system

Abstract

The system according to the embodiment aims to automate the identification of a fault location and the presentation of a recovery method in server operation in an on-premise environment. [Solution] A system according to an embodiment includes a learning unit, an investigation unit, a presentation unit, and an execution unit. The learning unit studies a server configuration diagram or design document. The investigation unit investigates the location of a failure in the server based on the information learned by the learning unit. The presentation unit presents a recovery method based on the location of the failure investigated by the investigation unit. The execution unit allows a human operator to review the recovery method presented by the presentation unit and automatically executes approved operations.

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, when operating servers in an on-premises environment, identifying the faulty part and presenting a recovery method was done manually, which was a time-consuming and labor-intensive process.

[0005] The system according to the embodiment aims to automate the identification of a fault location and the presentation of a recovery method in server operation in an on-premise environment. [Means for solving the problem]

[0006] The system according to the embodiment includes a learning unit, an investigation unit, a presentation unit, and an execution unit. The learning unit studies the server configuration diagram or design document. The investigation unit investigates the location of a failure in the server based on the information learned by the learning unit. The presentation unit presents a recovery method based on the location of the failure investigated by the investigation unit. The execution unit allows a human operator to check the recovery method presented by the presentation unit and automatically executes the approved operation. [Effects of the Invention]

[0007] The system according to the embodiment can automate the identification of a fault location and the presentation of a recovery method when operating a server 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) A server operation automation system according to an embodiment of the present invention uses AI to automate server operations in on-premises environments. This server operation automation system learns documents such as server configuration diagrams and design documents. When a server failure occurs, it identifies the failure location, proposes a recovery method, and automatically executes approved operations. For example, in a server operation automation system, an AI first learns documents such as server configuration diagrams and design documents. The AI ​​then analyzes these documents to acquire knowledge about the server's configuration and design. For example, by learning the server's hardware configuration and software configuration information, it can grasp the overall picture of the server. Next, when a server failure occurs, the AI ​​investigates the failure location. The AI ​​analyzes server log data and monitoring data to identify the cause of the failure. For example, it can extract error messages from server log data and identify the failure location. This allows for rapid identification of the cause of the failure. Furthermore, the AI ​​proposes a recovery method based on the failure location. The AI ​​refers to past failure response history and best practices to propose the optimal recovery method. For example, it can propose specific recovery procedures, such as rebooting or changing settings, for a specific error message. A human operator then confirms the proposed recovery method. The operator checks the recovery method proposed by the AI ​​and approves it if there are no problems. For example, the operator checks the restart procedure proposed by the AI ​​and approves it if there are no problems. This process allows the operator to trust the AI's proposal and carry it out. Finally, the approved operation is automatically executed to recover the system. With the operator's approval, the AI ​​automatically executes the proposed recovery procedure. For example, it can automatically restart the server or change settings to recover from the failure. This enables quick and efficient failure response. This mechanism makes server operations in on-premises environments more efficient and speeds up failure response. By allowing the AI ​​to learn knowledge about server configuration and design and respond quickly when a failure occurs, it reduces the burden on operators and ensures stable system operation.This allows the server operation automation system to study the server configuration diagrams and design documents, investigate the faulty parts, present recovery methods, and automatically execute approved operations, thereby making server operations more efficient and enabling rapid response to failures.

[0029] A server operation automation system according to an embodiment includes a learning unit, an investigation unit, a presentation unit, and an execution unit. The learning unit studies server configuration diagrams and design documents. For example, the learning unit studies the server configuration diagrams and design documents as PDFs, image data, or text data. The learning unit analyzes these documents to acquire knowledge about the server configuration and design. For example, by studying the server's hardware configuration and software configuration information, the system can grasp an overall picture of the server. The investigation unit investigates the location of a server failure based on the information learned by the learning unit. For example, the investigation unit analyzes server log data and monitoring data and identifies the location of the failure using an anomaly detection algorithm. The investigation unit can extract error messages from the server log data and identify the location of the failure. This allows the system to quickly identify the cause of the failure. The presentation unit presents a recovery method based on the location of the failure investigated by the investigation unit. For example, the presentation unit compiles a database of past failure response histories and best practices to propose an optimal recovery method. The presentation unit can present specific recovery procedures, such as rebooting or changing settings, for specific error messages. The execution unit allows a human operator to review the recovery methods presented by the presentation unit and automatically execute the approved operations. For example, the execution unit automatically executes the proposed recovery procedures with the operator's approval. The execution unit can automatically restart the server or change settings to recover from the failure. As a result, the server operation automation system according to the embodiment learns the server configuration diagram and design documents, investigates the location of the failure, presents a recovery method, and automatically executes the approved operations, thereby enabling more efficient server operation and quicker failure response.

