System

Abstract

An object of a system according to an embodiment is to quickly identify the cause of a system failure and handle the system failure.SOLUTION: A system according to an embodiment includes a knowledge database learning unit, a configuration information learning unit, a design document learning unit, a visualization data identification unit, and a bulletin board data summarization unit. The knowledge-database learning unit learns a past knowledge database using the generated AI. The configuration information learning unit learns the configuration information and the environmental parameter of the system using the generated AI. The design document learning unit learns the design document and the procedure manual using the generated AI. A visualizer discriminator discriminates the visualizer using the generated AI. A bulletin board summarization part summarizes the bulletin board by using the generation AI.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] With conventional technology, there was a problem in that it took a long time to identify the cause and take action when a system failure occurred.

[0005] The system according to the embodiment aims to quickly identify the cause of a system failure and take action. [Means for solving the problem]

[0006] The system according to the embodiment includes a knowledge database learning unit, a configuration information learning unit, a design document learning unit, a visualization data identification unit, and a bulletin board data summarization unit. The knowledge database learning unit uses a generation AI to learn past knowledge databases. The configuration information learning unit uses a generation AI to learn system configuration information and environmental parameters. The design document learning unit uses a generation AI to learn design documents and procedure manuals. The visualization data identification unit uses a generation AI to identify visualization data. The bulletin board data summarization unit uses a generation AI to summarize bulletin board data. [Effects of the Invention]

[0007] The system according to the embodiment can quickly identify the cause of a system failure and take action. [Brief explanation of the drawings]

[0008] [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. DETAILED DESCRIPTION OF THE INVENTION

[0009] 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.

[0010] First, the terms used in the following description will be explained.

[0011] 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, the 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), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] 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.

[0013] 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.

[0014] 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), and Bluetooth (registered trademark).

[0015] 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."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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).

[0019] 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.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. 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 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. 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.

[0022] 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.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The support system according to the embodiment of the present invention is a system that, when a system failure occurs, quickly and efficiently identifies the cause and supports recovery work. As a result, when a system failure occurs, the support system can quickly and efficiently identify the cause and support recovery work.

[0029] The support system according to the embodiment includes a knowledge database learning unit, a configuration information learning unit, a design document learning unit, a visualization data identification unit, and a bulletin board data summarization unit. The knowledge database learning unit uses a generation AI to learn from past knowledge databases. For example, the generation AI refers to similar failure cases based on data on past failure cases and provides clues to identify the cause. The generation AI can also analyze data on past failure cases, analyze the frequency and impact of failures, and propose preventive measures. The generation AI can also automatically generate and provide real-time response procedures for when a failure occurs based on past knowledge database data. The configuration information learning unit uses the generation AI to learn system configuration information and environmental parameters. For example, the generation AI can analyze system configuration diagrams and environment setting files to help identify the location of a failure. The generation AI can also monitor fluctuations in configuration information and environmental parameters in real time and issue alerts when an abnormality is detected. The generation AI can also simulate the scope of impact when a failure occurs based on configuration information and environmental parameters and propose optimal response measures. The design document learning unit uses the generation AI to learn design documents and procedure manuals. For example, the generation AI analyzes the terminology and procedures described in the design documents and procedure manuals and provides the information necessary for disaster recovery. The generation AI can also automatically update the contents of the design documents and procedure manuals to provide the latest information. Furthermore, the generation AI can automatically generate response procedures in the event of a disaster based on the data in the design documents and procedure manuals and provide them in real time. The visualization data identification unit uses the generation AI to identify visualized data. For example, the generation AI analyzes visualized images of system monitoring screens and log data to identify the scope of the impact of a disaster. The generation AI can also identify the scope of the impact in real time based on the image identification results of the visualized data. Furthermore, the generation AI can automatically generate response procedures in the event of a disaster based on the visualized data and provide them in real time. The bulletin board data summarization unit uses the generation AI to summarize bulletin board data. For example, the generation AI analyzes time-series data from an accident response bulletin board and summarizes important information to provide it.The generation AI can also automatically generate response procedures in the event of a failure based on bulletin board data and provide them in real time. Furthermore, the generation AI can use its emotion estimation function to analyze the content of bulletin board data posts and provide a customized summary based on the user's emotions. This allows the assistance system according to the embodiment to quickly and efficiently identify the cause of a system failure and support recovery efforts. For example, the generation AI can identify the cause by referencing a past knowledge database, and identify the location of the failure by analyzing system configuration information and environmental parameters. It can also provide necessary information by referencing design documents and procedure manuals, and analyze visualized data to identify the scope of the impact. Furthermore, by providing a summary of bulletin board data, it can assist in understanding the content when joining an incident response midway.

[0030] The knowledge database learning unit can analyze the frequency and impact of failures from the knowledge database and propose preventive measures. For example, the knowledge database learning unit uses generation AI to analyze the frequency of failures from past knowledge databases and extract specific patterns. For example, if a specific system configuration or environmental parameter contributes to the occurrence of a failure, the unit identifies that pattern and proposes preventive measures. The knowledge database learning unit also evaluates the impact of failures based on past knowledge databases, and the generation AI proposes preventive measures for failures with high impact. For example, for failures with high impact, the unit proposes system redundancy and strengthened backups. The knowledge database learning unit also uses generation AI to simultaneously analyze the frequency and impact of failures from past knowledge databases and proposes the most effective preventive measures. For example, for failures with high frequency and high impact, the unit proposes system design changes or revisions to operational procedures. This makes it possible to prevent failures from occurring in the first place.

[0031] The knowledge database learning unit can automatically generate response procedures for when a failure occurs based on data in the knowledge database and provide them in real time. The knowledge database learning unit, for example, uses a generation AI to automatically generate response procedures for when a failure occurs from past knowledge databases. For example, it analyzes past failure response records and provides optimal response procedures in real time. The knowledge database learning unit also uses a generation AI to automatically generate response procedures for when a failure occurs based on data in the knowledge database and notifies the system administrator in real time. For example, it provides specific response procedures according to the type of failure and the scope of impact. The knowledge database learning unit also uses a generation AI to automatically generate response procedures for when a failure occurs from past knowledge databases and makes them available to system administrators in real time. For example, it displays response procedures step by step to support rapid response. This enables rapid response when a failure occurs.

[0032] The configuration information learning unit can monitor fluctuations in configuration information and environmental parameters in real time and issue an alert when an abnormality is detected. The configuration information learning unit, for example, uses a generation AI to build a system that monitors fluctuations in configuration information and environmental parameters in real time and issues an alert when an abnormality is detected. For example, it uses an anomaly detection algorithm to identify an abnormality. The configuration information learning unit also builds a system that monitors fluctuations in configuration information and environmental parameters in real time and issues an alert when an abnormality is detected. For example, it sets an anomaly detection threshold and issues an alert when an abnormality occurs. The configuration information learning unit also builds a system that monitors fluctuations in configuration information and environmental parameters in real time and issues an alert when an abnormality is detected using a generation AI. For example, it learns anomaly detection patterns and identifies anomalies. This enables early detection of abnormalities and rapid response.

