System

Abstract

An object of a system according to an embodiment is to automate failure handling and periodic updating in a server operation in an on-premises environment.SOLUTION: A system according to an embodiment includes a learning unit, a failure identification unit, a restoration presentation unit, an approval unit, an execution unit, and an update unit. The learning unit learns a configuration diagram and a design document of the server. The failure identification unit identifies a failure location when a failure occurs in the server. The restoration presentation unit presents a restoration method based on the failure location specified by the failure specifying unit. The approval unit allows the operator to confirm and approve the recovery method presented by the recovery presentation unit. The execution unit automatically executes the recovery method approved by the approval unit. The update unit creates a periodic update procedure and automatically executes the update after the operator confirms the update procedure.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, troubleshooting and regular update processes for on-premise server operations are performed manually, which is inefficient and prone to human error.

[0005] The system according to the embodiment aims to automate troubleshooting and periodic updates in server operations in an on-premise environment. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning unit, a fault identification unit, a recovery presentation unit, an approval unit, an execution unit, and an update unit. The learning unit learns the configuration diagram and design document of the server. The fault identification unit identifies the location of the fault when a failure occurs in the server. The recovery presentation unit presents a recovery method based on the location of the fault identified by the fault identification unit. The approval unit allows an operator to check and approve the recovery method presented by the recovery presentation unit. The execution unit automatically executes the recovery method approved by the approval unit. The update unit creates a periodic update procedure and automatically executes the update after the operator has checked it. [Effects of the Invention]

[0007] The system according to the embodiment can automate troubleshooting and periodic updates when operating servers in an on-premise environment. [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 automated operation system according to an embodiment of the present invention is a system that learns server configuration diagrams and design documents, identifies the location of a failure when a failure occurs, presents a recovery method, and automatically recovers the failure with the operator's approval. As a result, the automated operation system realizes automation of server operations in an on-premises environment, enabling rapid response when a failure occurs and automation of regular updates.

[0029] An automated operation system according to an embodiment includes a learning unit, a fault identification unit, a recovery presentation unit, an approval unit, an execution unit, and an update unit. The learning unit studies the server's configuration diagram and design documents. For example, the learning unit learns the server's network configuration, hardware layout, software version information, and the like. The learning unit also uses a generation AI (for example, a text generation AI or a multimodal generation AI) to understand the server's configuration and design. The fault identification unit identifies the location of a fault when a failure occurs in the server. For example, the fault identification unit analyzes log files and system status to identify the cause of the failure. The failure identification unit also uses the generation AI to identify the location of the failure based on the log files and system status at the time of the failure. The recovery presentation unit presents a recovery method based on the fault location identified by the fault identification unit. For example, the recovery presentation unit presents a procedure manual or guidelines to provide the recovery method to the operator. The recovery presentation unit also uses the generation AI to present the recovery method based on the fault location. The approval unit allows the operator to review and approve the recovery method presented by the recovery presentation unit. For example, the approval unit checks the recovery procedure presented by the operator and checks whether there are any problems with the procedure. The execution unit automatically executes the recovery method approved by the approval unit. For example, the execution unit restarts the server or changes its settings. The execution unit also uses a generation AI to automatically execute recovery in accordance with the approved recovery procedure. The update unit creates periodic update procedures and automatically executes updates after the operator has confirmed them. For example, the update unit creates update procedures for server software and firmware, which the operator confirms. As a result, the automated operation system according to the embodiment realizes automation of server operations in an on-premises environment, enabling rapid response when a failure occurs and automation of periodic updates.

[0030] The learning unit can learn from past failure histories and operation logs in addition to server configuration diagrams and design documents, enabling more accurate failure prediction. For example, the learning unit trains the AI ​​on past failure histories and operation logs in addition to server configuration diagrams and design documents. This allows the AI ​​to understand failure patterns and improve its ability to predict future failures. For example, it can learn from failures caused by specific hardware configurations or software versions and issue a warning when a similar configuration is used again. The learning unit also analyzes server operation logs and trains the AI ​​to distinguish between normal and abnormal operating conditions. For example, it can detect abnormal fluctuations in CPU usage or memory usage to detect early signs of a failure. The learning unit also uses past failure history to allow the AI ​​to learn the frequency and scope of failures and build a prediction model. For example, it can predict failures that occur during specific time periods or due to specific operations and take preventative measures. This improves the accuracy of failure predictions by learning from past failure histories and operation logs.

[0031] The learning unit converts server configuration diagrams and design documents into 3D models, enabling learning in a visually easy-to-understand format. For example, the learning unit converts server configuration diagrams and design documents into 3D models and trains the AI. This makes it easier for the AI ​​to visually understand physical layouts and connections. For example, the layout of each device in a server rack and the cable connections are represented in a 3D model. The learning unit also uses the 3D model to visually simulate server configurations and designs and trains the AI. For example, it simulates the impact of adding or changing a server on other devices and proposes optimal layouts. The learning unit also uses the 3D model to improve the AI's ability to identify physical faults in the server. For example, it visually displays cable breaks and equipment failures on the 3D model, supporting rapid response. As a result, using 3D models makes it easier to visually understand server configurations and designs.

[0032] The learning unit not only studies server configuration diagrams and design documents, but also related industry standards and best practices, allowing the AI ​​to acquire more comprehensive knowledge. For example, the learning unit has the AI ​​learn related industry standards and best practices in addition to server configuration diagrams and design documents. This enables the AI ​​to understand the latest technological trends and operational methods and propose optimal operational procedures. For example, the learning unit has the AI ​​learn frameworks such as ITIL and COBIT. The learning unit also optimizes server operations based on industry standards and best practices. For example, it proposes best practices for security measures and performance improvement. The learning unit also has the AI ​​learn related industry standards and best practices, allowing the AI ​​to provide comprehensive advice to operators. For example, it proposes optimal methods for server configuration and operational procedures. In this way, learning industry standards and best practices allows the AI ​​to acquire more comprehensive knowledge.

[0033] The learning unit can translate server configuration diagrams and design documents into different languages ​​to enable them to be compatible with international operating environments. The learning unit, for example, translates server configuration diagrams and design documents into different languages ​​to enable them to be compatible with international operating environments. For example, it supports multiple languages ​​such as English, Japanese, and Chinese. The learning unit also uses AI to propose multilingual operating procedures based on server configuration diagrams and design documents translated into different languages. For example, it provides procedure manuals that operators can understand in their native language. The learning unit also uses AI to provide advice suitable for international operating environments based on the translated server configuration diagrams and design documents. For example, it proposes operating procedures that are compatible with different languages ​​and cultures. In this way, by translating into different languages, it is possible to support international operating environments.