[0030] The learning unit can learn server configuration diagrams or design documents as PDFs, image data, or text data. For example, the learning unit learns server configuration diagrams or design documents as PDFs, image data, or text data. The learning unit analyzes these documents to acquire knowledge about the server configuration and design. For example, by learning the server's hardware configuration and software configuration information, the overall picture of the server can be grasped. By learning server configuration diagrams and design documents in various data formats, a wider range of information can be acquired, improving the accuracy of learning. Some or all of the above-described processing in the learning unit may be performed using, or without, AI. For example, the learning unit may input PDF data of server configuration diagrams or design documents into a generation AI and have the generation AI convert the PDF data into text data.

[0031] The investigation unit can analyze server log data or monitoring data and identify the location of a failure using an anomaly detection algorithm. For example, the investigation unit can analyze server log data or monitoring data and identify the location of a failure using an anomaly detection algorithm. The investigation unit can extract error messages from server log data and identify the location of a failure. This allows the cause of a failure to be quickly identified. For example, the investigation unit can detect anomalies using a machine learning algorithm. The investigation unit can also identify anomalies using a rule-based detection method. Furthermore, the investigation unit can analyze server monitoring data in real time and immediately detect anomalies. This allows the location of a failure to be quickly and accurately identified by analyzing server log data or monitoring data and using an anomaly detection algorithm. Some or all of the above-mentioned processing in the investigation unit may be performed using, for example, AI, or may be performed without using AI. For example, the investigation unit can input server log data to a generation AI and have the generation AI perform anomaly detection.

[0032] The presentation unit can create a database of past fault response histories or best practices and propose an optimal recovery method. The presentation unit, for example, creates a database of past fault response histories and best practices and proposes an optimal recovery method. The presentation unit can present specific recovery procedures, such as rebooting or changing settings, for a specific error message. The presentation unit analyzes past fault response histories and prioritizes proposals of recovery methods with a high success rate. The presentation unit can also propose an optimal recovery method based on best practices. Furthermore, the presentation unit can propose an optimal recovery method by consulting the opinions of external experts. By creating a database of past fault response histories and best practices, an optimal recovery method can be quickly proposed. Some or all of the above-described processing in the presentation unit may be performed using, for example, AI, or may be performed without AI. For example, the presentation unit can input past fault response histories into a generation AI and cause the generation AI to propose an optimal recovery method.

[0033] The execution unit can automatically execute the proposed recovery procedure with the operator's approval. For example, the execution unit automatically executes the proposed recovery procedure with the operator's approval. The execution unit can automatically restart servers and change settings to recover from failures. The execution unit executes the recovery procedure using an automation tool such as Ansible or Puppet. The execution unit also has a process for obtaining the operator's approval. For example, the execution unit presents details of the recovery procedure to the operator and requests approval. Once the operator approves, the execution unit automatically executes the recovery procedure. This enables rapid and accurate failure recovery by automatically executing the recovery procedure after receiving the operator's approval. Some or all of the above-mentioned processing in the execution unit may be performed using, for example, AI, or may be performed without using AI. For example, the execution unit can input the recovery procedure approved by the operator into a generation AI and have the generation AI execute the recovery procedure.

[0034] The execution unit can execute the recovery procedure using an automation tool (e.g., Ansible or Puppet). The execution unit executes the recovery procedure using an automation tool such as Ansible or Puppet. By using these automation tools, the execution unit can improve the efficiency of the execution of the recovery procedure and reduce human error. The execution unit can automatically change the server configuration using, for example, Ansible. The execution unit can also automatically restart the server using Puppet. Furthermore, the execution unit can also execute the recovery procedure using other automation tools. In this way, by using automation tools, the execution of the recovery procedure can be improved in efficiency and human error can be reduced. Some or all of the above-mentioned processing in the execution unit may be performed using, for example, AI, or may be performed without using AI. For example, the execution unit can input configuration information for Ansible or Puppet to a generation AI and cause the generation AI to execute the recovery procedure.