[0033] The configuration information learning unit can simulate the scope of impact when a failure occurs based on configuration information and environmental parameters, and propose optimal countermeasures. The configuration information learning unit, for example, uses a generation AI to simulate the scope of impact when a failure occurs based on configuration information and environmental parameters, and builds a system that proposes optimal countermeasures. For example, it proposes countermeasures based on the simulation results. The configuration information learning unit also simulates the scope of impact when a failure occurs based on configuration information and environmental parameters, and builds a system that proposes optimal countermeasures. For example, it visualizes the scope of impact and proposes countermeasures. The configuration information learning unit also uses a generation AI to simulate the scope of impact when a failure occurs based on configuration information and environmental parameters, and builds a system that proposes optimal countermeasures. For example, it proposes response procedures based on the simulation results. This makes it possible to quickly propose optimal countermeasures when a failure occurs.

[0034] The configuration information learning unit can link configuration information and environmental parameters with other systems to achieve comprehensive system management. The configuration information learning unit, for example, links configuration information and environmental parameters with a security system to build a system that achieves comprehensive system management. For example, it integrates and manages security events and system configuration information. The configuration information learning unit also uses a generative AI to link configuration information and environmental parameters with a security system to achieve comprehensive system management. For example, it integrates and manages security incidents and system configuration information. The configuration information learning unit also links configuration information and environmental parameters with a security system to build a system that achieves comprehensive system management. For example, it integrates and manages security alerts and system configuration information. This makes comprehensive system management possible.

[0035] The configuration information learning unit can optimize the system based on configuration information and environmental parameters to improve performance. The configuration information learning unit, for example, uses a generative AI to optimize the system based on configuration information and environmental parameters to build a system that improves performance. For example, it proposes optimal resource allocation. The configuration information learning unit also optimizes the system based on configuration information and environmental parameters to build a system that improves performance. For example, it detects resource surpluses and shortages and proposes optimal allocation. The configuration information learning unit also uses a generative AI to optimize the system based on configuration information and environmental parameters to build a system that improves performance. For example, it implements an optimization algorithm to maximize resource utilization efficiency. This improves system performance.

[0036] The design document learning unit can automatically update the contents of design documents and procedure manuals and provide the latest information. The design document learning unit, for example, uses generation AI to build a system that automatically updates the contents of design documents and procedure manuals and provides the latest information. For example, it automatically updates them when new technologies or methods are introduced. The design document learning unit also builds a system that automatically updates the contents of design documents and procedure manuals and provides the latest information. For example, it periodically scans design documents and procedure manuals and automatically reflects changes. The design document learning unit also builds a system that automatically updates the contents of design documents and procedure manuals and provides the latest information using generation AI. For example, it updates design documents and procedure manuals based on user feedback. This makes it possible to keep the contents of design documents and procedure manuals always up to date.

[0037] The design document learning unit can automatically generate response procedures in the event of a failure based on data in design documents and procedure manuals, and provide them in real time. The design document learning unit, for example, uses generation AI to build a system that automatically generates response procedures in the event of a failure based on data in design documents and procedure manuals, and provides them in real time. For example, it analyzes the contents of design documents and procedure manuals and generates optimal response procedures. The design document learning unit also builds a system that automatically generates response procedures in the event of a failure based on data in design documents and procedure manuals, and provides them in real time. For example, it displays response procedures step by step based on the contents of procedure manuals. The design document learning unit also uses generation AI to build a system that automatically generates response procedures in the event of a failure based on data in design documents and procedure manuals, and provides them in real time. For example, it customizes response procedures based on the contents of design documents and procedure manuals. This enables rapid response when a failure occurs.

[0038] The design document learning unit can link design document and procedure manual data with other systems to support the progress of a project. For example, the design document learning unit links design document and procedure manual data with a project management system to build a system that supports the progress of a project. For example, the contents of the design document and procedure manual are automatically reflected in the project management system. The design document learning unit also uses generative AI to link design document and procedure manual data with the project management system to support the progress of a project. For example, it visualizes the progress of a project based on the contents of the design document and procedure manual. The design document learning unit also links design document and procedure manual data with the project management system to build a system that supports the progress of a project. For example, it automatically generates project tasks based on the contents of the design document and procedure manual. This makes it possible to efficiently support the progress of a project.

[0039] The design document learning unit can optimize the system based on the design document and procedure manuals to improve performance. The design document learning unit, for example, uses a generative AI to optimize the system based on the design document and procedure manuals and build a system that improves performance. For example, it analyzes the contents of the design document and procedure manuals and proposes optimal resource allocation. The design document learning unit also optimizes the system based on the design document and procedure manuals and builds a system that improves performance. For example, it detects resource surpluses and shortages based on the contents of the procedure manuals and proposes optimal allocation. The design document learning unit also uses a generative AI to optimize the system based on the design document and procedure manuals and build a system that improves performance. For example, it implements an optimization algorithm to maximize resource utilization efficiency based on the contents of the design document and procedure manuals. This improves system performance.

[0040] The visualized data identification unit can identify the extent of impact when a failure occurs in real time based on the image identification results of the visualized data. The visualized data identification unit, for example, uses a generation AI to build a system that identifies the extent of impact when a failure occurs in real time based on the image identification results of the visualized data. For example, it analyzes images of a monitoring screen to identify the extent of impact. The visualized data identification unit also builds a system that identifies the extent of impact when a failure occurs in real time based on the image identification results of the visualized data. For example, it analyzes visualized images of log data to identify the extent of impact. The visualized data identification unit also builds a system that identifies the extent of impact when a failure occurs in real time based on the image identification results of the visualized data. For example, it analyzes visualized images of a system's monitoring screen or log data to identify the extent of impact. This makes it possible to quickly identify the extent of impact when a failure occurs.

[0041] The visualized data identification unit can automatically generate response procedures when a failure occurs based on the visualized data and provide them in real time. The visualized data identification unit, for example, uses a generation AI to build a system that automatically generates response procedures when a failure occurs based on the visualized data and provides them in real time. For example, it analyzes images of a monitoring screen and generates optimal response procedures. The visualized data identification unit also builds a system that automatically generates response procedures when a failure occurs based on the visualized data and provides them in real time. For example, it analyzes visualized images of log data and displays response procedures step by step. The visualized data identification unit also builds a system that automatically generates response procedures when a failure occurs based on the visualized data and provides them in real time. For example, it analyzes visualized images of a monitoring screen or log data and customizes response procedures. This enables a rapid response when a failure occurs.

[0042] The visualized data identification unit can link the visualized data with other systems to achieve comprehensive system management. The visualized data identification unit, for example, links the visualized data with a monitoring system to build a system that achieves comprehensive system management. For example, it analyzes images on a monitoring screen and integrates them into the monitoring system. The visualized data identification unit also uses generative AI to link the visualized data with the monitoring system to achieve comprehensive system management. For example, it analyzes images on a monitoring screen and reflects the results in the monitoring system in real time. The visualized data identification unit also links the visualized data with the monitoring system to build a system that achieves comprehensive system management. For example, it analyzes images on a monitoring screen and integrates them into the monitoring system for management. This makes comprehensive system management possible.

