of a robot in the factory starts making an abnormal noise. The server collects data on the robot in real time and detects the abnormality. In this case, the server analyzes the abnormal sound data and identifies that the problem is with a specific motor part. The server then generates an appropriate recovery method (e.g., restarting the motor) and uses an emotion engine to display a notification on the smart glasses based on the user's emotional state. Once the user confirms and approves the recovery method, the server immediately executes the procedure and returns the motor to normal.

[1050] Prompt Sentence Examples

[1051] An example of a prompt when a failure occurs could be the following text:

[1052] Based on server log data and resource metrics, the following anomalies were detected:

[1053] CPU usage is 85%.

[1054] Memory usage is 78%.

[1055] Network traffic is 50%.

[1056] Use this information to identify the cause of the anomaly and suggest the best way to recover.

[1057] Please include specific steps and risk assessments in your proposal.

[1058] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1059] Step 1:

[1060] The server uploads documents such as server configuration diagrams and design documents, analyzes them, and learns. The server configuration information (documents) is used as input, and the server configuration information is saved in a database as an analysis result, which is then trained by the AI ​​model. This makes it possible to understand the server configuration and the role of each component.

[1061] Step 2:

[1062] During operation, the server collects real-time data such as log files and resource metrics (CPU usage, memory usage, network traffic, etc.) using Elasticsearch and Apache Kafka. The input is operational data from servers and robots, which is stored as time-series data.

[1063] Step 3:

[1064] The server applies an anomaly detection algorithm to the collected real-time data to detect faults. This process uses the "PyCaret" anomaly detection algorithm. The input is real-time data, and the output is a check for the presence or absence of an abnormality and generates notification information if an abnormality is detected.

[1065] Step 4:

[1066] The server uses a generative AI model to identify the cause of the detected anomaly and generate an optimal recovery method. The input is the log file and resource metrics when the anomaly is detected, and the output is the identified cause of the failure and a proposed recovery method.

[1067] Step 5:

[1068] The server sends the generated recovery method to a device such as smart glasses to notify the user. An emotion engine is running and adjusts the notification content according to the user's emotional state. The input is the generated recovery method and the user's emotion analysis data, and the output is an appropriate notification message for the user.

[1069] Step 6:

[1070] The user checks the notification content using the smart glasses and approves the recovery method. The input is the recovery method displayed on the smart glasses, and the output is the user's approval action (clicking the approval button).

[1071] Step 7:

[1072] The server executes recovery procedures upon receiving approval from the user. The input is the approval data from the user, and the output is the recovery procedures to be executed (for example, restarting a high-load process or redistributing resources). This process restores normal operation of the server or robot, and the recovery results are recorded in the log again.

[1073] Step 8:

[1074] The server again logs the recovery result and notifies the user. The input is the result data of the recovery process, and the output is the log of the result and a final notification to the user.

[1075] 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.

[1076] 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.

[1077] 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.

[1078] [Fourth embodiment]

[1079] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1080] 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.

[1081] 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).

[1082] 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.

[1083] 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.

[1084] 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).

[1085] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1086] 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.

[1087] 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.

[1088] 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.

[1089] 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.

[1090] 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.

[1091] 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."

[1092] The present invention is a system that analyzes and learns from materials including server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval.

[1093] System Overview

[1094] Learning server configuration information

[1095] Before a server begins operation, users upload server configuration diagrams, design documents, and other documents to the server using a terminal. The server analyzes these documents, stores the server configuration information in a database, and trains an AI model. This process allows the server to understand its own structure and the role of each component.

[1096] Fault Monitoring and Detection

[1097] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.) The server's built-in AI applies anomaly detection algorithms to this data to detect failures in real time.

[1098] Identifying the cause of the problem and presenting recovery methods

[1099] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. Next, the AI ​​generates the optimal recovery method based on learned data and past failure cases. The server notifies the user of this recovery method via their device.

[1100] Confirm and approve the recovery method

[1101] The user checks the recovery method presented on the terminal. The recovery method includes specific procedures and risk assessments. If the user is satisfied with the recovery method, they click the approval button to send instructions to the server.

[1102] Implementing an automatic recovery process

[1103] With user approval, the server automatically executes recovery procedures, which can include restarting the overloaded process, changing configuration settings, or redistributing resources. The server again logs the results of the recovery and notifies the user.

[1104] Specific examples

[1105] For example, consider a situation where a server's CPU usage suddenly increases and the service becomes unresponsive. In this situation, the server detects the anomaly and, by analyzing logs and resource metrics, discovers that a specific process is using excessive resources.

[1106] Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. This proposal is notified to the user via their device. The user checks the proposal and clicks the approval button. Upon approval, the server restarts the high-load process, and CPU usage returns to normal range.

[1107] The above is the overall flow of the automated operation process realized by the system of the present invention. This system makes it possible to improve the efficiency of server operation and the reliability of services.

[1108] The processing flow will be explained below.

[1109] Step 1: Upload the server configuration information

[1110] The terminal sends the server configuration diagram and design documents to the server through a dedicated upload interface.

[1111] Step 2: Analyze and learn server configuration information

[1112] The server analyzes the uploaded data, stores the server configuration information in a database, and trains an AI model to understand the server's structure and the role of each component.

[1113] Step 3: Collect real-time data

[1114] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.).

[1115] Step 4: Detecting failures

[1116] The AI ​​in the server applies an anomaly detection algorithm to the collected data and determines whether there are any abnormalities in real time.

[1117] Step 5: Identify the cause of the problem

[1118] When a failure is detected, the server performs further analysis of log files and resource metrics to identify the specific cause of the failure.

[1119] Step 6: Generate recovery methods

[1120] The AI ​​in the server generates the optimal recovery method based on the learned data and past failure cases. The generated recovery method includes specific steps and necessary commands.