[0034] The fault identification unit monitors the status of the entire system in real time when a failure occurs, and not only identifies the location of the failure, but also proposes preventive measures. For example, when a failure occurs, the AI ​​in the fault identification unit monitors the status of the entire system in real time and identifies the location of the failure. For example, it monitors network traffic and CPU usage and detects anomalies. The fault identification unit not only identifies the location of the failure, but also proposes preventive measures. For example, it proposes replacing specific hardware or updating software. The fault identification unit also monitors the status of the entire system in real time and not only identifies the location of the failure, but also proposes preventive measures automatically. For example, it automatically starts a backup when an abnormality is detected. This makes it possible to monitor the status of the entire system in real time and propose preventive measures.

[0035] The fault identification unit can present multiple different recovery scenarios depending on the type of failure, allowing the operator to select the optimal method. For example, the AI ​​in the fault identification unit presents multiple recovery scenarios depending on the type of failure. For example, it proposes different recovery procedures in the case of hardware failure and software errors. The fault identification unit also presents the advantages and disadvantages of each scenario so that the operator can select the optimal recovery method. For example, it compares recovery time and risk. The fault identification unit also presents multiple recovery scenarios, and the AI ​​automatically performs recovery based on the scenario selected by the operator. For example, it restarts the server according to the procedure selected by the operator. This makes it possible to select the optimal recovery scenario depending on the type of failure.

[0036] The fault identification unit automatically coordinates with other systems and services when a failure occurs, and is able to present a comprehensive recovery method. For example, when a failure occurs, the AI ​​in the fault identification unit automatically coordinates with other systems and services to present a comprehensive recovery method. For example, when a network failure occurs, the status of related servers and devices is checked. The fault identification unit also proposes a comprehensive recovery method through coordination with other systems and services. For example, it coordinates with cloud services and external monitoring systems to present the optimal recovery procedure. The fault identification unit also automatically coordinates with other systems and services when a failure occurs, and executes a comprehensive recovery method. For example, it automatically activates a backup system when an abnormality is detected. This makes it possible to present a comprehensive recovery method through coordination with other systems and services.

[0037] The fault identification unit can guide the operator through recovery procedures via voice when a fault occurs, enabling the operator to respond even in situations where visual confirmation is difficult. For example, when a fault occurs, the AI ​​in the fault identification unit guides the operator through recovery procedures via voice. For example, the system enables the operator to perform recovery work by following voice instructions even in situations where the operator cannot use their hands. The fault identification unit also uses voice guidance to enable the operator to understand the recovery procedures even in situations where visual confirmation is difficult. For example, it supports work in dark or noisy environments. The fault identification unit also provides recovery procedures via voice in real time when a fault occurs, enabling the operator to respond quickly. For example, it issues voice instructions for each step and notifies the operator when to proceed to the next step. In this way, the use of voice guidance makes it possible to respond even in situations where visual confirmation is difficult.

[0038] The recovery presentation unit can present similar past cases for reference when confirming a recovery method. For example, when confirming a recovery method, the recovery presentation unit uses AI to present similar past cases. For example, it displays response procedures and results when a similar failure occurs. The recovery presentation unit also provides information that operators can refer to based on similar past cases. For example, it presents details of successful and unsuccessful recovery procedures. The recovery presentation unit also uses AI to analyze similar past cases and propose the optimal recovery method. For example, it selects the most effective procedure based on past data. In this way, operators can refer to similar past cases.

[0039] When confirming recovery procedures, the recovery presentation unit can perform a risk assessment of the procedures and highlight high-risk parts to the operator. For example, when confirming recovery procedures, the recovery presentation unit uses AI to perform a risk assessment of the procedures. For example, it quantifies the risk level of each procedure and presents it to the operator. The recovery presentation unit also highlights high-risk parts to make clear the points that the operator should pay attention to. For example, it displays high-risk procedures in red. The recovery presentation unit also suggests risk mitigation measures to the operator based on the AI's risk assessment of the procedures. For example, it presents alternative procedures or additional confirmation procedures. In this way, by highlighting high-risk parts, it becomes clear that the operator should pay attention to them.

[0040] The recovery suggestion unit can collect feedback from other operators when checking recovery procedures and suggest improvements to the procedures. For example, when checking recovery procedures, the recovery suggestion unit uses AI to collect feedback from other operators. For example, it collects opinions and evaluations from operators who have used the same procedures in the past. The recovery suggestion unit also uses AI to suggest improvements to the procedures based on feedback from other operators. For example, it suggests simplifying the procedures or adding additional checking steps. The recovery suggestion unit also uses AI to analyze feedback from other operators and suggest optimal recovery procedures. For example, it adjusts the priority of procedures based on the feedback. This makes it possible to suggest improvements to the procedures based on feedback from other operators.

[0041] The recovery presentation unit, when confirming recovery procedures, can provide the procedures in video format, making them easier to understand visually. For example, when confirming recovery procedures, the recovery presentation unit uses AI to provide the procedures in video format. For example, the operations for each step can be shown in video, allowing the operator to understand visually. The recovery presentation unit also uses video procedures to enable the operator to intuitively understand the procedures. For example, the actual operation screen or device operation can be shown in video. The recovery presentation unit also uses AI to provide the procedures in video format, making them easier to understand visually. For example, the operations for each step can be shown in video, allowing the operator to understand visually. As a result, providing the procedures in video format makes them easier to understand visually.

[0042] When automatic recovery is being performed, the execution unit monitors the recovery process in real time, and can respond immediately if an abnormality occurs. For example, when automatic recovery is being performed, AI in the execution unit monitors the recovery process in real time. For example, it monitors each step of the recovery procedure and issues an alert if an abnormality occurs. Furthermore, if an abnormality occurs during the recovery process, the AI ​​responds immediately. For example, it automatically starts a backup when an abnormality is detected. Furthermore, the execution unit monitors the recovery process in real time, and can respond immediately if an abnormality occurs. For example, it automatically starts a backup when an abnormality is detected. This allows the recovery process to be monitored in real time, and can respond immediately if an abnormality occurs.

[0043] After performing automatic recovery, the execution unit can report the recovery results in detail and provide feedback to the operator. For example, after performing automatic recovery, the AI ​​in the execution unit reports the recovery results in detail. For example, it reports the results and required time for each step of the recovery procedure. In addition, in the execution unit, the AI ​​provides feedback to the operator based on the recovery results. For example, it suggests improvements to the recovery procedure and measures to be taken next time. In addition, in the execution unit, the AI ​​reports the recovery results in detail so that the operator can understand the recovery process. For example, it reports the results and required time for each step of the recovery procedure. This makes it possible to report the recovery results in detail and provide feedback to the operator.