[0043] The visualization data identification unit can optimize the system based on the visualization data and improve performance. The visualization data identification unit, for example, uses a generation AI to optimize the system based on the visualization data and build a system that improves performance. For example, it analyzes images of a monitoring screen and proposes optimal resource allocation. The visualization data identification unit also optimizes the system based on the visualization data and builds a system that improves performance. For example, it analyzes visualized images of log data, detects resource surpluses and shortages, and proposes optimal allocation. The visualization data identification unit also uses a generation AI to optimize the system based on the visualization data and build a system that improves performance. For example, it analyzes visualized images of a monitoring screen or log data and implements an optimization algorithm to maximize resource utilization efficiency. This improves system performance.

[0044] The bulletin board data summarization unit can analyze time-series data from the accident countermeasure bulletin board and summarize important information in real time. The bulletin board data summarization unit, for example, uses a generation AI to analyze time-series data from the accident countermeasure bulletin board and build a system that summarizes important information in real time. For example, it analyzes the content of bulletin board posts and extracts and summarizes important information. The bulletin board data summarization unit also builds a system that summarizes important information in real time based on the time-series data from the accident countermeasure bulletin board. For example, it analyzes the content of bulletin board posts and summarizes important information step by step. The bulletin board data summarization unit also uses a generation AI to analyze time-series data from the accident countermeasure bulletin board and build a system that summarizes important information in real time. For example, it analyzes the content of bulletin board posts and customizes and summarizes important information. This allows important information to be grasped quickly.

[0045] The bulletin board data summarization unit can automatically generate response procedures in the event of a failure based on data from the accident response bulletin board and provide them in real time. The bulletin board data summarization unit, for example, uses generation AI to build a system that automatically generates response procedures in the event of a failure based on data from the accident response bulletin board and provides them in real time. For example, it analyzes the content of bulletin board posts and generates optimal response procedures. The bulletin board data summarization unit also builds a system that automatically generates response procedures in the event of a failure based on data from the accident response bulletin board and provides them in real time. For example, it displays response procedures step by step based on the content of bulletin board posts. The bulletin board data summarization unit also uses generation AI to build a system that automatically generates response procedures in the event of a failure based on data from the accident response bulletin board and provides them in real time. For example, it customizes the response procedures based on the content of bulletin board posts. This enables rapid response when a failure occurs.

[0046] The bulletin board data summarization unit can link data from the accident countermeasure bulletin board with other systems to achieve comprehensive information management. The bulletin board data summarization unit, for example, links data from the accident countermeasure bulletin board with a knowledge management system to build a system that achieves comprehensive information management. For example, it automatically reflects the content of bulletin board posts in the knowledge management system. The bulletin board data summarization unit also uses generation AI to link data from the accident countermeasure bulletin board with the knowledge management system to achieve comprehensive information management. For example, it reflects the content of bulletin board posts in real time in the knowledge management system. The bulletin board data summarization unit also links data from the accident countermeasure bulletin board with the knowledge management system to build a system that achieves comprehensive information management. For example, it integrates and manages the content of bulletin board posts in the knowledge management system. This makes comprehensive information management possible.

[0047] The bulletin board data summarizing unit can optimize the system based on the data from the accident countermeasure bulletin board and improve performance. The bulletin board data summarizing unit, for example, uses a generation AI to optimize the system based on the data from the accident countermeasure bulletin board and build a system that improves performance. For example, it analyzes the content of bulletin board posts and proposes optimal resource allocation. The bulletin board data summarizing unit also optimizes the system based on the data from the accident countermeasure bulletin board and builds a system that improves performance. For example, it detects resource surpluses or shortages based on the content of bulletin board posts and proposes optimal allocation. The bulletin board data summarizing unit also uses a generation AI to optimize the system based on the data from the accident countermeasure bulletin board and builds a system that improves performance. For example, it implements an optimization algorithm to maximize resource utilization efficiency based on the content of bulletin board posts. This improves system performance.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The support system can further include a voice recognition unit. The voice recognition unit can analyze the system administrator's voice instructions in real time and provide appropriate response procedures. For example, when the system administrator explains the situation of a failure verbally, the voice recognition unit analyzes the content and provides information from a related knowledge database. The voice recognition unit can also automatically generate and provide response procedures in real time based on the system administrator's voice instructions. Furthermore, the voice recognition unit can analyze system configuration information and environmental parameters based on the system administrator's voice instructions and identify the location of the failure. This allows the system administrator to quickly obtain response procedures using only voice, without using their hands.

[0050] The support system can further include a predictive analysis unit. The predictive analysis unit can predict the risk of future failures based on past failure data. For example, the predictive analysis unit can analyze past failure patterns and evaluate the likelihood that specific system configurations or environmental parameters will contribute to future failures. The predictive analysis unit can also monitor system usage and load status in real time and issue alerts if the risk of a failure increases. Furthermore, the predictive analysis unit can suggest changes to the system configuration or revisions to operational procedures based on the prediction results. This makes it possible to prevent failures from occurring.

[0051] The support system can further include a user interface unit. The user interface unit can provide an interface that can be operated intuitively by the system administrator. For example, the user interface unit can provide a function that allows the system administrator to display and edit system configuration information using drag-and-drop operations. The user interface unit can also visualize the system status in real time and display a visual alert when an abnormality occurs. Furthermore, the user interface unit can provide a customizable dashboard that allows the system administrator to quickly access the information they need. This allows the system administrator to manage the system efficiently.

[0052] The support system can further include an automatic repair unit. The automatic repair unit can automatically perform repair work when a system failure occurs. For example, the automatic repair unit can identify the cause of the failure based on system configuration information and environmental parameters, and automatically start repair work. The automatic repair unit can also refer to past failure response procedures and automatically generate the optimal repair procedure. Furthermore, the automatic repair unit can monitor the progress of the repair work in real time and notify the system administrator as necessary. This allows for rapid recovery from system failures.

[0053] The support system can further include a data backup unit. The data backup unit periodically backs up important system data, enabling rapid recovery in the event of a failure. For example, the data backup unit periodically backs up system configuration information and environmental parameters, and performs recovery operations using the latest backup data in the event of a failure. The data backup unit can also periodically check the integrity of the backup data and issue an alert if a problem occurs. Furthermore, the data backup unit can store the backup data in cloud storage, safely protecting the data even in the event of a disaster. This ensures that the system's data is protected and enables rapid recovery.