[1121] Step 7: Notification of restoration proposal

[1122] The server notifies the user of the generated recovery method by sending an alert to the terminal and displaying the proposed method.

[1123] Step 8: Check the recovery method

[1124] The user can then view the recovery proposal from the server via their device, which includes specific recovery procedures, an estimate of the time required, and an assessment of the risks.

[1125] Step 9: Send approval

[1126] After the user confirms that there are no problems with the proposed recovery method, he or she clicks the approval button on the terminal and sends instructions to the server.

[1127] Step 10: Perform recovery procedures

[1128] The server receives approval from the user and automatically executes the proposed recovery steps, which may include restarting services, changing configuration, or redistributing resources.

[1129] Step 11: Logging the recovery results and resuming monitoring

[1130] The server logs the recovery steps it took and their results, collects new data, and re-monitors the system status to see if the problem has been resolved.

[1131] Step 12: Notification of results

[1132] The server will notify the user of the final recovery result and inform them that recovery is complete.

[1133] Example 1

[1134] 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."

[1135] Modern server operations require the ability to grasp server configuration information and monitor failures in real time, but there is a lack of methods for managing these efficiently and recovering quickly and accurately. In particular, identifying the cause of complex failures and creating optimal recovery methods requires advanced technology, placing a heavy burden on users. For this reason, improving the efficiency and reliability of server operations has become a challenge.

[1136] 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.

[1137] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting failures based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying the user of the generated recovery method, means for receiving user approval, means for executing the approved recovery method, means for analyzing log files and resource metrics to identify the cause of the failure, means for training an AI model to learn the server configuration information, means for using an anomaly detection algorithm, and means for including specific procedures and risk assessments in the recovery method, thereby enabling the efficiency and reliability of server operation to be improved.

[1138] "Server configuration information" is information that indicates details such as the layout, settings, and linkage relationships of the server's hardware and software.

[1139] "Documents" refers to documents and data files that contain server configuration information, such as server configuration diagrams and design documents.

[1140] "Real-time data" refers to data that is continuously collected and processed immediately while the server is running, including resource metrics such as CPU usage, memory usage, and network traffic.

[1141] "Failure" refers to a condition that prevents the normal operation of a server or an event that causes the provision of service to cease.

[1142] "Recovery method" refers to the procedures and actions taken to resolve the detected failure and restore normal operation of the server.

[1143] "User" refers to the person or organization that operates and manages the server.

[1144] An "AI model" is an algorithm or system that uses data to learn and has the ability to help detect faults and generate recovery methods.

[1145] A "log file" refers to a file that records the server's operation history, error messages, etc.

[1146] "Resource metrics" is data that indicates the usage of server resources, such as CPU usage, memory usage, and network traffic.

[1147] "Approval" refers to the action of the user agreeing to the presented recovery method and allowing it to be carried out.

[1148] An "anomaly detection algorithm" is a method for analyzing collected data and detecting abnormal behavior or conditions.

[1149] "Risk assessment" refers to the process of assessing the potential risks involved in executing a recovery method and presenting them to the user.

[1150] This invention is a system that analyzes and learns from materials including server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval. Specific embodiments of this system are described below.

[1151] Learning server configuration information

[1152] Before the server begins operation, the user uses a terminal to upload documents such as server configuration diagrams and design documents to the server. The server automatically analyzes these documents and obtains server configuration information. The analyzed information is stored in a database and fed to an AI model for learning. This learning allows the server to understand its own structure and the role of each component.

[1153] Fault Monitoring and Detection

[1154] During operation, the server periodically collects log files and resource metrics (e.g., CPU usage, memory usage, network traffic, etc.). The collected data is analyzed in real time by the server's built-in AI using anomaly detection algorithms. This process allows the server to quickly detect failures.

[1155] Identifying the cause of the problem and presenting recovery methods

[1156] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. The AI ​​model then generates an optimal recovery plan based on the learned data and past failure cases. This recovery plan includes specific steps and risk assessments, and the server notifies the user via the terminal.

[1157] Confirm and approve the recovery method

[1158] The user checks the recovery method presented on the terminal, confirms the procedures and risk assessment displayed on the screen, and if there are no problems, clicks the approval button to send the instructions to the server.

[1159] Implementing an automatic recovery process

[1160] The server receives approval from the user and automatically executes recovery procedures, which may include restarting high-load processes, changing configurations, redistributing resources, etc. Once recovery is complete, the server logs the results and notifies the user again.

[1161] Specific examples

[1162] For example, consider a situation where a server's CPU usage suddenly rises and the service stops responding. In this situation, the server detects the anomaly and, after analyzing logs and resource metrics, discovers that a specific process is using excessive resources. Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. This proposal is notified to the user via their terminal. The user confirms the proposal and clicks the approval button. With approval, the server restarts the high-load process, and CPU usage returns to the normal range.

[1163] Prompt Sentence Examples

[1164] By inputting prompts like the following into the generative AI model, you can get detailed information about the system and its specific processing:

[1165] What resource metrics does the server collect while it is running?

[1166]

[1167] What are the specific steps to train AI to learn server configuration information?

[1168]

[1169] What risk assessment factors should users consider when approving a recovery method?

[1170] The above is a specific embodiment of the system of the present invention, which aims to improve the efficiency and reliability of server operation.

[1171] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1172] Step 1: Collect and analyze server configuration information

[1173] Users use their devices to upload documents such as server configuration diagrams and design documents to the server. The server receives the uploaded documents as input and analyzes them. During this analysis process, text information from the documents is extracted and components and settings are identified. The server configuration information obtained as a result of the analysis is stored in a database. This information is used for subsequent AI model training.

[1174] Step 2: Learn the server configuration information

[1175] The server supplies the server configuration information obtained in step 1 as input to the AI ​​model for learning. During this learning process, data calculations are performed to understand the relationships between the server's components and the role of each component. As a result of learning, the AI ​​model gains a deeper understanding of the server configuration and improves its ability to generate appropriate countermeasures in the event of a failure.