[0044] The execution unit can achieve comprehensive recovery by coordinating with other systems and services when automatic recovery is performed. In the execution unit, for example, AI coordinates with other systems and services when automatic recovery is performed. For example, when a network failure occurs, the status of related servers and devices is checked. The execution unit also achieves comprehensive recovery through collaboration with other systems and services. For example, it coordinates with cloud services and external monitoring systems to present optimal recovery procedures. The execution unit also achieves comprehensive recovery by coordinating with other systems and services when automatic recovery is performed. For example, it automatically activates a backup system when an abnormality is detected. This makes it possible to achieve comprehensive recovery through collaboration with other systems and services.

[0045] When automatic recovery is performed, the execution unit can report progress to the operator via voice, allowing the operator to respond even in situations where visual confirmation is difficult. For example, when automatic recovery is performed, the execution unit has the AI ​​report progress via voice to the operator. For example, the progress status of each step of the recovery procedure is notified via voice. The execution unit also uses voice reports to enable the operator to understand the recovery procedure even in situations where visual confirmation is difficult. For example, this supports work in dark places or noisy environments. Furthermore, when automatic recovery is performed, the AI ​​reports progress via voice in real time, allowing the operator to respond quickly. For example, voice instructions are given for each step to notify the operator when to proceed to the next step. In this way, by reporting progress via voice, it becomes possible to respond even in situations where visual confirmation is difficult.

[0046] When creating an update procedure, the update unit can refer to past update history and propose the optimal procedure. For example, when creating an update procedure, the update unit uses AI to refer to past update history and propose the optimal procedure. For example, a new procedure is created based on past successful update procedures. The update unit also uses AI to propose improvements to the update procedure based on past update history. For example, it analyzes past failure cases and proposes procedures to avoid risks. The update unit also uses AI to refer to past update history and automatically generate the optimal procedure. For example, it selects the most effective procedure based on past data. This makes it possible to propose the optimal procedure by referring to past update history.

[0047] When creating update procedures, the update unit can perform a risk assessment of the procedures and highlight high-risk parts to the operator. For example, when creating update procedures, the update unit uses AI to perform a risk assessment of the procedures. For example, it quantifies the risk level of each procedure and presents it to the operator. The update unit also highlights high-risk parts to make it clear that operators need to pay attention to them. For example, it displays high-risk procedures in red. The update unit also suggests risk mitigation measures to the operator based on the AI's risk assessment of the procedures. For example, it presents alternative procedures or additional confirmation procedures. In this way, by highlighting high-risk parts, it is possible to make clear that operators need to pay attention to them.

[0048] When checking the update procedure, the update unit can collect feedback from other operators and suggest improvements to the procedure. For example, when checking the update procedure, the AI ​​in the update unit collects feedback from other operators. For example, it collects opinions and evaluations from operators who have used the same procedure in the past. The update unit also suggests improvements to the procedure based on feedback from other operators. For example, it suggests simplifying the procedure or adding additional confirmation steps. The update unit also analyzes feedback from other operators and suggests the optimal update procedure. For example, it adjusts the priority of the procedures based on the feedback. This makes it possible to suggest improvements to the procedure based on feedback from other operators.

[0049] When confirming the update procedure, the update unit can provide the procedure in video format, making it easier to understand visually. When confirming the update procedure, for example, the update unit has AI provide the procedure in video format. For example, the operation for each step can be shown in video, allowing the operator to understand visually. The update unit also uses video-format procedures to enable the operator to intuitively understand the procedure. For example, the actual operation screen or operation of the device can be shown in video. The update unit also has AI provide the procedure in video format, making it easier for the operator to visually confirm. For example, the operation for each step can be shown in video, allowing the operator to understand visually. As a result, providing the procedure in video format makes it easier to understand visually.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The automated operation system can further include a prediction unit. The prediction unit predicts the possibility of future failures based on server operation data. For example, it analyzes past failure history and operation logs and detects specific patterns to predict future failures. The prediction unit also uses AI to analyze server performance data in real time and detect signs of abnormalities early. For example, it detects abnormal fluctuations in CPU usage or memory usage and issues a warning to the operator. The prediction unit also suggests steps to take in advance to address predicted failures. For example, by replacing specific hardware or updating software in advance, it is possible to prevent failures from occurring. Thus, by including a prediction unit, future failures can be predicted and countermeasures can be taken in advance.

[0052] The automated operation system can further include a user feedback collection unit. The user feedback collection unit collects feedback from operators and uses it to improve the system. For example, it collects opinions and evaluations about the recovery procedures and operations used by operators. The user feedback collection unit also uses the AI ​​to suggest improvements to the system based on the collected feedback. For example, it may suggest simplifying procedures or improving the interface. Furthermore, the user feedback collection unit updates the system to make it easier for operators to use, based on the collected feedback. For example, it may add new functions that reflect the opinions of operators. In this way, by including a user feedback collection unit, it is possible to collect feedback from operators and use it to improve the system.

[0053] The automated operation system can further include a training department. The training department trains operators on how to use the system and procedures for responding to failures. For example, it provides online courses for learning basic system operations and recovery procedures. The training department also uses a simulation environment to allow operators to practice responding to actual failures. For example, it reproduces failures in a virtual environment and allows operators to practice recovery procedures. The training department also provides customized training programs according to the skill level of the operators. For example, it provides basic courses for beginners and advanced courses for advanced users. In this way, having a training department allows operators to effectively learn how to use the system and procedures for responding to failures.

[0054] An automated operation system can further be equipped with an anomaly detection unit. The anomaly detection unit monitors the server's operational data in real time and detects anomalies. For example, it detects abnormal fluctuations in network traffic or CPU usage. The anomaly detection unit also issues an alert to the operator when it detects an anomaly. For example, it notifies the operator immediately when an anomaly occurs, encouraging a prompt response. Furthermore, the anomaly detection unit identifies the cause of the anomaly and proposes specific countermeasures to the operator. For example, it proposes replacing specific hardware or updating software. Thus, by having an anomaly detection unit, it is possible to monitor the server's operational data in real time, detect anomalies, and respond promptly.

[0055] The automated operation system can further include a data backup unit. The data backup unit periodically backs up server data to prevent data loss in the event of a failure. For example, it automatically performs data backups every night. The data backup unit also checks the consistency of the backup data and notifies the operator if a problem occurs. For example, it issues an alert if the backup data contains an error. Furthermore, the data backup unit provides procedures for quickly restoring data in the event of a failure. For example, it presents the operator with procedures for restoring data from backup data. Thus, having a data backup unit enables regular data backups and quick data restoration in the event of a failure.