[0054] The support system can further include a remote access unit. The remote access unit enables a system administrator to access the system from a remote location and respond to failures. For example, the remote access unit uses a secure communication protocol to enable the system administrator to access the system from home or while on a business trip. The remote access unit can also display system configuration information and environmental parameters in real time, enabling a quick response when a failure occurs. Furthermore, the remote access unit can provide an interface that enables the system administrator to change system settings and perform repair work from a remote location. This allows the system administrator to respond quickly regardless of location.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The knowledge database learning unit uses the generation AI to learn from past knowledge databases. For example, the generation AI can refer to similar failure cases based on data on past failure cases and provide clues to identify the cause. The generation AI can also analyze data on past failure cases, analyze the frequency and impact of failures, and propose preventive measures. Furthermore, the generation AI can automatically generate response procedures for when a failure occurs based on data from the past knowledge database and provide them in real time. Step 2: The configuration information learning unit uses the generation AI to learn the system's configuration information and environmental parameters. For example, the generation AI analyzes the system's configuration diagram and environmental setting files to help identify the location of a failure. The generation AI can also monitor fluctuations in the configuration information and environmental parameters in real time and issue an alert when an abnormality is detected. Furthermore, the generation AI can simulate the scope of impact when a failure occurs based on the configuration information and environmental parameters and propose optimal countermeasures. Step 3: The design document learning unit uses the generation AI to learn the design documents and procedure manuals. For example, the generation AI analyzes the technical terms and procedures described in the design documents and procedure manuals and provides the information necessary for disaster recovery. The generation AI can also automatically update the contents of the design documents and procedure manuals to provide the latest information. Furthermore, the generation AI can automatically generate response procedures in the event of a disaster based on the data in the design documents and procedure manuals and provide them in real time. Step 4: The visualization data identification unit uses the generation AI to identify the visualization data. For example, the generation AI analyzes visualized images of the system's monitoring screen or log data to identify the extent of the impact of a failure. The generation AI can also identify the extent of the impact in real time when a failure occurs, based on the image identification results of the visualization data. Furthermore, the generation AI can automatically generate response procedures in the event of a failure based on the visualization data and provide them in real time. Step 5: The bulletin board data summarization unit uses the generation AI to summarize the bulletin board data. For example, the generation AI analyzes the time-series data of an accident response bulletin board and summarizes and provides important information. The generation AI can also automatically generate response procedures in the event of an incident based on the bulletin board data and provide them in real time. Furthermore, the generation AI can use an emotion estimation function to analyze the content of bulletin board posts and provide a customized summary based on the user's emotions.

[0057] (Example 2) The support system according to the embodiment of the present invention is a system that, when a system failure occurs, quickly and efficiently identifies the cause and supports recovery work. As a result, when a system failure occurs, the support system can quickly and efficiently identify the cause and support recovery work.

[0058] The support system according to the embodiment includes a knowledge database learning unit, a configuration information learning unit, a design document learning unit, a visualization data identification unit, and a bulletin board data summarization unit. The knowledge database learning unit uses a generation AI to learn from past knowledge databases. For example, the generation AI refers to similar failure cases based on data on past failure cases and provides clues to identify the cause. The generation AI can also analyze data on past failure cases, analyze the frequency and impact of failures, and propose preventive measures. The generation AI can also automatically generate and provide real-time response procedures for when a failure occurs based on past knowledge database data. The configuration information learning unit uses the generation AI to learn system configuration information and environmental parameters. For example, the generation AI can analyze system configuration diagrams and environment setting files to help identify the location of a failure. The generation AI can also monitor fluctuations in configuration information and environmental parameters in real time and issue alerts when an abnormality is detected. The generation AI can also simulate the scope of impact when a failure occurs based on configuration information and environmental parameters and propose optimal response measures. The design document learning unit uses the generation AI to learn design documents and procedure manuals. For example, the generation AI analyzes the terminology and procedures described in the design documents and procedure manuals and provides the information necessary for disaster recovery. The generation AI can also automatically update the contents of the design documents and procedure manuals to provide the latest information. Furthermore, the generation AI can automatically generate response procedures in the event of a disaster based on the data in the design documents and procedure manuals and provide them in real time. The visualization data identification unit uses the generation AI to identify visualized data. For example, the generation AI analyzes visualized images of system monitoring screens and log data to identify the scope of the impact of a disaster. The generation AI can also identify the scope of the impact in real time based on the image identification results of the visualized data. Furthermore, the generation AI can automatically generate response procedures in the event of a disaster based on the visualized data and provide them in real time. The bulletin board data summarization unit uses the generation AI to summarize bulletin board data. For example, the generation AI analyzes time-series data from an accident response bulletin board and summarizes important information to provide it.The generation AI can also automatically generate response procedures in the event of a failure based on bulletin board data and provide them in real time. Furthermore, the generation AI can use its emotion estimation function to analyze the content of bulletin board data posts and provide a customized summary based on the user's emotions. This allows the assistance system according to the embodiment to quickly and efficiently identify the cause of a system failure and support recovery efforts. For example, the generation AI can identify the cause by referencing a past knowledge database, and identify the location of the failure by analyzing system configuration information and environmental parameters. It can also provide necessary information by referencing design documents and procedure manuals, and analyze visualized data to identify the scope of the impact. Furthermore, by providing a summary of bulletin board data, it can assist in understanding the content when joining an incident response midway.

[0059] The knowledge database learning unit can analyze the frequency and impact of failures from the knowledge database and propose preventive measures. For example, the knowledge database learning unit uses generation AI to analyze the frequency of failures from past knowledge databases and extract specific patterns. For example, if a specific system configuration or environmental parameter contributes to the occurrence of a failure, the unit identifies that pattern and proposes preventive measures. The knowledge database learning unit also evaluates the impact of failures based on past knowledge databases, and the generation AI proposes preventive measures for failures with high impact. For example, for failures with high impact, the unit proposes system redundancy and strengthened backups. The knowledge database learning unit also uses generation AI to simultaneously analyze the frequency and impact of failures from past knowledge databases and proposes the most effective preventive measures. For example, for failures with high frequency and high impact, the unit proposes system design changes or revisions to operational procedures. This makes it possible to prevent failures from occurring in the first place.

[0060] The knowledge database learning unit can automatically generate response procedures for when a failure occurs based on data in the knowledge database and provide them in real time. The knowledge database learning unit, for example, uses a generation AI to automatically generate response procedures for when a failure occurs from past knowledge databases. For example, it analyzes past failure response records and provides optimal response procedures in real time. The knowledge database learning unit also uses a generation AI to automatically generate response procedures for when a failure occurs based on data in the knowledge database and notifies the system administrator in real time. For example, it provides specific response procedures according to the type of failure and the scope of impact. The knowledge database learning unit also uses a generation AI to automatically generate response procedures for when a failure occurs from past knowledge databases and makes them available to system administrators in real time. For example, it displays response procedures step by step to support rapid response. This enables rapid response when a failure occurs.