[1176] Step 3: Collect real-time data

[1177] During operation, the server periodically collects log files and resource metrics (e.g., CPU usage, memory usage, network traffic, etc.). This data is continuously input by the server's internal monitoring system. The collected data is stored as the basis for real-time analysis.

[1178] Step 4: Applying anomaly detection algorithms

[1179] The server takes the real-time data collected in step 3 as input and applies an anomaly detection algorithm. This algorithm performs data analysis and statistical processing to identify deviations from normal operating patterns. If an anomaly is detected, the information is flagged as a fault.

[1180] Step 5: Identify the cause of the problem

[1181] When a failure is detected, the server analyzes log files and resource metrics in detail and uses that data as input to identify the cause of the failure. Specifically, it performs a comparative analysis by comparing the log data immediately before the anomaly was detected with past failure cases. This analysis identifies the cause of the failure, such as a process using excessive resources or a configuration error.

[1182] Step 6: Generate optimal recovery method

[1183] The server uses the AI ​​model to input the identified cause of the failure and generate the optimal recovery method. In this process, a recovery method including optimal procedures and risk assessment is proposed by referencing past failure data and learned data. The generated recovery method is notified to the user as a proposal.

[1184] Step 7: Notification of recovery method

[1185] The server notifies the user of the recovery method generated in step 6 via the terminal. The user confirms the information presented on the terminal. This notification includes specific recovery procedures and a risk assessment.

[1186] Step 8: Review and approve the recovery method

[1187] The user checks the proposed recovery method on the terminal, and if they find it satisfactory, they click the approval button to send the instruction to the server. After receiving the user's approval as input, the server proceeds to the next recovery procedure.

[1188] Step 9: Implementing the Automated Recovery Process

[1189] The server receives user approval as input and automatically executes recovery procedures, which may include restarting high-load processes, changing configurations, redistributing resources, etc. Once recovery is complete, the server again logs the results and notifies the user.

[1190] (Application example 1)

[1191] 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."

[1192] Sensor and computer system failures can occur in autonomous vehicles. Such failures directly affect the safety and reliability of the vehicle, so a rapid and accurate response is required. However, with current technology, failure detection and recovery are often performed manually, which is inefficient. It is also difficult to identify the cause of the failure and propose the optimal recovery method.

[1193] 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.

[1194] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting failures based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying a user of the generated recovery method, means for receiving user approval, means for executing the approved recovery method, means for collecting vehicle sensor data and resource metrics, and means for detecting anomalies in the autonomous vehicle and proposing a recovery method. This enables efficient and reliable failure response, such as quickly detecting system failures in the autonomous vehicle and automatically generating and executing an optimal recovery method.

[1195] "Server configuration information" refers to information that indicates the server's role, connection relationships, placement, etc., and refers to materials included in server configuration diagrams and design documents.

[1196] "Real-time data" refers to log files and resource metrics (CPU usage, memory usage, network traffic, etc.) generated during system operation.

[1197] "Failure" refers to an abnormality or malfunction that occurs in a server or autonomous vehicle system, including an event that interferes with normal operation.

[1198] "Cause of failure" refers to the specific factor or problem that caused the detected failure.

[1199] "Recovery method" refers to the procedures and measures to resolve a detected failure and restore normal system operation.

[1200] "User" refers to the person or computer program that manages, monitors, or operates the server or autonomous vehicle system.

[1201] "Sensor data" refers to information collected from sensors installed in autonomous vehicles, including location information, speed, surrounding conditions, etc.

[1202] "Resource metrics" are indicators that show the resource usage status of a system, and include CPU usage, memory usage, network traffic, etc.

[1203] "Abnormality" refers to any deviation from normal operating conditions or unexpected occurrence, including any malfunction that may adversely affect system performance or operation.

[1204] This invention is a system that analyzes and learns server configuration information, collects real-time data to detect faults, identifies the cause of the fault, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval. This system is particularly useful for improving the safety and reliability of autonomous vehicles. Specific embodiments of this system are described below.

[1205] This system has a means of analyzing and learning from server configuration information. The server uses a terminal to upload documents such as server configuration diagrams and design documents. The server analyzes these documents, stores the server configuration information in a database, and trains a generative AI model. This process allows the server to understand its own structure and the role of each component.

[1206] Next, it has a means of collecting real-time data. The server periodically collects log files and resource metrics (e.g., CPU usage, memory usage, network traffic, etc.) during operation. The server's built-in anomaly detection algorithm analyzes this data and detects failures in real time.

[1207] When a failure is detected, the server identifies the cause and generates the optimal recovery method. The server analyzes detailed log files and resource metrics, and derives appropriate countermeasures based on past failure cases and learned data. The server then notifies the user of the generated recovery method.

[1208] The user checks the recovery method presented on the terminal. The recovery method includes specific steps and risk assessment. If the user determines that there are no problems with the recovery method, they click the approval button to send instructions to the server.

[1209] The server automatically executes recovery procedures after receiving approval from the user, for example, restarting the heavily loaded process, changing the configuration, or redistributing resources. The server again logs the recovery results and notifies the user.

[1210] This system can also be applied to the monitoring and recovery of autonomous vehicles. It collects data from sensors and computer systems installed in autonomous vehicles, detects faults based on anomaly detection algorithms, and generates and proposes optimal recovery methods. Users (in this case, the operation manager or system administrator) can approve and execute recovery operations.

[1211] Specific examples

[1212] For example, consider a situation where the CPU usage of an autonomous vehicle suddenly increases. In this situation, the server detects the anomaly and, after analyzing logs and resource metrics, discovers that a specific high-load process is the cause. Based on this information, the server's AI model proposes the optimal recovery method and notifies the user of the details via their device. If the user confirms the proposal and clicks the approval button, the server will restart the high-load process, and CPU usage will return to the normal range.