[0056] An automated operation system can further be equipped with a security monitoring unit. The security monitoring unit monitors the security status of the server in real time and detects abnormal access or unauthorized operations. For example, it detects unauthorized access from a specific IP address. The security monitoring unit also issues an alert to the operator when it detects an abnormality. For example, it immediately notifies the operator when unauthorized access occurs, encouraging a prompt response. The security monitoring unit also proposes specific countermeasures for detected abnormalities. For example, it proposes changing firewall settings or resetting passwords. Thus, by having a security monitoring unit, it is possible to monitor the security status of the server in real time, detect abnormalities, and respond promptly.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The learning unit studies the server's configuration diagram and design documents. For example, the learning unit learns the server's network configuration, hardware layout, software version information, etc. The learning unit also uses generative AI (e.g., text generation AI or multimodal generation AI) to understand the server's configuration and design. Step 2: The fault identification unit identifies the location of the failure when a server failure occurs. For example, the fault identification unit analyzes log files and system status to identify the cause of the failure. The fault identification unit also uses a generation AI to identify the location of the failure based on the log files and system status at the time of the failure. Step 3: The recovery presentation unit presents a recovery method based on the fault location identified by the fault identification unit. For example, the recovery presentation unit presents a procedure manual or guidelines to provide the operator with a recovery method. The recovery presentation unit also uses a generation AI to present a recovery method based on the fault location. Step 4: In the approval unit, the operator checks and approves the recovery method presented by the recovery presentation unit. For example, the approval unit checks the presented recovery procedure and checks whether there are any problems with the procedure. Step 5: The execution unit automatically executes the recovery method approved by the approval unit. For example, the execution unit restarts the server or changes its settings. The execution unit also uses the generation AI to automatically execute recovery according to the approved recovery procedure. Step 6: The update unit creates a regular update procedure and automatically executes the update after the administrator has confirmed it. For example, the update unit creates a server software or firmware update procedure, which the administrator then confirms.

[0059] (Example 2) The automated operation system according to an embodiment of the present invention is a system that learns server configuration diagrams and design documents, identifies the location of a failure when a failure occurs, presents a recovery method, and automatically recovers the failure with the operator's approval. As a result, the automated operation system realizes automation of server operations in an on-premises environment, enabling rapid response when a failure occurs and automation of regular updates.

[0060] An automated operation system according to an embodiment includes a learning unit, a fault identification unit, a recovery presentation unit, an approval unit, an execution unit, and an update unit. The learning unit studies the server's configuration diagram and design documents. For example, the learning unit learns the server's network configuration, hardware layout, software version information, and the like. The learning unit also uses a generation AI (for example, a text generation AI or a multimodal generation AI) to understand the server's configuration and design. The fault identification unit identifies the location of a fault when a failure occurs in the server. For example, the fault identification unit analyzes log files and system status to identify the cause of the failure. The failure identification unit also uses the generation AI to identify the location of the failure based on the log files and system status at the time of the failure. The recovery presentation unit presents a recovery method based on the fault location identified by the fault identification unit. For example, the recovery presentation unit presents a procedure manual or guidelines to provide the recovery method to the operator. The recovery presentation unit also uses the generation AI to present the recovery method based on the fault location. The approval unit allows the operator to review and approve the recovery method presented by the recovery presentation unit. For example, the approval unit checks the recovery procedure presented by the operator and checks whether there are any problems with the procedure. The execution unit automatically executes the recovery method approved by the approval unit. For example, the execution unit restarts the server or changes its settings. The execution unit also uses a generation AI to automatically execute recovery in accordance with the approved recovery procedure. The update unit creates periodic update procedures and automatically executes updates after the operator has confirmed them. For example, the update unit creates update procedures for server software and firmware, which the operator confirms. As a result, the automated operation system according to the embodiment realizes automation of server operations in an on-premises environment, enabling rapid response when a failure occurs and automation of periodic updates.

[0061] The learning unit can learn from past failure histories and operation logs in addition to server configuration diagrams and design documents, enabling more accurate failure prediction. For example, the learning unit trains the AI ​​on past failure histories and operation logs in addition to server configuration diagrams and design documents. This allows the AI ​​to understand failure patterns and improve its ability to predict future failures. For example, it can learn from failures caused by specific hardware configurations or software versions and issue a warning when a similar configuration is used again. The learning unit also analyzes server operation logs and trains the AI ​​to distinguish between normal and abnormal operating conditions. For example, it can detect abnormal fluctuations in CPU usage or memory usage to detect early signs of a failure. The learning unit also uses past failure history to allow the AI ​​to learn the frequency and scope of failures and build a prediction model. For example, it can predict failures that occur during specific time periods or due to specific operations and take preventative measures. This improves the accuracy of failure predictions by learning from past failure histories and operation logs.

[0062] The learning unit converts server configuration diagrams and design documents into 3D models, enabling learning in a visually easy-to-understand format. For example, the learning unit converts server configuration diagrams and design documents into 3D models and trains the AI. This makes it easier for the AI ​​to visually understand physical layouts and connections. For example, the layout of each device in a server rack and the cable connections are represented in a 3D model. The learning unit also uses the 3D model to visually simulate server configurations and designs and trains the AI. For example, it simulates the impact of adding or changing a server on other devices and proposes optimal layouts. The learning unit also uses the 3D model to improve the AI's ability to identify physical faults in the server. For example, it visually displays cable breaks and equipment failures on the 3D model, supporting rapid response. As a result, using 3D models makes it easier to visually understand server configurations and designs.

[0063] The learning unit uses the emotion estimation function to learn what emotions operators have felt in the past when responding to problems, and is able to propose less stressful operating procedures. For example, the learning unit uses the emotion estimation function to learn what emotions operators had when responding to problems in the past. For example, it identifies procedures and operations that caused stress to the operator and suggests areas for improvement. The learning unit also uses AI to propose less stressful operating procedures based on the operator's emotional data. For example, it designs procedures and interfaces that allow operators to work in a relaxed manner. The learning unit also uses the emotion estimation function to analyze what emotions operators have felt in the past, and automatically generates less stressful operating procedures. For example, it prioritizes proposing procedures that the operator feels positive about. This makes it possible to propose less stressful operating procedures based on the operator's emotional data.

[0064] The learning unit not only studies server configuration diagrams and design documents, but also related industry standards and best practices, allowing the AI ​​to acquire more comprehensive knowledge. For example, the learning unit has the AI ​​learn related industry standards and best practices in addition to server configuration diagrams and design documents. This enables the AI ​​to understand the latest technological trends and operational methods and propose optimal operational procedures. For example, the learning unit has the AI ​​learn frameworks such as ITIL and COBIT. The learning unit also optimizes server operations based on industry standards and best practices. For example, it proposes best practices for security measures and performance improvement. The learning unit also has the AI ​​learn related industry standards and best practices, allowing the AI ​​to provide comprehensive advice to operators. For example, it proposes optimal methods for server configuration and operational procedures. In this way, learning industry standards and best practices allows the AI ​​to acquire more comprehensive knowledge.