[0061] The knowledge database learning unit can use the emotion estimation function to analyze the emotions of staff members when responding to past outages and propose response procedures that are less stressful. For example, the knowledge database learning unit uses the emotion estimation function to analyze emotional data of staff members when responding to past outages, and the generation AI proposes response procedures that are less stressful. For example, emotion scores are extracted from past response records to identify procedures that are less stressful. The knowledge database learning unit also uses the generation AI to automatically generate response procedures that are less stressful based on the emotional data of staff members when responding to past outages. For example, procedures with low emotion scores are prioritized for proposal. The knowledge database learning unit also uses the emotion estimation function to analyze emotional data of staff members when responding to past outages, and the generation AI proposes response procedures that are less stressful. For example, procedures with high emotion scores are avoided and procedures with low emotion scores are selected. This reduces stress on staff members and enables efficient response.

[0062] The configuration information learning unit can monitor fluctuations in configuration information and environmental parameters in real time and issue an alert when an abnormality is detected. The configuration information learning unit, for example, uses a generation AI to build a system that monitors fluctuations in configuration information and environmental parameters in real time and issues an alert when an abnormality is detected. For example, it uses an anomaly detection algorithm to identify an abnormality. The configuration information learning unit also builds a system that monitors fluctuations in configuration information and environmental parameters in real time and issues an alert when an abnormality is detected. For example, it sets an anomaly detection threshold and issues an alert when an abnormality occurs. The configuration information learning unit also builds a system that monitors fluctuations in configuration information and environmental parameters in real time and issues an alert when an abnormality is detected using a generation AI. For example, it learns anomaly detection patterns and identifies anomalies. This enables early detection of abnormalities and rapid response.

[0063] The configuration information learning unit can simulate the scope of impact when a failure occurs based on configuration information and environmental parameters, and propose optimal countermeasures. The configuration information learning unit, for example, uses a generation AI to simulate the scope of impact when a failure occurs based on configuration information and environmental parameters, and builds a system that proposes optimal countermeasures. For example, it proposes countermeasures based on the simulation results. The configuration information learning unit also simulates the scope of impact when a failure occurs based on configuration information and environmental parameters, and builds a system that proposes optimal countermeasures. For example, it visualizes the scope of impact and proposes countermeasures. The configuration information learning unit also uses a generation AI to simulate the scope of impact when a failure occurs based on configuration information and environmental parameters, and builds a system that proposes optimal countermeasures. For example, it proposes response procedures based on the simulation results. This makes it possible to quickly propose optimal countermeasures when a failure occurs.

[0064] The configuration information learning unit can use the emotion estimation function to consider the emotional state of the system administrator and provide a low-stress troubleshooting procedure. The configuration information learning unit, for example, uses the emotion estimation function to build a system that considers the emotional state of the system administrator and provides a low-stress troubleshooting procedure. For example, it proposes an optimal troubleshooting procedure based on an emotion score. The configuration information learning unit also uses a generative AI to build a system that considers the emotional state of the system administrator and provides a low-stress troubleshooting procedure. For example, it preferentially proposes procedures with a low emotion score. The configuration information learning unit also uses the emotion estimation function to consider the emotional state of the system administrator and build a system that provides a low-stress troubleshooting procedure. For example, it avoids procedures with a high emotion score and selects an optimal procedure. This reduces stress for the system administrator and enables efficient response.

[0065] The configuration information learning unit can link configuration information and environmental parameters with other systems to achieve comprehensive system management. The configuration information learning unit, for example, links configuration information and environmental parameters with a security system to build a system that achieves comprehensive system management. For example, it integrates and manages security events and system configuration information. The configuration information learning unit also uses a generative AI to link configuration information and environmental parameters with a security system to achieve comprehensive system management. For example, it integrates and manages security incidents and system configuration information. The configuration information learning unit also links configuration information and environmental parameters with a security system to build a system that achieves comprehensive system management. For example, it integrates and manages security alerts and system configuration information. This makes comprehensive system management possible.

[0066] The configuration information learning unit can optimize the system based on configuration information and environmental parameters to improve performance. The configuration information learning unit, for example, uses a generative AI to optimize the system based on configuration information and environmental parameters to build a system that improves performance. For example, it proposes optimal resource allocation. The configuration information learning unit also optimizes the system based on configuration information and environmental parameters to build a system that improves performance. For example, it detects resource surpluses and shortages and proposes optimal allocation. The configuration information learning unit also uses a generative AI to optimize the system based on configuration information and environmental parameters to build a system that improves performance. For example, it implements an optimization algorithm to maximize resource utilization efficiency. This improves system performance.

[0067] The configuration information learning unit can use the emotion estimation function to provide a management screen customized according to the emotions of the system administrator. The configuration information learning unit, for example, uses the emotion estimation function to build a system that provides a management screen customized according to the emotions of the system administrator. For example, the layout and color tone of the management screen are adjusted based on the emotion score. The configuration information learning unit also uses a generation AI to provide a management screen customized according to the emotions of the system administrator. For example, a simple screen is displayed when the emotion score is high, and detailed information is displayed when the emotion score is low. The configuration information learning unit also uses the emotion estimation function to build a system that provides a management screen customized according to the emotions of the system administrator. For example, the way alerts are displayed is changed depending on the emotion score. This enables efficient management by providing a management screen that corresponds to the emotions of the system administrator.

[0068] The design document learning unit can automatically update the contents of design documents and procedure manuals and provide the latest information. The design document learning unit, for example, uses generation AI to build a system that automatically updates the contents of design documents and procedure manuals and provides the latest information. For example, it automatically updates them when new technologies or methods are introduced. The design document learning unit also builds a system that automatically updates the contents of design documents and procedure manuals and provides the latest information. For example, it periodically scans design documents and procedure manuals and automatically reflects changes. The design document learning unit also builds a system that automatically updates the contents of design documents and procedure manuals and provides the latest information using generation AI. For example, it updates design documents and procedure manuals based on user feedback. This makes it possible to keep the contents of design documents and procedure manuals always up to date.

[0069] The design document learning unit can automatically generate response procedures in the event of a failure based on data in design documents and procedure manuals, and provide them in real time. The design document learning unit, for example, uses generation AI to build a system that automatically generates response procedures in the event of a failure based on data in design documents and procedure manuals, and provides them in real time. For example, it analyzes the contents of design documents and procedure manuals and generates optimal response procedures. The design document learning unit also builds a system that automatically generates response procedures in the event of a failure based on data in design documents and procedure manuals, and provides them in real time. For example, it displays response procedures step by step based on the contents of procedure manuals. The design document learning unit also uses generation AI to build a system that automatically generates response procedures in the event of a failure based on data in design documents and procedure manuals, and provides them in real time. For example, it customizes response procedures based on the contents of design documents and procedure manuals. This enables rapid response when a failure occurs.

[0070] The design document learning unit can use the emotion estimation function to analyze the contents of design documents and procedure manuals and convert them into a format that is easy for users to understand. For example, the design document learning unit uses the emotion estimation function to build a system that analyzes the contents of design documents and procedure manuals and converts them into a format that is easy for users to understand. For example, it adjusts the layout of design documents and procedure manuals based on the emotion score. The design document learning unit also uses a generative AI to analyze the contents of design documents and procedure manuals and convert them into a format that is easy for users to understand. For example, it highlights parts with high emotion scores and simplifies parts with low emotion scores. The design document learning unit also uses the emotion estimation function to build a system that analyzes the contents of design documents and procedure manuals and converts them into a format that is easy for users to understand. For example, it reconstructs the contents of design documents and procedure manuals according to the emotion score. This makes it easier for users to understand the design documents and procedure manuals.