[1213] Prompt Sentence Examples

[1214] "In a self-driving car system, detect an anomaly when CPU usage suddenly increases, and propose the optimal recovery method. After the user approves the proposal, implement a system in Python that automatically executes the recovery method."

[1215] As described above, by implementing the present invention, it becomes possible to quickly detect system failures in autonomous vehicles and automatically generate and execute optimal recovery methods, thereby enabling advanced failure response.

[1216] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1217] Step 1:

[1218] The server analyzes and learns from uploaded documents (server configuration diagrams and design documents) to understand its own structure and the role of each component.

[1219] Input: Server configuration diagram and design document (configuration information document)

[1220] Output: Analyzed server configuration information, trained generative AI model

[1221] Specific operation: The server reads the configuration diagrams and design documents, stores the structural information in a database, and trains the generative AI model.

[1222] Step 2:

[1223] The server collects log files and resource metrics (such as CPU usage, memory usage, and network traffic) in real time, allowing you to monitor the current state of the system.

[1224] Input: System log files, resource metrics (real-time data)

[1225] Output: Collected data

[1226] Specific operation: The server periodically collects data from sensors and system logs and stores it in a designated database.

[1227] Step 3:

[1228] The server applies an anomaly detection algorithm based on the collected real-time data to detect faults.

[1229] Input: Collected data (system log files, resource metrics)

[1230] Output: Fault detection result (abnormal occurrence status)

[1231] Specific operation: The server runs an anomaly detection algorithm, analyzes patterns in the data, and detects anomalies.

[1232] Step 4:

[1233] The server identifies the cause of the detected failure and generates the optimal recovery method based on past cases and learned data.

[1234] Input: fault detection results, log files, resource metrics, past fault cases

[1235] Output: Generated recovery methods

[1236] How it works: The server performs detailed analysis of the data and uses a generative AI model to suggest the optimal recovery method.

[1237] Step 5:

[1238] The server notifies the user of the generated recovery method, and the user can check the details of the recovery method using the terminal.

[1239] Input: Generated recovery method

[1240] Output: Recovery method notified to the user

[1241] Specific operation: The server notifies the user via the terminal of details of how to recover.

[1242] Step 6:

[1243] The user checks the presented recovery method and clicks the approval button to send approval to the server.

[1244] Input: User confirmation and approval

[1245] Output: Approved recovery methods

[1246] Specific operation: The user checks the proposal on the device and clicks the approval button to send instructions to the server.

[1247] Step 7:

[1248] The server automatically executes recovery procedures approved by the user.

[1249] Input: Approved recovery method

[1250] Output: Recovery steps taken, normalized system state

[1251] Specific Action: The server executes authorized recovery procedures to restore system performance.

[1252] 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.

[1253] This invention combines an emotion engine with a system that analyzes and learns from materials including server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of that recovery method, and executes the recovery method after receiving the user's approval. The emotion engine has the function of recognizing the user's emotions and adjusting the notification content and recovery process accordingly.

[1254] System Overview

[1255] Learning server configuration information

[1256] Before a server begins operation, users upload server configuration diagrams, design documents, and other documents to the server using a terminal. The server analyzes these documents, stores the server configuration information in a database, and trains an AI model. This process allows the server to understand its own structure and the role of each component.

[1257] Fault Monitoring and Detection

[1258] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.) The server's built-in AI applies anomaly detection algorithms to this data to detect failures in real time.

[1259] Identifying the cause of the failure and generating a recovery method

[1260] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. Next, the AI ​​generates the optimal recovery method based on learned data and past failure cases. The server notifies the user of this recovery method via their device.

[1261] Adjusting notification content with an emotion engine

[1262] The emotion engine analyzes the user's facial expressions, voice tone, and other biometric signals to recognize the user's emotions. The server uses the emotion engine to adjust the notification content based on the user's emotions. For example, if the user is feeling stressed, the server can make the notification content clearer and more concise.

[1263] Confirm and approve the recovery method

[1264] The user confirms the recovery method presented on the device, which includes specific steps and risk assessments. The emotion engine also works during this process, utilizing the user's emotional data to assist in reducing the psychological burden. If the user is satisfied with the recovery method, they click the approve button to send instructions to the server.

[1265] Implementing an automatic recovery process

[1266] With user approval, the server automatically executes recovery procedures, which can include restarting the overloaded process, changing configuration settings, or redistributing resources. The server again logs the results of the recovery and notifies the user.

[1267] Specific examples

[1268] For example, consider a situation where a server's CPU usage suddenly increases and the service becomes unresponsive. In this situation, the server detects the anomaly and, by analyzing logs and resource metrics, discovers that a specific process is using excessive resources.

[1269] Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. The server then uses an emotion engine to analyze the user's emotions, and if signs of stress are detected, the server notifies the user of the proposal in a more understandable and concise manner. The user checks the proposal, agrees, and clicks the approval button. Upon receiving approval, the server restarts the high-load process, and CPU usage returns to normal.

[1270] This system not only improves the efficiency of server operations and the reliability of services, but also reduces the psychological burden on users. In this way, incorporating emotional engineering will enable more advanced server operation management.

[1271] The processing flow will be explained below.

[1272] Step 1: Upload the server configuration information

[1273] The terminal sends the server configuration diagram and design documents to the server through a dedicated upload interface.

[1274] Step 2: Analyze and learn server configuration information

[1275] The server analyzes the uploaded data, stores the server configuration information in a database, and trains an AI model to understand the server's structure and the role of each component.

[1276] Step 3: Collect real-time data

[1277] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.).

[1278] Step 4: Detecting failures

[1279] The AI ​​in the server applies an anomaly detection algorithm to the collected data and determines whether there are any abnormalities in real time.