[0035] The learning unit can track the update history of the server's configuration diagram or design document and constantly learn the latest information. For example, the learning unit can periodically check the update history of the server's configuration diagram or design document and automatically learn the latest information. The learning unit can analyze the update history and prioritize learning of important changes. The learning unit can also compare past information with the latest information based on the update history and learn the differences. In this way, by tracking the update history of the server's configuration diagram or design document, the latest information can always be learned and the accuracy of the system can be improved. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without AI. For example, the learning unit can input update history data of the server's configuration diagram or design document into the generation AI and cause the generation AI to learn the latest information.

[0036] The learning unit can automatically identify particularly important parts in a server configuration diagram or design document and focus on learning them. For example, the learning unit analyzes the server configuration diagram or design document and automatically identifies important hardware configurations and software settings. The learning unit refers to past failure history and best practices to identify important parts. The learning unit can also focus on learning the identified important parts and postpone other parts. This improves learning efficiency by automatically identifying particularly important parts in a server configuration diagram or design document. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without AI. For example, the learning unit can input data from the server configuration diagram or design document into a generation AI and have the generation AI identify and learn important parts.

[0037] The learning unit can study the server's operation manual and troubleshooting guide in addition to the server configuration diagram and design document. For example, the learning unit studies the server's operation manual to understand operation procedures and best practices. The learning unit studies the troubleshooting guide to learn how to respond when a failure occurs. The learning unit can also grasp the overall picture of the server based on the operation manual and troubleshooting guide. In this way, by studying the server's operation manual and troubleshooting guide, more comprehensive knowledge can be acquired. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data from the server's operation manual and troubleshooting guide into the generation AI and have the generation AI perform learning.

[0038] When learning the server configuration diagrams and design documents, the learning unit can also refer to the configuration diagrams and design documents of other similar systems. For example, the learning unit may study the configuration diagrams and design documents of other similar systems to understand their similarities and differences. The learning unit may refer to best practices from other systems and use this knowledge in server operation. The learning unit may also study the failure history of other systems and use this knowledge in responding to server failures. In this way, by referring to the configuration diagrams and design documents of other similar systems, a broader range of knowledge can be acquired and used in server operation. Some or all of the above-described processing in the learning unit may be performed, for example, using AI, or may be performed without AI. For example, the learning unit may input data from the configuration diagrams and design documents of other similar systems into the generation AI and have the generation AI extract information to use as reference.

[0039] The investigation unit can focus its analysis on parts of the server log data and monitoring data that are particularly prone to abnormalities. For example, the investigation unit identifies parts that are prone to abnormalities based on past failure history and performs focused analysis. The investigation unit analyzes the server log data and focuses its investigation on parts where errors frequently occur. The investigation unit can also analyze monitoring data to identify time periods and conditions when abnormalities are likely to occur. This allows for focused analysis of parts that are prone to abnormalities, thereby quickly identifying the location of the failure. Some or all of the above-mentioned processing by the investigation unit may be performed using, for example, AI, or may be performed without using AI. For example, the investigation unit can input the server log data and monitoring data into the generation AI and have the generation AI perform an analysis of parts that are prone to abnormalities.

[0040] The investigation unit can analyze server log data and monitoring data in real time and immediately identify the location of a failure. For example, the investigation unit analyzes server log data in real time and immediately identify the location of a failure if an abnormality is detected. The investigation unit can also analyze monitoring data in real time and immediately identify the location of a failure if an abnormality occurs. The investigation unit can also perform an integrated analysis of log data and monitoring data in real time and quickly identify the location of a failure. This allows for real-time analysis to quickly identify the location of a failure and respond immediately. Some or all of the above-mentioned processing in the investigation unit may be performed using, for example, AI, or may be performed without using AI. For example, the investigation unit can input log data and monitoring data acquired in real time into a generation AI and have the generation AI identify the location of a failure.

[0041] The investigation unit can analyze network traffic data in addition to server log data and monitoring data. For example, the investigation unit analyzes network traffic data in addition to server log data and monitoring data to detect anomalies. The investigation unit analyzes network traffic data to identify network problems related to server anomalies. The investigation unit can also perform an integrated analysis of log data, monitoring data, and network traffic data to identify the cause of anomalies. In this way, by analyzing network traffic data as well, anomalies can be identified based on a wider range of data. Some or all of the above-mentioned processing in the investigation unit may be performed using, for example, AI, or may be performed without using AI. For example, the investigation unit can input network traffic data into a generation AI and have the generation AI detect and identify anomalies.