[0071] The design document learning unit can link design document and procedure manual data with other systems to support the progress of a project. For example, the design document learning unit links design document and procedure manual data with a project management system to build a system that supports the progress of a project. For example, the contents of the design document and procedure manual are automatically reflected in the project management system. The design document learning unit also uses generative AI to link design document and procedure manual data with the project management system to support the progress of a project. For example, it visualizes the progress of a project based on the contents of the design document and procedure manual. The design document learning unit also links design document and procedure manual data with the project management system to build a system that supports the progress of a project. For example, it automatically generates project tasks based on the contents of the design document and procedure manual. This makes it possible to efficiently support the progress of a project.

[0072] The design document learning unit can optimize the system based on the design document and procedure manuals to improve performance. The design document learning unit, for example, uses a generative AI to optimize the system based on the design document and procedure manuals and build a system that improves performance. For example, it analyzes the contents of the design document and procedure manuals and proposes optimal resource allocation. The design document learning unit also optimizes the system based on the design document and procedure manuals and builds a system that improves performance. For example, it detects resource surpluses and shortages based on the contents of the procedure manuals and proposes optimal allocation. The design document learning unit also uses a generative AI to optimize the system based on the design document and procedure manuals and build a system that improves performance. For example, it implements an optimization algorithm to maximize resource utilization efficiency based on the contents of the design document and procedure manuals. This improves system performance.

[0073] The design document learning unit can use the emotion estimation function to provide customized procedures that correspond to the user's emotions based on the contents of the design document or procedure manual. The design document learning unit, for example, uses the emotion estimation function to build a system that provides customized procedures that correspond to the user's emotions based on the contents of the design document or procedure manual. For example, it proposes an optimal procedure based on an emotion score. The design document learning unit also uses a generative AI to provide customized procedures that correspond to the user's emotions based on the contents of the design document or procedure manual. For example, it preferentially proposes procedures with a high emotion score. The design document learning unit also uses the emotion estimation function to build a system that provides customized procedures that correspond to the user's emotions based on the contents of the design document or procedure manual. For example, it avoids procedures with a low emotion score and selects an optimal procedure. This enables efficient response by providing procedures that correspond to the user's emotions.

[0074] The visualized data identification unit can identify the extent of impact when a failure occurs in real time based on the image identification results of the visualized data. The visualized data identification unit, for example, uses a generation AI to build a system that identifies the extent of impact when a failure occurs in real time based on the image identification results of the visualized data. For example, it analyzes images of a monitoring screen to identify the extent of impact. The visualized data identification unit also builds a system that identifies the extent of impact when a failure occurs in real time based on the image identification results of the visualized data. For example, it analyzes visualized images of log data to identify the extent of impact. The visualized data identification unit also builds a system that identifies the extent of impact when a failure occurs in real time based on the image identification results of the visualized data. For example, it analyzes visualized images of a system's monitoring screen or log data to identify the extent of impact. This makes it possible to quickly identify the extent of impact when a failure occurs.

[0075] The visualized data identification unit can automatically generate response procedures when a failure occurs based on the visualized data and provide them in real time. The visualized data identification unit, for example, uses a generation AI to build a system that automatically generates response procedures when a failure occurs based on the visualized data and provides them in real time. For example, it analyzes images of a monitoring screen and generates optimal response procedures. The visualized data identification unit also builds a system that automatically generates response procedures when a failure occurs based on the visualized data and provides them in real time. For example, it analyzes visualized images of log data and displays response procedures step by step. The visualized data identification unit also builds a system that automatically generates response procedures when a failure occurs based on the visualized data and provides them in real time. For example, it analyzes visualized images of a monitoring screen or log data and customizes response procedures. This enables a rapid response when a failure occurs.

[0076] The visualized data identification unit can use the emotion estimation function to provide a response procedure customized according to the user's emotion based on the analysis results of the visualized data. The visualized data identification unit, for example, uses the emotion estimation function to build a system that provides a response procedure customized according to the user's emotion based on the analysis results of the visualized data. For example, the optimal response procedure is proposed based on the emotion score. The visualized data identification unit also uses a generative AI to provide a response procedure customized according to the user's emotion based on the analysis results of the visualized data. For example, procedures with a high emotion score are preferentially proposed. The visualized data identification unit also uses the emotion estimation function to build a system that provides a response procedure customized according to the user's emotion based on the analysis results of the visualized data. For example, procedures with a low emotion score are avoided and an optimal procedure is selected. This enables efficient responses by providing a response procedure according to the user's emotion.

[0077] The visualized data identification unit can link the visualized data with other systems to achieve comprehensive system management. The visualized data identification unit, for example, links the visualized data with a monitoring system to build a system that achieves comprehensive system management. For example, it analyzes images on a monitoring screen and integrates them into the monitoring system. The visualized data identification unit also uses generative AI to link the visualized data with the monitoring system to achieve comprehensive system management. For example, it analyzes images on a monitoring screen and reflects the results in the monitoring system in real time. The visualized data identification unit also links the visualized data with the monitoring system to build a system that achieves comprehensive system management. For example, it analyzes images on a monitoring screen and integrates them into the monitoring system for management. This makes comprehensive system management possible.

[0078] The visualization data identification unit can optimize the system based on the visualization data and improve performance. The visualization data identification unit, for example, uses a generation AI to optimize the system based on the visualization data and build a system that improves performance. For example, it analyzes images of a monitoring screen and proposes optimal resource allocation. The visualization data identification unit also optimizes the system based on the visualization data and builds a system that improves performance. For example, it analyzes visualized images of log data, detects resource surpluses and shortages, and proposes optimal allocation. The visualization data identification unit also uses a generation AI to optimize the system based on the visualization data and build a system that improves performance. For example, it analyzes visualized images of a monitoring screen or log data and implements an optimization algorithm to maximize resource utilization efficiency. This improves system performance.

[0079] The visualized data identification unit can use the emotion estimation function to provide a management screen customized according to the user's emotion based on the analysis results of the visualized data. The visualized data identification unit, for example, uses the emotion estimation function to build a system that provides a management screen customized according to the user's emotion based on the analysis results of the visualized data. For example, the layout and color tone of the management screen are adjusted based on the emotion score. The visualized data identification unit also uses a generation AI to provide a management screen customized according to the user's emotion based on the analysis results of the visualized data. For example, a simple screen is displayed when the emotion score is high, and detailed information is displayed when the emotion score is low. The visualized data identification unit also uses the emotion estimation function to build a system that provides a management screen customized according to the user's emotion based on the analysis results of the visualized data. For example, the method of displaying alerts is changed depending on the emotion score. This enables efficient management by providing a management screen that corresponds to the user's emotion.