[1280] Step 5: Identify the cause of the problem

[1281] When a failure is detected, the server performs further analysis of log files and resource metrics to identify the specific cause of the failure.

[1282] Step 6: Generate recovery methods

[1283] The AI ​​in the server generates the optimal recovery method based on the learned data and past failure cases. The generated recovery method includes specific steps and necessary commands.

[1284] Step 7: Notification of restoration proposal

[1285] The server notifies the user of the generated recovery method by sending an alert to the terminal and displaying the proposed method.

[1286] Step 8: Adjusting notification content with the emotion engine

[1287] The server runs an emotion engine that analyzes the user's facial expressions, voice tone, and other biometric signals to recognize the user's emotions. If the user is feeling stressed, the notification content will be adjusted to be more clear and concise.

[1288] Step 9: Check the recovery method

[1289] The user can then view the recovery proposal from the server via their device, which includes specific recovery procedures, an estimate of the time required, and an assessment of the risks.

[1290] Step 10: Assisting the user with an emotion engine

[1291] The server's emotion engine assists users in understanding the suggestions, for example by adding reassuring explanations and support messages if the user is feeling anxious.

[1292] Step 11: Send Approval

[1293] After the user confirms that there are no problems with the proposed recovery method, he or she clicks the approval button on the terminal and sends instructions to the server.

[1294] Step 12: Perform recovery procedures

[1295] The server receives approval from the user and automatically executes the proposed recovery steps, which may include restarting services, changing configuration, or redistributing resources.

[1296] Step 13: Logging the recovery results and resuming monitoring

[1297] The server logs the recovery steps it took and their results, collects new data, and re-monitors the system status to see if the problem has been resolved.

[1298] Step 14: Notification of results

[1299] The server notifies the user of the final recovery result, letting them know that recovery is complete, and uses an emotion engine to provide reassuring feedback to the user.

[1300] Example 2

[1301] 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."

[1302] In modern information systems, server operation and management is a complex and advanced task. When a failure occurs, it is extremely difficult to quickly identify the cause and take appropriate action, placing significant stress on users. Furthermore, traditional systems often provide notifications and instructions without considering the user's emotional state, making it difficult for users to understand and respond to the information. This can lead to issues such as reduced service reliability and operational efficiency.

[1303] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1304] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting failures based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying the user of the generated recovery method, means for analyzing the user's emotions, means for adjusting the notification content according to the user's emotions, means for accepting the user's approval, and means for executing the approved recovery method. This improves the efficiency of server operation management and service reliability, reduces the psychological burden on users, and enables quick and appropriate failure response.

[1305] "Server configuration information" is information that indicates the physical and logical layout of the server, the network configuration, and the role and design principles of each component.

[1306] "Real-time data" refers to data that is updated regularly, such as log files, CPU usage, memory usage, and network traffic, that the server collects to understand its current status.

[1307] A "failure" is an abnormal behavior or error that occurs during server operation, which disrupts the normal functioning of the system.

[1308] A "recovery method" refers to specific procedures and measures to resolve the cause of a failure when it occurs and to restore the server to normal operating status.

[1309] The "emotion engine" is a system that analyzes a user's facial expressions, voice tone, and biometric signals to recognize their emotional state.

[1310] "Adjusting notification content" is the process of changing the format and content of the information or instructions provided depending on the user's emotional state.

[1311] "Approval" is the act of the user agreeing with the proposed recovery method and allowing its execution.

[1312] An "automatic recovery process" is a series of specific actions based on a recovery method that are automatically executed by the server after receiving user approval.

[1313] This invention is a system that analyzes and learns from server configuration information, collects real-time data to detect failures, identifies the cause of the failure, generates an optimal recovery method, notifies the user of the recovery method, and executes the recovery method after receiving the user's approval. Furthermore, by combining it with an emotion engine, it has the function of adjusting the notification content and recovery process according to the user's emotional state.

[1314] Learning server configuration information

[1315] Before the server begins operation, documents such as server configuration diagrams and design documents are uploaded to the server using a terminal. The server analyzes these documents using natural language processing (NLP) technology and stores the server configuration information in a database. For example, the analysis uses SpaCy as an NLP library and TensorFlow or PyTorch as an AI model. This allows the server to understand its own structure and the role of each component.

[1316] Fault Monitoring and Detection

[1317] During operation, the server periodically collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.). The AI ​​in the server applies anomaly detection algorithms such as Isolation Forest and LSTM (Long Short-Term Memory) to analyze the collected data in real time to detect anomalies. For example, it can be configured to issue an alert if CPU usage exceeds 80%.

[1318] Identifying the cause of the failure and generating a recovery method

[1319] When a failure is detected, the server analyzes log files and resource metrics in detail to identify the cause of the failure. Based on the analysis results, the AI ​​refers to learned data and past failure cases to generate the optimal recovery method. The generated recovery method includes specific steps and risk assessments. This information is notified to the user via their device.

[1320] Adjusting notification content with an emotion engine

[1321] The emotion engine recognizes the user's emotions by analyzing their facial expressions (collected by a webcam), voice tone (collected by a microphone), and other biometric signals (such as heart rate and galvanic skin response). The server uses the emotion engine to tailor the notification content based on the user's emotions. For example, if the user is feeling stressed, the server can respond by making the notification content more understandable and concise. Examples of prompts input to the generative AI model include: "Please give a short, clear explanation of the suggestion to restart a high-load process."

[1322] Confirm and approve the recovery method

[1323] The user confirms the recovery method presented on the device, which includes specific steps and risk assessments. The emotion engine also works during this process, utilizing the user's emotional data to assist in reducing the psychological burden. If the user is satisfied with the recovery method, they click the approve button to send instructions to the server.