[0065] The learning unit can translate server configuration diagrams and design documents into different languages ​​to enable them to be compatible with international operating environments. The learning unit, for example, translates server configuration diagrams and design documents into different languages ​​to enable them to be compatible with international operating environments. For example, it supports multiple languages ​​such as English, Japanese, and Chinese. The learning unit also uses AI to propose multilingual operating procedures based on server configuration diagrams and design documents translated into different languages. For example, it provides procedure manuals that operators can understand in their native language. The learning unit also uses AI to provide advice suitable for international operating environments based on the translated server configuration diagrams and design documents. For example, it proposes operating procedures that are compatible with different languages ​​and cultures. In this way, by translating into different languages, it is possible to support international operating environments.

[0066] The learning unit uses the emotion estimation function to analyze the emotions felt by the administrator when reviewing learning materials and can suggest a format for the materials that is easy to understand. The learning unit, for example, uses the emotion estimation function to analyze the emotions felt by the administrator when reviewing learning materials. For example, it identifies parts that cause stress to the administrator and suggests areas for improvement. The learning unit also uses the administrator's emotion data to suggest a format for materials that is easy for the AI ​​to understand. For example, it designs a layout and format for materials that allows the administrator to study in a relaxed manner. The learning unit also uses the emotion estimation function to monitor the emotions felt by the administrator when reviewing learning materials in real time and automatically generates a format for materials that are easy to understand. For example, it prioritizes providing materials that the administrator feels positive about. This makes it possible to suggest a format for materials that are easy to understand based on the administrator's emotion data.

[0067] The fault identification unit monitors the status of the entire system in real time when a failure occurs, and not only identifies the location of the failure, but also proposes preventive measures. For example, when a failure occurs, the AI ​​in the fault identification unit monitors the status of the entire system in real time and identifies the location of the failure. For example, it monitors network traffic and CPU usage and detects anomalies. The fault identification unit not only identifies the location of the failure, but also proposes preventive measures. For example, it proposes replacing specific hardware or updating software. The fault identification unit also monitors the status of the entire system in real time and not only identifies the location of the failure, but also proposes preventive measures automatically. For example, it automatically starts a backup when an abnormality is detected. This makes it possible to monitor the status of the entire system in real time and propose preventive measures.

[0068] The fault identification unit can present multiple different recovery scenarios depending on the type of failure, allowing the operator to select the optimal method. For example, the AI ​​in the fault identification unit presents multiple recovery scenarios depending on the type of failure. For example, it proposes different recovery procedures in the case of hardware failure and software errors. The fault identification unit also presents the advantages and disadvantages of each scenario so that the operator can select the optimal recovery method. For example, it compares recovery time and risk. The fault identification unit also presents multiple recovery scenarios, and the AI ​​automatically performs recovery based on the scenario selected by the operator. For example, it restarts the server according to the procedure selected by the operator. This makes it possible to select the optimal recovery scenario depending on the type of failure.

[0069] The fault identification unit uses the emotion estimation function to analyze the emotions that operators had when responding to faults in the past, and can propose a less stressful recovery method. The fault identification unit, for example, uses the emotion estimation function to analyze the emotions that operators had when responding to faults in the past. For example, it identifies procedures and operations that caused stress to the operator and suggests areas for improvement. The fault identification unit also uses AI to propose a less stressful recovery method based on the operator's emotion data. For example, it designs procedures and interfaces that allow the operator to work in a relaxed manner. The fault identification unit also uses the emotion estimation function to analyze the emotions that operators had when responding to faults in the past, and automatically generates a less stressful recovery method. For example, it prioritizes proposing procedures that the operator feels positive about. This makes it possible to propose a less stressful recovery method based on the operator's emotion data.

[0070] The fault identification unit automatically coordinates with other systems and services when a failure occurs, and is able to present a comprehensive recovery method. For example, when a failure occurs, the AI ​​in the fault identification unit automatically coordinates with other systems and services to present a comprehensive recovery method. For example, when a network failure occurs, the status of related servers and devices is checked. The fault identification unit also proposes a comprehensive recovery method through coordination with other systems and services. For example, it coordinates with cloud services and external monitoring systems to present the optimal recovery procedure. The fault identification unit also automatically coordinates with other systems and services when a failure occurs, and executes a comprehensive recovery method. For example, it automatically activates a backup system when an abnormality is detected. This makes it possible to present a comprehensive recovery method through coordination with other systems and services.

[0071] The fault identification unit can guide the operator through recovery procedures via voice when a fault occurs, enabling the operator to respond even in situations where visual confirmation is difficult. For example, when a fault occurs, the AI ​​in the fault identification unit guides the operator through recovery procedures via voice. For example, the system enables the operator to perform recovery work by following voice instructions even in situations where the operator cannot use their hands. The fault identification unit also uses voice guidance to enable the operator to understand the recovery procedures even in situations where visual confirmation is difficult. For example, it supports work in dark or noisy environments. The fault identification unit also provides recovery procedures via voice in real time when a fault occurs, enabling the operator to respond quickly. For example, it issues voice instructions for each step and notifies the operator when to proceed to the next step. In this way, the use of voice guidance makes it possible to respond even in situations where visual confirmation is difficult.

[0072] The fault identification unit uses the emotion estimation function to monitor in real time the stress felt by operators while responding to faults and can suggest breaks at appropriate times. The fault identification unit, for example, uses the emotion estimation function to monitor in real time the stress felt by operators while responding to faults. For example, it analyzes the operator's facial expressions and voice to measure stress levels. Furthermore, when the operator's stress level rises, the AI ​​in the fault identification unit suggests a break at an appropriate time. For example, it issues an alert urging the operator to take a break if a certain stress level is exceeded. Furthermore, the fault identification unit uses the emotion estimation function to suggest ways to relax when the operator feels stressed. For example, it issues instructions for deep breathing and stretching. This makes it possible to monitor the operator's stress in real time and suggest breaks at appropriate times.

[0073] The recovery presentation unit can present similar past cases for reference when confirming a recovery method. For example, when confirming a recovery method, the recovery presentation unit uses AI to present similar past cases. For example, it displays response procedures and results when a similar failure occurs. The recovery presentation unit also provides information that operators can refer to based on similar past cases. For example, it presents details of successful and unsuccessful recovery procedures. The recovery presentation unit also uses AI to analyze similar past cases and propose the optimal recovery method. For example, it selects the most effective procedure based on past data. In this way, operators can refer to similar past cases.