[0042] When analyzing server log data and monitoring data, the investigation department can also refer to data from other similar systems. For example, the investigation department refers to log data and monitoring data from other similar systems to identify abnormality patterns. The investigation department quickly identifies server abnormalities based on data from other systems. The investigation department can also analyze data from other systems to identify the cause of the server abnormality. By referring to data from other similar systems, the abnormality pattern can be more accurately identified. Some or all of the above-mentioned processing by the investigation department may be performed using, for example, AI, or may be performed without using AI. For example, the investigation department can input data from other similar systems into the generation AI and have the generation AI identify abnormality patterns.

[0043] The presentation unit can prioritize suggesting methods with a particularly high success rate from among past failure response histories and best practices. The presentation unit, for example, analyzes past failure response histories and prioritizes suggesting recovery methods with a high success rate. The presentation unit proposes the optimal recovery method based on best practices. The presentation unit can also create a database of methods with high success rates and prioritize suggesting them. This improves the success rate of recovery by prioritizing the suggestion of methods with a high success rate. Some or all of the above-mentioned processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input past failure response histories into a generation AI and cause the generation AI to suggest recovery methods with a high success rate.

[0044] The presentation unit can collect feedback on the presented recovery method and reflect it in the next proposal. The presentation unit, for example, collects feedback from an operator and reflects it in the next proposal. The presentation unit evaluates the effectiveness of the recovery method and makes improvements based on the feedback. The presentation unit can also create a database of feedback and use it in the next proposal. In this way, by collecting feedback and reflecting it in the next proposal, the accuracy of the proposal is improved. Some or all of the above-mentioned processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input feedback data from an operator into the generation AI and cause the generation AI to execute processing to reflect the feedback in the next proposal.

[0045] The presentation unit can refer to the opinions of external experts in addition to past failure response history and best practices. For example, the presentation unit refers to the opinions of external experts and proposes an optimal recovery method. The presentation unit creates a database of expert opinions and uses them to propose recovery methods. The presentation unit can also improve the recovery method based on the expert opinions. In this way, by also referring to the opinions of external experts, it is possible to propose a more reliable recovery method. Some or all of the above-mentioned processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input the opinion data of external experts into the generation AI and cause the generation AI to execute processing to reflect the opinion data in the proposed recovery method.

[0046] The presentation unit can present multiple options for the proposed recovery method, allowing the operator to select one. The presentation unit, for example, presents multiple recovery methods, allowing the operator to select the optimal method. The presentation unit presents the advantages and disadvantages of each recovery method, making it easier for the operator to select. The presentation unit can also reflect the operator's selection in the next proposal. In this way, by presenting multiple options, the operator can select the optimal method. Some or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input data of multiple recovery methods into the generation AI and cause the generation AI to present the options.

[0047] The execution unit can highlight particularly important steps in the execution procedure and prompt the operator to confirm them. For example, the execution unit can highlight particularly important steps in the execution procedure and prompt the operator to confirm them. The execution unit can display a pop-up for an important step requesting the operator's confirmation. The execution unit can also send a message requesting the operator's confirmation before executing an important step. By highlighting important steps in this way, the operator can be sure to confirm them and prevent mistakes. Some or all of the above-mentioned processing in the execution unit may be performed using AI, for example, or may be performed without using AI. For example, the execution unit can input information about important steps into the generation AI and have the generation AI execute processing to prompt confirmation.

[0048] The execution unit records the results of the execution procedure in detail, which can be used to respond to the next failure. For example, the execution unit records the results of each step of the execution procedure in detail, which can be used to respond to the next failure. The execution unit creates a database of the results of the execution procedure, which can be referenced by operators. The execution unit can also analyze the results of the execution procedure and reflect them in the next proposal. In this way, by recording the results of the execution procedure in detail, it can be used to respond to the next failure. Some or all of the above-mentioned processing in the execution unit may be performed using, for example, AI, or may be performed without using AI. For example, the execution unit can input result data of the execution procedure into a generation AI and have the generation AI execute processing to be used to respond to the next failure.