[1324] Implementing an automatic recovery process

[1325] With user approval, the server automatically executes recovery procedures, such as restarting high-load processes, changing configurations, reallocating resources, etc. The server logs the results of these operations and notifies the user.

[1326] As a concrete example, consider a case where a server's CPU usage suddenly rises and the service becomes unresponsive. In this situation, the server detects the anomaly and, after analyzing logs and resource metrics, discovers that a specific process is using excessive resources. Based on this information, the server's AI generates a proposal to restart the high-load process as the optimal recovery method. The server then uses an emotion engine to analyze the user's emotions, and if signs of stress are detected, the server notifies the user of the proposal in a more understandable and concise manner. The user confirms the proposal, agrees, and clicks the approval button. With approval, the server restarts the high-load process, and CPU usage returns to normal range.

[1327] This system not only improves the efficiency of server operations and the reliability of services, but also reduces the psychological burden on users. In this way, incorporating emotional engineering will enable more advanced server operation management.

[1328] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1329] Step 1:

[1330] The user uploads server configuration information using a terminal. The user sends documents such as server configuration diagrams and design documents to the server via the terminal. The server configuration diagram and design document files are provided as input, and these documents are uploaded to the server as output.

[1331] Specific behavior:

[1332] The user selects the file "server_diagram.pdf" from the folder and clicks the upload button displayed on the terminal. The server receives the file and prepares it for analysis.

[1333] Step 2:

[1334] The server analyzes the uploaded materials. The server uses natural language processing (NLP) technology to analyze the files to extract server configuration information. The input is the server configuration diagram or design document to be analyzed, and the analysis results are stored in a database as output.

[1335] Specific behavior:

[1336] The server uses an NLP library (e.g., SpaCy) to analyze the uploaded "server_diagram.pdf" and extract the network structure and the role of each component. The extracted information is stored in a database.

[1337] Step 3:

[1338] The server uses the configuration information stored in the database to train the AI ​​model. Data is input into the AI ​​model (e.g., TensorFlow or PyTorch), and the server understands its own structure and the role of each component. The server configuration information is provided as input, and a trained model is obtained as output.

[1339] Specific behavior:

[1340] The server provides the configuration information saved in the previous step to the AI ​​model and starts the learning process. Once learning is complete, the server saves the model and prepares it for future fault detection.

[1341] Step 4:

[1342] The server periodically collects real-time data. During operation, the server collects log files and resource metrics such as CPU usage, memory usage, and network traffic. Various resource data is provided as input, and a periodically updated collection of data is obtained as output.

[1343] Specific behavior:

[1344] The server records CPU usage every five minutes and collects memory usage and network traffic data, which is then stored in a log file.

[1345] Step 5:

[1346] The server applies an anomaly detection algorithm to detect faults. The AI ​​in the server uses an anomaly detection algorithm such as Isolation Forest or LSTM on the collected real-time data. The real-time data is provided as input, and the anomaly detection results are obtained as output.

[1347] Specific behavior:

[1348] The server periodically analyzes the collected data and issues an alert if CPU usage exceeds 80%. Data patterns that are deemed abnormal are recorded.

[1349] Step 6:

[1350] The server identifies the cause of the failure and generates the optimal recovery method. The server performs detailed analysis of the detected anomaly to identify the cause of the failure. Next, it uses an AI model to generate the optimal recovery method. The failure detection results and past failure case data are provided as input, and the recovery method is generated as output.

[1351] Specific behavior:

[1352] The server analyzes the log files and extracts events before and after the abnormality occurred. AI proposes the optimal recovery method based on past data and automatically generates the procedure.

[1353] Step 7:

[1354] The generated recovery method is notified to the user. The server notifies the user of the proposed recovery method through the terminal. The generated recovery method is provided as input, and a notification displayed to the user is obtained as output.

[1355] Specific behavior:

[1356] The server sends the provided recovery method to the user's terminal and displays a message saying "The high-load process will be restarted."

[1357] Step 8:

[1358] The server analyzes the user's emotions using an emotion engine. The user's facial expressions, voice tone, and biometric signals are collected and analyzed by the emotion engine. Data from the webcam, microphone, and biometric sensors are provided as input, and the user's emotional state is obtained as output.

[1359] Specific behavior:

[1360] The user sits in front of the camera, and the server collects facial expressions and tone of voice. The emotion engine analyzes these and determines whether the user is feeling stressed.

[1361] Step 9:

[1362] The server adjusts the notification content according to the user's emotions. Based on the collected emotional data, the server adjusts the notification content appropriately. The user's emotional state is provided as input, and the adjusted notification content is obtained as output.

[1363] Specific behavior:

[1364] If the user is stressed, the server will try to make the notification message as clear and concise as possible. For example, it will send a simple message such as "Please restart the high-load process."

[1365] Step 10:

[1366] The user checks and approves the recovery method presented on the terminal. The user checks the recovery method via the terminal and clicks the approve button. The details of the recovery method are provided as input, and the click of the "Approve" button is obtained as output.

[1367] Specific behavior:

[1368] The user checks the recovery procedure displayed on the screen and, if there are no problems, clicks the "Approve" button.

[1369] Step 11:

[1370] The server automatically executes recovery procedures after receiving approval from the user. Based on the approved recovery method, the server automatically initiates a response. The user's approval is provided as input, and the executed recovery operation is obtained as output.

[1371] Specific behavior:

[1372] The server will automatically take action such as restarting high-load processes, changing settings, and reallocating resources.

[1373] Step 12:

[1374] The server logs the recovery results and notifies the user. The server logs the recovery results and notifies the user of successful recovery. The input is the result of the performed recovery operation, and the output is the logged data and a notification.

[1375] Specific behavior:

[1376] The server logs the results of the recovery operation and sends a message to the user saying, "The high-load process was successfully restarted. CPU usage has returned to normal."

[1377] (Application example 2)

[1378] 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."