[0074] When confirming recovery procedures, the recovery presentation unit can perform a risk assessment of the procedures and highlight high-risk parts to the operator. For example, when confirming recovery procedures, the recovery presentation unit uses AI to perform a risk assessment of the procedures. For example, it quantifies the risk level of each procedure and presents it to the operator. The recovery presentation unit also highlights high-risk parts to make clear the points that the operator should pay attention to. For example, it displays high-risk procedures in red. The recovery presentation unit also suggests risk mitigation measures to the operator based on the AI's risk assessment of the procedures. For example, it presents alternative procedures or additional confirmation procedures. In this way, by highlighting high-risk parts, it becomes clear that the operator should pay attention to them.

[0075] The recovery presentation unit uses the emotion estimation function to analyze the emotions of operators when they confirm recovery procedures, and can automatically generate easy-to-understand procedure manuals. The recovery presentation unit, for example, uses the emotion estimation function to analyze the emotions of operators when they confirm recovery procedures. For example, it identifies parts that cause stress to operators and suggests areas for improvement. The recovery presentation unit also uses AI to automatically generate easy-to-understand procedure manuals based on the operator's emotion data. For example, it designs a layout and format for the procedure manual that allows operators to work in a relaxed manner. The recovery presentation unit also uses the emotion estimation function to monitor the emotions of operators when they confirm recovery procedures in real time, and automatically generate easy-to-understand procedure manuals. For example, it prioritizes providing procedure manuals that the operator has positive emotions about. This makes it possible to automatically generate easy-to-understand procedure manuals based on the operator's emotion data.

[0076] The recovery suggestion unit can collect feedback from other operators when checking recovery procedures and suggest improvements to the procedures. For example, when checking recovery procedures, the recovery suggestion unit uses AI to collect feedback from other operators. For example, it collects opinions and evaluations from operators who have used the same procedures in the past. The recovery suggestion unit also uses AI to suggest improvements to the procedures based on feedback from other operators. For example, it suggests simplifying the procedures or adding additional checking steps. The recovery suggestion unit also uses AI to analyze feedback from other operators and suggest optimal recovery procedures. For example, it adjusts the priority of procedures based on the feedback. This makes it possible to suggest improvements to the procedures based on feedback from other operators.

[0077] The recovery presentation unit, when confirming recovery procedures, can provide the procedures in video format, making them easier to understand visually. For example, when confirming recovery procedures, the recovery presentation unit uses AI to provide the procedures in video format. For example, the operations for each step can be shown in video, allowing the operator to understand visually. The recovery presentation unit also uses video procedures to enable the operator to intuitively understand the procedures. For example, the actual operation screen or device operation can be shown in video. The recovery presentation unit also uses AI to provide the procedures in video format, making them easier to understand visually. For example, the operations for each step can be shown in video, allowing the operator to understand visually. As a result, providing the procedures in video format makes them easier to understand visually.

[0078] The recovery presentation unit uses the emotion estimation function to monitor the emotions of the operator when confirming procedures in real time, and can issue an alert if the operator feels stressed. The recovery presentation unit, for example, uses the emotion estimation function to monitor the emotions of the operator when confirming procedures in real time. For example, it analyzes the operator's facial expressions and voice to measure the stress level. The recovery presentation unit also uses AI to issue an alert when the operator's stress level increases. For example, it issues an alert encouraging the operator to take a break if a certain stress level is exceeded. The recovery presentation unit also uses the emotion estimation function to suggest ways to relax when the operator feels stressed. For example, it instructs the operator to take deep breaths or stretch. In this way, the operator's emotions can be monitored in real time, and an alert can be issued if the operator feels stressed, enabling appropriate action to be taken.

[0079] When automatic recovery is being performed, the execution unit monitors the recovery process in real time, and can respond immediately if an abnormality occurs. For example, when automatic recovery is being performed, AI in the execution unit monitors the recovery process in real time. For example, it monitors each step of the recovery procedure and issues an alert if an abnormality occurs. Furthermore, if an abnormality occurs during the recovery process, the AI ​​responds immediately. For example, it automatically starts a backup when an abnormality is detected. Furthermore, the execution unit monitors the recovery process in real time, and can respond immediately if an abnormality occurs. For example, it automatically starts a backup when an abnormality is detected. This allows the recovery process to be monitored in real time, and can respond immediately if an abnormality occurs.

[0080] After performing automatic recovery, the execution unit can report the recovery results in detail and provide feedback to the operator. For example, after performing automatic recovery, the AI ​​in the execution unit reports the recovery results in detail. For example, it reports the results and required time for each step of the recovery procedure. In addition, in the execution unit, the AI ​​provides feedback to the operator based on the recovery results. For example, it suggests improvements to the recovery procedure and measures to be taken next time. In addition, in the execution unit, the AI ​​reports the recovery results in detail so that the operator can understand the recovery process. For example, it reports the results and required time for each step of the recovery procedure. This makes it possible to report the recovery results in detail and provide feedback to the operator.

[0081] The execution unit can use the emotion estimation function to provide support to reduce the anxiety felt by the operator while automatic recovery is being performed. The execution unit, for example, uses the emotion estimation function to provide support to reduce the anxiety felt by the operator while automatic recovery is being performed. For example, the execution unit analyzes the operator's facial expressions and voice and suggests ways to help the operator relax when they feel anxious. The execution unit also uses AI to provide real-time support to reduce the operator's anxiety. For example, the execution unit reports the progress of the recovery procedure on a regular basis to help the operator feel at ease. The execution unit also uses the emotion estimation function to provide support to reduce the anxiety felt by the operator while automatic recovery is being performed. For example, the execution unit analyzes the operator's facial expressions and voice and suggests ways to help the operator relax when they feel anxious. This makes it possible to provide support to reduce the anxiety felt by the operator while automatic recovery is being performed.

[0082] The execution unit can achieve comprehensive recovery by coordinating with other systems and services when automatic recovery is performed. In the execution unit, for example, AI coordinates with other systems and services when automatic recovery is performed. For example, when a network failure occurs, the status of related servers and devices is checked. The execution unit also achieves comprehensive recovery through collaboration with other systems and services. For example, it coordinates with cloud services and external monitoring systems to present optimal recovery procedures. The execution unit also achieves comprehensive recovery by coordinating with other systems and services when automatic recovery is performed. For example, it automatically activates a backup system when an abnormality is detected. This makes it possible to achieve comprehensive recovery through collaboration with other systems and services.