[0049] The execution unit can present, in addition to the execution procedure, auxiliary procedures that the operator should perform manually. For example, the execution unit presents, in addition to the execution procedure, auxiliary procedures that the operator should perform manually. The execution unit explains the auxiliary procedures in detail to make it easier for the operator to understand. The execution unit can also present points to note when performing the auxiliary procedures and prompt the operator to check them. In this way, by presenting the auxiliary procedures, the operator can easily understand the procedures that should be performed manually. Some or all of the above-mentioned processing in the execution unit may be performed using, for example, AI, or may be performed without using AI. For example, the execution unit can input information about the auxiliary procedures to a generation AI and have the generation AI perform the presentation.

[0050] The execution unit can include, in the execution procedure, a procedure that takes into account cooperation with other systems and devices. For example, the execution unit includes, in the execution procedure, a procedure that takes into account cooperation with other systems and devices. The execution unit refers to the configuration information of the systems and devices that are to be linked and proposes an optimal procedure. The execution unit can also monitor the status of the systems and devices that are to be linked and adjust the procedure as necessary. This makes it possible to execute a more comprehensive recovery procedure by taking into account cooperation with other systems and devices. Some or all of the above-mentioned processing in the execution unit may be performed using, for example, AI, or may be performed without using AI. For example, the execution unit can input information about other systems and devices into the generation AI and cause the generation AI to execute a procedure that takes into account cooperation.

[0051] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0052] The learning unit can study the server's operation manual and troubleshooting guide in addition to the server configuration diagram and design document. For example, the learning unit studies the server's operation manual to understand operation procedures and best practices. The learning unit studies the troubleshooting guide to learn how to respond when a failure occurs. The learning unit can also grasp the overall picture of the server based on the operation manual and troubleshooting guide. In this way, by studying the server's operation manual and troubleshooting guide, more comprehensive knowledge can be acquired. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data from the server's operation manual and troubleshooting guide into the generation AI and have the generation AI perform learning.

[0053] The investigation unit can analyze network traffic data in addition to server log data and monitoring data. For example, the investigation unit analyzes network traffic data in addition to server log data and monitoring data to detect anomalies. The investigation unit analyzes network traffic data to identify network problems related to server anomalies. The investigation unit can also perform an integrated analysis of log data, monitoring data, and network traffic data to identify the cause of anomalies. In this way, by analyzing network traffic data as well, anomalies can be identified based on a wider range of data. Some or all of the above-mentioned processing in the investigation unit may be performed using, for example, AI, or may be performed without using AI. For example, the investigation unit can input network traffic data to a generation AI and have the generation AI detect and identify anomalies.

[0054] The presentation unit can present multiple options for the proposed recovery method, allowing the operator to select the most suitable method. For example, the presentation unit can present multiple recovery methods, allowing the operator to select the most suitable method. The presentation unit can present the advantages and disadvantages of each recovery method, making it easier for the operator to select. The presentation unit can also reflect the operator's selection in the next proposal. In this way, by presenting multiple options, the operator can select the most suitable method. Some or all of the above-described processing in the presentation unit may be performed using, or without, AI, for example. For example, the presentation unit can input data on multiple recovery methods into the generation AI and cause the generation AI to present the options.

[0055] The execution unit can highlight particularly important steps in the execution procedure and prompt the operator to confirm them. For example, the execution unit can highlight particularly important steps in the execution procedure and prompt the operator to confirm them. The execution unit can display a pop-up for an important step requesting the operator's confirmation. The execution unit can also send a message requesting the operator's confirmation before executing an important step. By highlighting important steps in this way, the operator can be sure to confirm them and prevent mistakes. Some or all of the above-mentioned processing in the execution unit may be performed using AI, for example, or may be performed without using AI. For example, the execution unit can input information about important steps into the generation AI and have the generation AI execute processing to prompt confirmation.

[0056] The execution unit records the results of the execution procedure in detail, which can be used to respond to the next failure. For example, the execution unit records the results of each step of the execution procedure in detail, which can be used to respond to the next failure. The execution unit creates a database of the results of the execution procedure, which can be referenced by operators. The execution unit can also analyze the results of the execution procedure and reflect them in the next proposal. In this way, by recording the results of the execution procedure in detail, it can be used to respond to the next failure. Some or all of the above-mentioned processing in the execution unit may be performed using, for example, AI, or may be performed without using AI. For example, the execution unit can input result data of the execution procedure into a generation AI and have the generation AI execute processing to be used to respond to the next failure.