[0080] The bulletin board data summarization unit can analyze time-series data from the accident countermeasure bulletin board and summarize important information in real time. The bulletin board data summarization unit, for example, uses a generation AI to analyze time-series data from the accident countermeasure bulletin board and build a system that summarizes important information in real time. For example, it analyzes the content of bulletin board posts and extracts and summarizes important information. The bulletin board data summarization unit also builds a system that summarizes important information in real time based on the time-series data from the accident countermeasure bulletin board. For example, it analyzes the content of bulletin board posts and summarizes important information step by step. The bulletin board data summarization unit also uses a generation AI to analyze time-series data from the accident countermeasure bulletin board and build a system that summarizes important information in real time. For example, it analyzes the content of bulletin board posts and customizes and summarizes important information. This allows important information to be grasped quickly.

[0081] The bulletin board data summarization unit can automatically generate response procedures in the event of a failure based on data from the accident response bulletin board and provide them in real time. The bulletin board data summarization unit, for example, uses generation AI to build a system that automatically generates response procedures in the event of a failure based on data from the accident response bulletin board and provides them in real time. For example, it analyzes the content of bulletin board posts and generates optimal response procedures. The bulletin board data summarization unit also builds a system that automatically generates response procedures in the event of a failure based on data from the accident response bulletin board and provides them in real time. For example, it displays response procedures step by step based on the content of bulletin board posts. The bulletin board data summarization unit also uses generation AI to build a system that automatically generates response procedures in the event of a failure based on data from the accident response bulletin board and provides them in real time. For example, it customizes the response procedures based on the content of bulletin board posts. This enables rapid response when a failure occurs.

[0082] The message board data summarization unit can use the emotion estimation function to analyze the content posted on the accident countermeasure message board and provide a customized summary according to the user's emotion. For example, the message board data summarization unit uses the emotion estimation function to analyze the content posted on the accident countermeasure message board and build a system that provides a customized summary according to the user's emotion. For example, it proposes an optimal summary based on the emotion score. The message board data summarization unit also uses a generation AI to analyze the content posted on the accident countermeasure message board and provide a customized summary according to the user's emotion. For example, it highlights parts with high emotion scores and simplifies parts with low emotion. The message board data summarization unit also uses the emotion estimation function to analyze the content posted on the accident countermeasure message board and build a system that provides a customized summary according to the user's emotion. For example, it reconstructs the posted content according to the emotion score. This enables efficient information understanding by providing a summary according to the user's emotion.

[0083] The bulletin board data summarization unit can link data from the accident countermeasure bulletin board with other systems to achieve comprehensive information management. The bulletin board data summarization unit, for example, links data from the accident countermeasure bulletin board with a knowledge management system to build a system that achieves comprehensive information management. For example, it automatically reflects the content of bulletin board posts in the knowledge management system. The bulletin board data summarization unit also uses generation AI to link data from the accident countermeasure bulletin board with the knowledge management system to achieve comprehensive information management. For example, it reflects the content of bulletin board posts in real time in the knowledge management system. The bulletin board data summarization unit also links data from the accident countermeasure bulletin board with the knowledge management system to build a system that achieves comprehensive information management. For example, it integrates and manages the content of bulletin board posts in the knowledge management system. This makes comprehensive information management possible.

[0084] The bulletin board data summarizing unit can optimize the system based on the data from the accident countermeasure bulletin board and improve performance. The bulletin board data summarizing unit, for example, uses a generation AI to optimize the system based on the data from the accident countermeasure bulletin board and build a system that improves performance. For example, it analyzes the content of bulletin board posts and proposes optimal resource allocation. The bulletin board data summarizing unit also optimizes the system based on the data from the accident countermeasure bulletin board and builds a system that improves performance. For example, it detects resource surpluses or shortages based on the content of bulletin board posts and proposes optimal allocation. The bulletin board data summarizing unit also uses a generation AI to optimize the system based on the data from the accident countermeasure bulletin board and builds a system that improves performance. For example, it implements an optimization algorithm to maximize resource utilization efficiency based on the content of bulletin board posts. This improves system performance.

[0085] The message board data summarization unit can use the emotion estimation function to provide customized response procedures according to the user's emotions based on the content posted on the accident response message board. The message board data summarization unit, for example, uses the emotion estimation function to build a system that provides customized response procedures according to the user's emotions based on the content posted on the accident response message board. For example, it proposes an optimal response procedure based on an emotion score. The message board data summarization unit also uses a generation AI to provide customized response procedures according to the user's emotions based on the content posted on the accident response message board. For example, it prioritizes proposing procedures with a high emotion score. The message board data summarization unit also uses the emotion estimation function to build a system that provides customized response procedures according to the user's emotions based on the content posted on the accident response message board. For example, it avoids procedures with a low emotion score and selects an optimal procedure. This enables efficient response by providing response procedures according to the user's emotions.

[0086] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0087] The support system can further include a voice recognition unit. The voice recognition unit can analyze the system administrator's voice instructions in real time and provide appropriate response procedures. For example, when the system administrator explains the situation of a failure verbally, the voice recognition unit analyzes the content and provides information from a related knowledge database. The voice recognition unit can also automatically generate and provide response procedures in real time based on the system administrator's voice instructions. Furthermore, the voice recognition unit can analyze system configuration information and environmental parameters based on the system administrator's voice instructions and identify the location of the failure. This allows the system administrator to quickly obtain response procedures using only voice, without using their hands.

[0088] The support system can further include a predictive analysis unit. The predictive analysis unit can predict the risk of future failures based on past failure data. For example, the predictive analysis unit can analyze past failure patterns and evaluate the likelihood that specific system configurations or environmental parameters will contribute to future failures. The predictive analysis unit can also monitor system usage and load status in real time and issue alerts if the risk of a failure increases. Furthermore, the predictive analysis unit can suggest changes to the system configuration or revisions to operational procedures based on the prediction results. This makes it possible to prevent failures from occurring.

[0089] The support system can further include a user interface unit. The user interface unit can provide an interface that can be operated intuitively by the system administrator. For example, the user interface unit can provide a function that allows the system administrator to display and edit system configuration information using drag-and-drop operations. The user interface unit can also visualize the system status in real time and display a visual alert when an abnormality occurs. Furthermore, the user interface unit can provide a customizable dashboard that allows the system administrator to quickly access the information they need. This allows the system administrator to manage the system efficiently.

[0090] The support system can further use an emotion estimation function to provide alert notifications that take into account the emotional state of the system administrator. For example, if the system administrator is feeling stressed, the emotion estimation function can be used to reduce the alert notification volume. Alternatively, if the system administrator is relaxed, the emotion estimation function can be used to provide detailed alert information. Furthermore, the emotion estimation function can be used to adjust the priority of alerts according to the emotional state of the system administrator. This reduces the stress of the system administrator and enables efficient response.