[1379] In conventional systems, when a server or robot failure occurs, there are limited ways to respond quickly and appropriately, which places a significant psychological burden on on-site maintenance staff. Furthermore, it is difficult to collect and notify real-time data on-site, which often means that staff are unable to respond immediately. Therefore, there is a need for more efficient fault response and a reduction in the psychological burden on staff.

[1380] 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.

[1381] In this invention, the server includes means for analyzing and learning from materials including server configuration information, means for collecting real-time data, means for detecting a failure based on the collected data, means for identifying the cause of the failure and generating an optimal recovery method, means for notifying a user of the generated recovery method, means for receiving user approval, means for executing the approved recovery method, means for recognizing the user's emotions using an emotion engine and adjusting the notification content, and means for displaying real-time data using smart glasses and monitoring the user's emotions. This enables a quick and appropriate response when a failure occurs and reduces the psychological burden on maintenance staff.

[1382] "Server configuration information" is information that describes the structure of the server, the layout of each component, and the settings.

[1383] "Documents" refers to all documents necessary for server operation, such as server configuration diagrams and design documents.

[1384] "Real-time data" refers to data collected at any time while a server or robot is operating, and includes CPU usage, memory usage, network traffic, etc.

[1385] "Failure" refers to an abnormal situation that prevents a server or robot from operating normally.

[1386] "Cause of failure" refers to the direct cause or factor of the failure that occurred.

[1387] "Recovery methods" are procedures and measures for resolving a failure and restoring the system to normal operating condition.

[1388] An "emotion engine" refers to technology that recognizes emotions by analyzing a user's facial expressions, voice tone, biometric signals, etc.

[1389] "Smart glasses" are a wearable eyeglass-type device equipped with technologies such as augmented reality, and are used to display and collect information.

[1390] "User emotion" refers to the emotional state that a user feels when responding to a problem.

[1391] "Adjusting notification content" is the process of changing the content and format of a notification message based on the user's emotions recognized by the emotion engine.

[1392] To specifically implement this invention, the following system configuration and processes are required: The roles of the server, terminal, and user are clarified, and technical details are described.

[1393] Cloud server and real-time data collection

[1394] The server is deployed on the cloud and learns by analyzing documents such as server configuration diagrams and design documents. After uploading these documents, the server analyzes them using an AI model and stores the server configuration information in a database. This process primarily uses the Python programming language and the TensorFlow library.

[1395] During operation, the server collects log files and resource metrics (CPU usage, memory usage, network traffic, etc.) in real time, using Elasticsearch as a log management system and Apache Kafka for real-time processing.

[1396] Implementing fault detection and recovery processes

[1397] The server detects anomalies based on the collected data. Specifically, it uses the PyCaret anomaly detection algorithm to detect failures in real time. When an anomaly is detected, the server performs a detailed analysis of log files and resource metrics and identifies the cause of the failure using a generative AI model. It then generates and proposes the optimal recovery method.

[1398] At this time, the server notifies the user of the generated recovery method. This notification is displayed in real time on the device, such as smart glasses, so the user can confirm and approve it. For example, you can use 'React Native' to build an application for smart glasses that displays the necessary information.

[1399] Smart glasses and emotion engine operation

[1400] The smart glasses are equipped with an emotion engine that recognizes the user's emotions by analyzing their facial expressions, voice tone, and biometric signals. This uses libraries such as OpenCV and Dlib, and adjusts the notification content according to the user's emotions. For example, if the user is feeling stressed, the notification message will be changed to a simpler and more understandable one.

[1401] Specific examples

[1402] As a concrete example of setting the subject to the server, consider a case where a maintenance staff member at a factory is wearing smart glasses when the motor of a robot in the factory starts making an abnormal noise. The server collects data on the robot in real time and detects the abnormality. In this case, the server analyzes the abnormal sound data and identifies that the problem is with a specific motor part. The server then generates an appropriate recovery method (e.g., restarting the motor) and uses an emotion engine to display a notification on the smart glasses based on the user's emotional state. Once the user confirms and approves the recovery method, the server immediately executes the procedure and returns the motor to normal.

[1403] Prompt Sentence Examples

[1404] An example of a prompt when a failure occurs could be the following text:

[1405] Based on server log data and resource metrics, the following anomalies were detected:

[1406] CPU usage is 85%.

[1407] Memory usage is 78%.

[1408] Network traffic is 50%.

[1409] Use this information to identify the cause of the anomaly and suggest the best way to recover.

[1410] Please include specific steps and risk assessments in your proposal.

[1411] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1412] Step 1:

[1413] The server uploads documents such as server configuration diagrams and design documents, analyzes them, and learns. The server configuration information (documents) is used as input, and the server configuration information is saved in a database as an analysis result, which is then trained by the AI ​​model. This makes it possible to understand the server configuration and the role of each component.

[1414] Step 2:

[1415] During operation, the server collects real-time data such as log files and resource metrics (CPU usage, memory usage, network traffic, etc.) using Elasticsearch and Apache Kafka. The input is operational data from servers and robots, which is stored as time-series data.

[1416] Step 3:

[1417] The server applies an anomaly detection algorithm to the collected real-time data to detect faults. This process uses the "PyCaret" anomaly detection algorithm. The input is real-time data, and the output is a check for the presence or absence of an abnormality and generates notification information if an abnormality is detected.

[1418] Step 4:

[1419] The server uses a generative AI model to identify the cause of the detected anomaly and generate an optimal recovery method. The input is the log file and resource metrics when the anomaly is detected, and the output is the identified cause of the failure and a proposed recovery method.

[1420] Step 5:

[1421] The server sends the generated recovery method to a device such as smart glasses to notify the user. An emotion engine is running and adjusts the notification content according to the user's emotional state. The input is the generated recovery method and the user's emotion analysis data, and the output is an appropriate notification message for the user.