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

[0058] Step 1: The learning unit studies the server's configuration diagrams and design documents. For example, the learning unit studies the server's configuration diagrams and design documents as PDFs, image data, or text data. The learning unit analyzes these documents and acquires knowledge about the server's configuration and design. For example, by studying the server's hardware configuration and software settings, the learning unit can grasp the overall picture of the server. Step 2: The investigation unit investigates the location of the server failure based on the information learned by the learning unit. For example, the investigation unit analyzes the server log data and monitoring data and identifies the location of the failure using an anomaly detection algorithm. The investigation unit can extract error messages from the server log data and identify the location of the failure. This allows the cause of the failure to be quickly identified. Step 3: The presentation unit presents a recovery method based on the fault location identified by the investigation unit. For example, the presentation unit may create a database of past failure response history and best practices to propose the optimal recovery method. For specific error messages, the presentation unit can present specific recovery procedures such as rebooting or changing settings. Step 4: The execution unit, where a human operator checks the recovery methods presented by the presentation unit, automatically executes the operations that have been approved. For example, the execution unit automatically executes the proposed recovery procedures after receiving approval from the operator. The execution unit can automatically restart the server or change settings to recover from the failure.

[0059] (Example 2) A server operation automation system according to an embodiment of the present invention uses AI to automate server operations in on-premises environments. This server operation automation system learns documents such as server configuration diagrams and design documents. When a server failure occurs, it identifies the failure location, proposes a recovery method, and automatically executes approved operations. For example, in a server operation automation system, an AI first learns documents such as server configuration diagrams and design documents. The AI ​​then analyzes these documents to acquire knowledge about the server's configuration and design. For example, by learning the server's hardware configuration and software configuration information, it can grasp the overall picture of the server. Next, when a server failure occurs, the AI ​​investigates the failure location. The AI ​​analyzes server log data and monitoring data to identify the cause of the failure. For example, it can extract error messages from server log data and identify the failure location. This allows for rapid identification of the cause of the failure. Furthermore, the AI ​​proposes a recovery method based on the failure location. The AI ​​refers to past failure response history and best practices to propose the optimal recovery method. For example, it can propose specific recovery procedures, such as rebooting or changing settings, for a specific error message. A human operator then confirms the proposed recovery method. The operator checks the recovery method proposed by the AI ​​and approves it if there are no problems. For example, the operator checks the restart procedure proposed by the AI ​​and approves it if there are no problems. This process allows the operator to trust the AI's proposal and carry it out. Finally, the approved operation is automatically executed to recover the system. With the operator's approval, the AI ​​automatically executes the proposed recovery procedure. For example, it can automatically restart the server or change settings to recover from the failure. This enables quick and efficient failure response. This mechanism makes server operations in on-premises environments more efficient and speeds up failure response. By allowing the AI ​​to learn knowledge about server configuration and design and respond quickly when a failure occurs, it reduces the burden on operators and ensures stable system operation.This allows the server operation automation system to study the server configuration diagrams and design documents, investigate the faulty parts, present recovery methods, and automatically execute approved operations, thereby making server operations more efficient and enabling rapid response to failures.

[0060] A server operation automation system according to an embodiment includes a learning unit, an investigation unit, a presentation unit, and an execution unit. The learning unit studies server configuration diagrams and design documents. For example, the learning unit studies the server configuration diagrams and design documents as PDFs, image data, or text data. The learning unit analyzes these documents to acquire knowledge about the server configuration and design. For example, by studying the server's hardware configuration and software configuration information, the system can grasp an overall picture of the server. The investigation unit investigates the location of a server failure based on the information learned by the learning unit. For example, the investigation unit analyzes server log data and monitoring data and identifies the location of the failure using an anomaly detection algorithm. The investigation unit can extract error messages from the server log data and identify the location of the failure. This allows the system to quickly identify the cause of the failure. The presentation unit presents a recovery method based on the location of the failure investigated by the investigation unit. For example, the presentation unit compiles a database of past failure response histories and best practices to propose an optimal recovery method. The presentation unit can present specific recovery procedures, such as rebooting or changing settings, for specific error messages. The execution unit allows a human operator to review the recovery methods presented by the presentation unit and automatically execute the approved operations. For example, the execution unit automatically executes the proposed recovery procedures with the operator's approval. The execution unit can automatically restart the server or change settings to recover from the failure. As a result, the server operation automation system according to the embodiment learns the server configuration diagram and design documents, investigates the location of the failure, presents a recovery method, and automatically executes the approved operations, thereby enabling more efficient server operation and quicker failure response.