[0091] The support system can further include an automatic repair unit. The automatic repair unit can automatically perform repair work when a system failure occurs. For example, the automatic repair unit can identify the cause of the failure based on system configuration information and environmental parameters, and automatically start repair work. The automatic repair unit can also refer to past failure response procedures and automatically generate the optimal repair procedure. Furthermore, the automatic repair unit can monitor the progress of the repair work in real time and notify the system administrator as necessary. This allows for rapid recovery from system failures.

[0092] The support system can further use the emotion estimation function to provide a training program according to the emotional state of the system administrator. For example, if the system administrator is feeling stressed, the emotion estimation function can be used to provide a training program for relaxation. Also, if the system administrator wants to improve their concentration, the emotion estimation function can be used to provide a training program for improving their concentration. Furthermore, the emotion estimation function can be used to customize the content of the training program according to the emotional state of the system administrator. This can improve the performance of the system administrator.

[0093] The support system can further include a data backup unit. The data backup unit periodically backs up important system data, enabling rapid recovery in the event of a failure. For example, the data backup unit periodically backs up system configuration information and environmental parameters, and performs recovery operations using the latest backup data in the event of a failure. The data backup unit can also periodically check the integrity of the backup data and issue an alert if a problem occurs. Furthermore, the data backup unit can store the backup data in cloud storage, safely protecting the data even in the event of a disaster. This ensures that the system's data is protected and enables rapid recovery.

[0094] The support system can further use the emotion estimation function to provide feedback according to the emotional state of the system administrator. For example, if the emotion estimation function is used, an encouraging message can be displayed when the system administrator is feeling stressed. Alternatively, if the emotion estimation function is used, specific advice for moving on to the next step can be provided when the system administrator is relaxed. Furthermore, the emotion estimation function can also be used to adjust the content and timing of the feedback according to the emotional state of the system administrator. This helps maintain the motivation of the system administrator and enables efficient response.

[0095] The support system can further include a remote access unit. The remote access unit enables a system administrator to access the system from a remote location and respond to failures. For example, the remote access unit uses a secure communication protocol to enable the system administrator to access the system from home or while on a business trip. The remote access unit can also display system configuration information and environmental parameters in real time, enabling a quick response when a failure occurs. Furthermore, the remote access unit can provide an interface that enables the system administrator to change system settings and perform repair work from a remote location. This allows the system administrator to respond quickly regardless of location.

[0096] The support system can further use the emotion estimation function to provide customized notification settings according to the emotional state of the system administrator. For example, the emotion estimation function can be used to reduce the frequency of notifications when the system administrator is stressed. Alternatively, the emotion estimation function can be used to provide more detailed notifications when the system administrator is relaxed. Furthermore, the emotion estimation function can be used to customize the content and format of notifications according to the emotional state of the system administrator. This reduces the stress of the system administrator and enables efficient response.

[0097] The processing flow of the second embodiment will be briefly explained below.

[0098] Step 1: The knowledge database learning unit uses the generation AI to learn from past knowledge databases. For example, the generation AI can refer to similar failure cases based on data on past failure cases and provide clues to identify the cause. The generation AI can also analyze data on past failure cases, analyze the frequency and impact of failures, and propose preventive measures. Furthermore, the generation AI can automatically generate response procedures for when a failure occurs based on data from the past knowledge database and provide them in real time. Step 2: The configuration information learning unit uses the generation AI to learn the system's configuration information and environmental parameters. For example, the generation AI analyzes the system's configuration diagram and environmental setting files to help identify the location of a failure. The generation AI can also monitor fluctuations in the configuration information and environmental parameters in real time and issue an alert when an abnormality is detected. Furthermore, the generation AI can simulate the scope of impact when a failure occurs based on the configuration information and environmental parameters and propose optimal countermeasures. Step 3: The design document learning unit uses the generation AI to learn the design documents and procedure manuals. For example, the generation AI analyzes the technical terms and procedures described in the design documents and procedure manuals and provides the information necessary for disaster recovery. The generation AI can also automatically update the contents of the design documents and procedure manuals to provide the latest information. Furthermore, the generation AI can automatically generate response procedures in the event of a disaster based on the data in the design documents and procedure manuals and provide them in real time. Step 4: The visualization data identification unit uses the generation AI to identify the visualization data. For example, the generation AI analyzes visualized images of the system's monitoring screen or log data to identify the extent of the impact of a failure. The generation AI can also identify the extent of the impact in real time when a failure occurs, based on the image identification results of the visualization data. Furthermore, the generation AI can automatically generate response procedures in the event of a failure based on the visualization data and provide them in real time. Step 5: The bulletin board data summarization unit uses the generation AI to summarize the bulletin board data. For example, the generation AI analyzes the time-series data of an accident response bulletin board and summarizes and provides important information. The generation AI can also automatically generate response procedures in the event of an incident based on the bulletin board data and provide them in real time. Furthermore, the generation AI can use an emotion estimation function to analyze the content of bulletin board posts and provide a customized summary based on the user's emotions.

[0099] 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.

[0100] 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> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). 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 speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. 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. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0101] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0102] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0103] 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.

[0104] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0105] 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.

[0106] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0107] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0112] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0113] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0114] 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.

[0115] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0116] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0117] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0118] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0119] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0120] 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.

[0121] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0122] 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 user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0127] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0128] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0129] 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.

[0130] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0131] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0132] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0133] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0134] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and 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 and / or a LAN.

[0135] 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.

[0136] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0137] 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 image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0138] 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.

[0139] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the 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.

[0140] 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.

[0141] 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.

[0142] 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. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0143] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0144] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0145] 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.

[0146] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. 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. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0147] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0148] 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.

[0149] FIG. 9 illustrates 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 behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions 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.

[0150] 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.

[0151] 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).

[0152] 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 expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, 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 expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0153] 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."

[0154] 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.

[0155] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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. A processor also includes 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.

[0160] The hardware resource that executes the specific process 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 process may be a single processor.

[0161] 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.

[0162] 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.

[0163] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0164] 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.

[0165] 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. [Explanation of symbols]

[0166] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. Using generative AI, a knowledge database learning unit that learns from a past knowledge database; a configuration information learning unit that learns system configuration information and environmental parameters; A design document study group where students study design documents and procedure manuals; a visualization data identification unit that identifies visualization data; a bulletin board data summarizing unit that summarizes bulletin board data; A system characterized by:

2. The knowledge database learning unit Analyze the frequency and impact of failures from the knowledge database and propose preventative measures 2. The system of claim 1.

3. The knowledge database learning unit Based on the data in the knowledge database, response procedures are automatically generated in the event of a failure and provided in real time.

2. The system of claim 1.

4. The knowledge database learning unit Analyze the emotions of staff members when dealing with past incidents and propose procedures to minimize stress 2. The system of claim 1.

5. The configuration information learning unit The system monitors the fluctuations of the configuration information and environmental parameters in real time and issues an alert when an abnormality is detected.

2. The system of claim 1.

6. The configuration information learning unit Based on the configuration information and environmental parameters, we simulate the extent of the impact when a failure occurs and propose optimal countermeasures.

2. The system of claim 1.

Images