[1422] Step 6:

[1423] The user checks the notification content using the smart glasses and approves the recovery method. The input is the recovery method displayed on the smart glasses, and the output is the user's approval action (clicking the approval button).

[1424] Step 7:

[1425] The server executes recovery procedures upon receiving approval from the user. The input is the approval data from the user, and the output is the recovery procedures to be executed (for example, restarting a high-load process or redistributing resources). This process restores normal operation of the server or robot, and the recovery results are recorded in the log again.

[1426] Step 8:

[1427] The server again logs the recovery result and notifies the user. The input is the result data of the recovery process, and the output is the log of the result and a final notification to the user.

[1428] 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.

[1429] 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.

[1430] 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 robot 414.

[1431] 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.

[1432] 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.

[1433] 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.

[1434] 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).

[1435] 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.

[1436] 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."

[1437] 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.

[1438] 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).

[1439] 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.

[1440] 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.

[1441] 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.

[1442] 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.

[1443] 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.

[1444] 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.

[1445] 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.

[1446] 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.

[1447] 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.

[1448] 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.

[1449] The following is further disclosed regarding the above embodiment.

[1450] (Claim 1)

[1451] A means for analyzing and learning from materials including server configuration information;

[1452] a means for collecting real-time data;

[1453] a means for detecting faults based on the collected data;

[1454] A means for identifying the cause of the failure and generating an optimal recovery method;

[1455] a means for notifying a user of the generated recovery method;

[1456] means for accepting user approval;

[1457] A means of implementing approved recovery methods;

[1458] A system including:

[1459] (Claim 2)

[1460] 2. The system according to claim 1, wherein the document containing the server configuration information is a server configuration diagram or a design document.

[1461] (Claim 3)

[1462] 10. The system of claim 1, wherein the collected data is log files and resource metrics.

[1463] "Example 1"

[1464] (Claim 1)

[1465] A means for analyzing and learning from materials including server configuration information;

[1466] a means for collecting real-time data;

[1467] a means for detecting faults based on the collected data;

[1468] A means for identifying the cause of the failure and generating an optimal recovery method;

[1469] a means for notifying a user of the generated recovery method;

[1470] means for accepting user approval;

[1471] A means of implementing approved recovery methods;

[1472] A means of identifying the cause of a problem by analyzing log files and resource metrics,

[1473] A means for the AI ​​model to learn server configuration information;

[1474] a means for using an anomaly detection algorithm;

[1475] Measures that include specific procedures and risk assessments for recovery methods;

[1476] A system including:

[1477] (Claim 2)

[1478] 2. The system according to claim 1, wherein the document containing the server configuration information is a server configuration diagram or a design document.

[1479] (Claim 3)

[1480] 10. The system of claim 1, wherein the collected data is log files and resource metrics.

[1481] "Application Example 1"

[1482] (Claim 1)

[1483] A means for analyzing and learning from materials including server configuration information;

[1484] a means for collecting real-time data;

[1485] a means for detecting faults based on the collected data;

[1486] A means for identifying the cause of the failure and generating an optimal recovery method;

[1487] a means for notifying a user of the generated recovery method;

[1488] means for accepting user approval;

[1489] A means of implementing approved recovery methods;

[1490] a means for collecting vehicle sensor data and resource metrics;

[1491] A means for detecting anomalies in an autonomous vehicle and proposing recovery methods;

[1492] A system including:

[1493] (Claim 2)

[1494] 2. The system according to claim 1, wherein the document containing the server configuration information is a server configuration diagram or a design document.

[1495] (Claim 3)

[1496] 10. The system of claim 1, wherein the collected data is log files and resource metrics.

[1497] "Example 2: Combining Emotion Engines"

[1498] (Claim 1)

[1499] A means for analyzing and learning from materials including server configuration information;

[1500] a means for collecting real-time data;

[1501] a means for detecting faults based on the collected data;

[1502] A means for identifying the cause of the failure and generating an optimal recovery method;

[1503] a means for notifying a user of the generated recovery method;

[1504] means for analyzing user emotions;

[1505] A means for adjusting notification content according to the user's emotions;

[1506] means for accepting user approval;

[1507] A means of implementing approved recovery methods;

[1508] A system including:

[1509] (Claim 2)

[1510] 2. The system according to claim 1, wherein the document containing the server configuration information is a server configuration diagram or a design document.

[1511] (Claim 3)

[1512] 10. The system of claim 1, wherein the collected data is log files and resource metrics.

[1513] "Application example 2 when combining emotion engines"

[1514] (Claim 1)

[1515] A means for analyzing and learning from materials including server configuration information;

[1516] a means for collecting real-time data;

[1517] a means for detecting faults based on the collected data;

[1518] A means for identifying the cause of the failure and generating an optimal recovery method;

[1519] a means for notifying a user of the generated recovery method;

[1520] means for accepting user approval;

[1521] A means of implementing approved recovery methods;

[1522] A means for recognizing a user's emotion using an emotion engine and adjusting the notification content;

[1523] means for displaying real-time data and monitoring user emotions using smart glasses;

[1524] A system including:

[1525] (Claim 2)

[1526] 2. The system according to claim 1, wherein the document containing the server configuration information is a server configuration diagram or a design document.

[1527] (Claim 3)

[1528] 10. The system of claim 1, wherein the collected data is log files and resource metrics. [Explanation of symbols]

[1529] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for analyzing and learning from materials including server configuration information; a means for collecting real-time data; a means for detecting faults based on the collected data; A means for identifying the cause of the failure and generating an optimal recovery method; a means for notifying a user of the generated recovery method; means for accepting user approval; A means of implementing approved recovery methods; A system including:

2. 2. The system according to claim 1, wherein the document containing the server configuration information is a server configuration diagram or a design document.

3. The system of claim 1 , wherein the collected data is log files and resource metrics.

Images