[0061] The learning unit can learn server configuration diagrams or design documents as PDFs, image data, or text data. For example, the learning unit learns server configuration diagrams or design documents as PDFs, image data, or text data. The learning unit analyzes these documents to acquire knowledge about the server configuration and design. For example, by learning the server's hardware configuration and software configuration information, the overall picture of the server can be grasped. By learning server configuration diagrams and design documents in various data formats, a wider range of information can be acquired, improving the accuracy of learning. Some or all of the above-described processing in the learning unit may be performed using, or without, AI. For example, the learning unit may input PDF data of server configuration diagrams or design documents into a generation AI and have the generation AI convert the PDF data into text data.

[0062] The investigation unit can analyze server log data or monitoring data and identify the location of a failure using an anomaly detection algorithm. For example, the investigation unit can analyze server log data or monitoring data and identify the location of a failure using an anomaly detection algorithm. The investigation unit can extract error messages from server log data and identify the location of a failure. This allows the cause of a failure to be quickly identified. For example, the investigation unit can detect anomalies using a machine learning algorithm. The investigation unit can also identify anomalies using a rule-based detection method. Furthermore, the investigation unit can analyze server monitoring data in real time and immediately detect anomalies. This allows the location of a failure to be quickly and accurately identified by analyzing server log data or monitoring data and using an anomaly detection algorithm. Some or all of the above-mentioned processing in the investigation unit may be performed using, for example, AI, or may be performed without using AI. For example, the investigation unit can input server log data to a generation AI and have the generation AI perform anomaly detection.

[0063] The presentation unit can create a database of past fault response histories or best practices and propose an optimal recovery method. The presentation unit, for example, creates a database of past fault response histories and best practices and proposes an optimal recovery method. The presentation unit can present specific recovery procedures, such as rebooting or changing settings, for a specific error message. The presentation unit analyzes past fault response histories and prioritizes proposals of recovery methods with a high success rate. The presentation unit can also propose an optimal recovery method based on best practices. Furthermore, the presentation unit can propose an optimal recovery method by consulting the opinions of external experts. By creating a database of past fault response histories and best practices, an optimal recovery method can be quickly proposed. Some or all of the above-described processing in the presentation unit may be performed using, for example, AI, or may be performed without AI. For example, the presentation unit can input past fault response histories into a generation AI and cause the generation AI to propose an optimal recovery method.

[0064] The execution unit can automatically execute the proposed recovery procedure with the operator's approval. For example, the execution unit automatically executes the proposed recovery procedure with the operator's approval. The execution unit can automatically restart servers and change settings to recover from failures. The execution unit executes the recovery procedure using an automation tool such as Ansible or Puppet. The execution unit also has a process for obtaining the operator's approval. For example, the execution unit presents details of the recovery procedure to the operator and requests approval. Once the operator approves, the execution unit automatically executes the recovery procedure. This enables rapid and accurate failure recovery by automatically executing the recovery procedure after receiving the operator's approval. Some or all of the above-mentioned processing in the execution unit may be performed using, for example, AI, or may be performed without using AI. For example, the execution unit can input the recovery procedure approved by the operator into a generation AI and have the generation AI execute the recovery procedure.

[0065] The execution unit can execute the recovery procedure using an automation tool (e.g., Ansible or Puppet). The execution unit executes the recovery procedure using an automation tool such as Ansible or Puppet. By using these automation tools, the execution unit can improve the efficiency of the execution of the recovery procedure and reduce human error. The execution unit can automatically change the server configuration using, for example, Ansible. The execution unit can also automatically restart the server using Puppet. Furthermore, the execution unit can also execute the recovery procedure using other automation tools. In this way, by using automation tools, the execution of the recovery procedure can be improved in efficiency and human error can be reduced. Some or all of the above-mentioned processing in the execution unit may be performed using, for example, AI, or may be performed without using AI. For example, the execution unit can input configuration information for Ansible or Puppet to a generation AI and cause the generation AI to execute the recovery procedure.