[0083] When automatic recovery is performed, the execution unit can report progress to the operator via voice, allowing the operator to respond even in situations where visual confirmation is difficult. For example, when automatic recovery is performed, the execution unit has the AI ​​report progress via voice to the operator. For example, the progress status of each step of the recovery procedure is notified via voice. The execution unit also uses voice reports to enable the operator to understand the recovery procedure even in situations where visual confirmation is difficult. For example, this supports work in dark places or noisy environments. Furthermore, when automatic recovery is performed, the AI ​​reports progress via voice in real time, allowing the operator to respond quickly. For example, voice instructions are given for each step to notify the operator when to proceed to the next step. In this way, by reporting progress via voice, it becomes possible to respond even in situations where visual confirmation is difficult.

[0084] The execution unit uses the emotion estimation function to allow the operator to monitor the progress of automatic recovery in real time and provide a sense of security. The execution unit, for example, uses the emotion estimation function to allow the operator to monitor the progress of automatic recovery in real time. For example, by analyzing the operator's facial expressions and voice, a sense of security is provided. Furthermore, the execution unit has the AI ​​report the progress in real time to provide the operator with a sense of security. For example, by reporting the progress of the recovery procedure on a regular basis, so that the operator can feel at ease. Furthermore, the execution unit uses the emotion estimation function to allow the operator to monitor the progress of automatic recovery in real time and provide a sense of security. For example, by analyzing the operator's facial expressions and voice, a sense of security is provided. This allows the operator to monitor the progress of automatic recovery in real time and provide a sense of security.

[0085] When creating an update procedure, the update unit can refer to past update history and propose the optimal procedure. For example, when creating an update procedure, the update unit uses AI to refer to past update history and propose the optimal procedure. For example, a new procedure is created based on past successful update procedures. The update unit also uses AI to propose improvements to the update procedure based on past update history. For example, it analyzes past failure cases and proposes procedures to avoid risks. The update unit also uses AI to refer to past update history and automatically generate the optimal procedure. For example, it selects the most effective procedure based on past data. This makes it possible to propose the optimal procedure by referring to past update history.

[0086] When creating update procedures, the update unit can perform a risk assessment of the procedures and highlight high-risk parts to the operator. For example, when creating update procedures, the update unit uses AI to perform a risk assessment of the procedures. For example, it quantifies the risk level of each procedure and presents it to the operator. The update unit also highlights high-risk parts to make it clear that operators need to pay attention to them. For example, it displays high-risk procedures in red. The update unit also suggests risk mitigation measures to the operator based on the AI's risk assessment of the procedures. For example, it presents alternative procedures or additional confirmation procedures. In this way, by highlighting high-risk parts, it is possible to make clear that operators need to pay attention to them.

[0087] The update unit uses the emotion estimation function to analyze the emotions of operators when they check the update procedures, and can automatically generate easy-to-understand procedure manuals. The update unit, for example, uses the emotion estimation function to analyze the emotions of operators when they check the update procedures. For example, it identifies parts that cause stress to operators and suggests areas for improvement. The update unit also uses AI to automatically generate easy-to-understand procedure manuals based on the operator's emotion data. For example, it designs a layout and format for the procedure manual that allows operators to work in a relaxed manner. The update unit also uses the emotion estimation function to monitor the emotions of operators in real time when they check the update procedures, and automatically generate easy-to-understand procedure manuals. For example, it prioritizes providing procedure manuals that the operator has positive emotions about. This makes it possible to automatically generate easy-to-understand procedure manuals based on the operator's emotion data.

[0088] When checking the update procedure, the update unit can collect feedback from other operators and suggest improvements to the procedure. For example, when checking the update procedure, the AI ​​in the update unit collects feedback from other operators. For example, it collects opinions and evaluations from operators who have used the same procedure in the past. The update unit also suggests improvements to the procedure based on feedback from other operators. For example, it suggests simplifying the procedure or adding additional confirmation steps. The update unit also analyzes feedback from other operators and suggests the optimal update procedure. For example, it adjusts the priority of the procedures based on the feedback. This makes it possible to suggest improvements to the procedure based on feedback from other operators.

[0089] When confirming the update procedure, the update unit can provide the procedure in video format, making it easier to understand visually. When confirming the update procedure, for example, the update unit has AI provide the procedure in video format. For example, the operation for each step can be shown in video, allowing the operator to understand visually. The update unit also uses video-format procedures to enable the operator to intuitively understand the procedure. For example, the actual operation screen or operation of the device can be shown in video. The update unit also has AI provide the procedure in video format, making it easier for the operator to visually confirm. For example, the operation for each step can be shown in video, allowing the operator to understand visually. As a result, providing the procedure in video format makes it easier to understand visually.

[0090] The update unit uses the emotion estimation function to monitor the emotions of the operator when confirming procedures in real time, and can issue an alert if the operator feels stressed. The update unit, for example, uses the emotion estimation function to monitor the emotions of the operator when confirming procedures in real time. For example, it analyzes the operator's facial expressions and voice to measure their stress level. The update unit also has the AI ​​issue an alert if the operator's stress level rises. For example, it issues an alert encouraging the operator to take a break if a certain stress level is exceeded. The update unit also uses the emotion estimation function to suggest ways to relax when the operator feels stressed. For example, it gives instructions for deep breathing and stretching. This makes it possible to monitor the operator's emotions in real time and issue an alert if the operator feels stressed, enabling appropriate action to be taken.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The automated operation system can further include a prediction unit. The prediction unit predicts the possibility of future failures based on server operation data. For example, it analyzes past failure history and operation logs and detects specific patterns to predict future failures. The prediction unit also uses AI to analyze server performance data in real time and detect signs of abnormalities early. For example, it detects abnormal fluctuations in CPU usage or memory usage and issues a warning to the operator. The prediction unit also suggests steps to take in advance to address predicted failures. For example, by replacing specific hardware or updating software in advance, it is possible to prevent failures from occurring. Thus, by including a prediction unit, future failures can be predicted and countermeasures can be taken in advance.

[0093] The automated operation system can further include a user feedback collection unit. The user feedback collection unit collects feedback from operators and uses it to improve the system. For example, it collects opinions and evaluations about the recovery procedures and operations used by operators. The user feedback collection unit also uses the AI ​​to suggest improvements to the system based on the collected feedback. For example, it may suggest simplifying procedures or improving the interface. Furthermore, the user feedback collection unit updates the system to make it easier for operators to use, based on the collected feedback. For example, it may add new functions that reflect the opinions of operators. In this way, by including a user feedback collection unit, it is possible to collect feedback from operators and use it to improve the system.

[0094] The automated operation system can further include a training department. The training department trains operators on how to use the system and procedures for responding to failures. For example, it provides online courses for learning basic system operations and recovery procedures. The training department also uses a simulation environment to allow operators to practice responding to actual failures. For example, it reproduces failures in a virtual environment and allows operators to practice recovery procedures. The training department also provides customized training programs according to the skill level of the operators. For example, it provides basic courses for beginners and advanced courses for advanced users. In this way, having a training department allows operators to effectively learn how to use the system and procedures for responding to failures.

[0095] The automated operation system can further use the emotion estimation function to provide a customized interface based on the operator's emotions. For example, if the operator is feeling stressed, the system will simplify the interface and make operation easier. If the operator is relaxed, it will provide detailed information and advanced operation options. Furthermore, the emotion estimation function can be used to provide support according to the operator's emotions. For example, if the operator is feeling anxious, the system will provide support in real time and reassure the operator. If the operator is feeling positive, the system will display messages of praise and encouragement. In this way, the emotion estimation function can provide a customized interface and support based on the operator's emotions.

[0096] The automated operation system can further use its emotion estimation function to suggest break times based on the operator's emotions. For example, if an operator has been working for a long time, the system will suggest a break at an appropriate time. Also, if the operator is feeling stressed, the system will suggest ways to relax. For example, it will instruct the operator to take deep breaths or stretch. Furthermore, the emotion estimation function can be used to provide a break plan based on the operator's emotions. For example, it could play music that helps the operator relax or suggest a short meditation session. In this way, the emotion estimation function can suggest break times and relaxation methods based on the operator's emotions.

[0097] The automated operation system can further use the emotion estimation function to provide feedback based on the operator's emotions. For example, if the operator is feeling stressed, the system can display an encouraging message to increase motivation. If the operator is relaxed, the system can provide positive feedback and praise the operator's progress. Furthermore, the emotion estimation function can be used to provide advice based on the operator's emotions. For example, if the operator is feeling anxious, the system can suggest specific solutions or next steps. If the operator is feeling positive, the system can suggest further challenges and encourage the operator to improve their skills. In this way, the emotion estimation function can provide feedback and advice based on the operator's emotions.

[0098] The automated operation system can further use the emotion estimation function to provide a training program based on the operator's emotions. For example, if the operator is feeling stressed, the system can suggest a training program that helps them relax. If the operator is relaxed, the system can provide a training program for learning advanced skills. Furthermore, the emotion estimation function can be used to monitor the progress of training based on the operator's emotions and provide appropriate feedback. For example, if the operator is feeling anxious, the system can display an encouraging message to increase motivation. If the operator has positive emotions, the system can suggest further challenges and encourage skill improvement. In this way, the emotion estimation function can be used to provide training programs and feedback based on the operator's emotions.

[0099] An automated operation system can further be equipped with an anomaly detection unit. The anomaly detection unit monitors the server's operational data in real time and detects anomalies. For example, it detects abnormal fluctuations in network traffic or CPU usage. The anomaly detection unit also issues an alert to the operator when it detects an anomaly. For example, it notifies the operator immediately when an anomaly occurs, encouraging a prompt response. Furthermore, the anomaly detection unit identifies the cause of the anomaly and proposes specific countermeasures to the operator. For example, it proposes replacing specific hardware or updating software. Thus, by having an anomaly detection unit, it is possible to monitor the server's operational data in real time, detect anomalies, and respond promptly.

[0100] The automated operation system can further include a data backup unit. The data backup unit periodically backs up server data to prevent data loss in the event of a failure. For example, it automatically performs data backups every night. The data backup unit also checks the consistency of the backup data and notifies the operator if a problem occurs. For example, it issues an alert if the backup data contains an error. Furthermore, the data backup unit provides procedures for quickly restoring data in the event of a failure. For example, it presents the operator with procedures for restoring data from backup data. Thus, having a data backup unit enables regular data backups and quick data restoration in the event of a failure.

[0101] An automated operation system can further be equipped with a security monitoring unit. The security monitoring unit monitors the security status of the server in real time and detects abnormal access or unauthorized operations. For example, it detects unauthorized access from a specific IP address. The security monitoring unit also issues an alert to the operator when it detects an abnormality. For example, it immediately notifies the operator when unauthorized access occurs, encouraging a prompt response. The security monitoring unit also proposes specific countermeasures for detected abnormalities. For example, it proposes changing firewall settings or resetting passwords. Thus, by having a security monitoring unit, it is possible to monitor the security status of the server in real time, detect abnormalities, and respond promptly.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The learning unit studies the server's configuration diagram and design documents. For example, the learning unit learns the server's network configuration, hardware layout, software version information, etc. The learning unit also uses generative AI (e.g., text generation AI or multimodal generation AI) to understand the server's configuration and design. Step 2: The fault identification unit identifies the location of the failure when a server failure occurs. For example, the fault identification unit analyzes log files and system status to identify the cause of the failure. The fault identification unit also uses a generation AI to identify the location of the failure based on the log files and system status at the time of the failure. Step 3: The recovery presentation unit presents a recovery method based on the fault location identified by the fault identification unit. For example, the recovery presentation unit presents a procedure manual or guidelines to provide the operator with a recovery method. The recovery presentation unit also uses a generation AI to present a recovery method based on the fault location. Step 4: In the approval unit, the operator checks and approves the recovery method presented by the recovery presentation unit. For example, the approval unit checks the presented recovery procedure and checks whether there are any problems with the procedure. Step 5: The execution unit automatically executes the recovery method approved by the approval unit. For example, the execution unit restarts the server or changes its settings. The execution unit also uses the generation AI to automatically execute recovery according to the approved recovery procedure. Step 6: The update unit creates a regular update procedure and automatically executes the update after the administrator has confirmed it. For example, the update unit creates a server software or firmware update procedure, which the administrator then confirms.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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.

[0158] 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."

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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]

[0171] 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. A learning department that studies server configuration diagrams and design documents, and a failure identification unit that identifies a failure location when a failure occurs in the server; a restoration suggestion unit that suggests a restoration method based on the failure location identified by the failure identification unit; an approval unit for allowing an operator to confirm and approve the recovery method presented by the recovery presentation unit; an execution unit that automatically executes the recovery method approved by the approval unit; an update unit that creates a periodic update procedure and automatically executes the update after the administrator confirms it; A system characterized by:

2. The learning unit In addition to server configuration diagrams and the aforementioned design documents, the system also learns from past failure history and operation logs to make more accurate failure predictions.

2. The system of claim 1.

3. The learning unit Server configuration diagrams and design documents are converted into 3D models for easy visual learning.

2. The system of claim 1.

4. The learning unit Learn how the operator responded in the past and propose less stressful operational procedures 2. The system of claim 1.

5. The learning unit Learn not only server configuration diagrams and design documents, but also relevant industry standards and best practices to gain more comprehensive knowledge 2. The system of claim 1.

Images