[0066] The learning unit can estimate the user's emotions and prioritize the learning data based on the estimated user emotions. For example, the learning unit estimates the user's emotions and prioritizes the learning data based on the estimated user emotions. When the user is stressed, the learning unit prioritizes learning of important server configuration diagrams and design documents. Furthermore, when the user is relaxed, the learning unit can prioritize learning of detailed design documents and supplementary materials. Furthermore, when the user is in a hurry, the learning unit can quickly learn the most important information and postpone other information. This enables optimal learning tailored to the user's situation by prioritizing the learning data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, an AI. For example, the learning unit can input user emotion data into the generation AI and have the generation AI determine the priorities of the learning data.

[0067] The learning unit can track the update history of the server's configuration diagram or design document and constantly learn the latest information. For example, the learning unit can periodically check the update history of the server's configuration diagram or design document and automatically learn the latest information. The learning unit can analyze the update history and prioritize learning of important changes. The learning unit can also compare past information with the latest information based on the update history and learn the differences. In this way, by tracking the update history of the server's configuration diagram or design document, the latest information can always be learned and the accuracy of the system can be improved. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without AI. For example, the learning unit can input update history data of the server's configuration diagram or design document into the generation AI and cause the generation AI to learn the latest information.

[0068] The learning unit can automatically identify particularly important parts in a server configuration diagram or design document and focus on learning them. For example, the learning unit analyzes the server configuration diagram or design document and automatically identifies important hardware configurations and software settings. The learning unit refers to past failure history and best practices to identify important parts. The learning unit can also focus on learning the identified important parts and postpone other parts. This improves learning efficiency by automatically identifying particularly important parts in a server configuration diagram or design document. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without AI. For example, the learning unit can input data from the server configuration diagram or design document into a generation AI and have the generation AI identify and learn important parts.

[0069] The learning unit can estimate the user's emotions and adjust the learning progress speed based on the estimated user emotions. For example, the learning unit estimates the user's emotions and adjusts the learning progress speed based on the estimated user emotions. If the user is feeling stressed, the learning unit slows down the learning progress speed to reduce the user's burden. The learning unit can also maintain the learning progress speed at a normal level if the user is relaxed. Furthermore, if the user is in a hurry, the learning unit can speed up the learning progress speed to quickly complete the learning. This reduces the user's burden and enables efficient learning by adjusting the learning progress speed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the learning unit can input the user's emotional data into the generation AI and cause the generation AI to adjust the speed at which learning progresses.

[0070] The learning unit can study the server's operation manual and troubleshooting guide in addition to the server configuration diagram and design document. For example, the learning unit studies the server's operation manual to understand operation procedures and best practices. The learning unit studies the troubleshooting guide to learn how to respond when a failure occurs. The learning unit can also grasp the overall picture of the server based on the operation manual and troubleshooting guide. In this way, by studying the server's operation manual and troubleshooting guide, more comprehensive knowledge can be acquired. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data from the server's operation manual and troubleshooting guide into the generation AI and have the generation AI perform learning.

[0071] When learning the server configuration diagrams and design documents, the learning unit can also refer to the configuration diagrams and design documents of other similar systems. For example, the learning unit may study the configuration diagrams and design documents of other similar systems to understand their similarities and differences. The learning unit may refer to best practices from other systems and use this knowledge in server operation. The learning unit may also study the failure history of other systems and use this knowledge in responding to server failures. In this way, by referring to the configuration diagrams and design documents of other similar systems, a broader range of knowledge can be acquired and used in server operation. Some or all of the above-described processing in the learning unit may be performed, for example, using AI, or may be performed without AI. For example, the learning unit may input data from the configuration diagrams and design documents of other similar systems into the generation AI and have the generation AI extract information to use as reference.

[0072] The research unit can estimate the user's emotions and adjust the display method of the survey results based on the estimated user emotions. For example, the research unit estimates the user's emotions and adjusts the display method of the survey results based on the estimated user emotions. If the user is feeling stressed, the research unit provides a simple, highly visible display method. If the user is relaxed, the research unit can also provide a display method that includes detailed information. If the user is in a hurry, the research unit can also provide a display method that focuses on the main points. This allows the display method of the survey results to be adjusted based on the user's emotions, making it easy for the user to view. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the research unit may be performed using AI, for example, or without AI. For example, the research unit can input user emotion data into the generation AI and have the generation AI adjust the display method of the survey results.

[0073] The investigation unit can focus its analysis on parts of the server log data and monitoring data that are particularly prone to abnormalities. For example, the investigation unit identifies parts that are prone to abnormalities based on past failure history and performs focused analysis. The investigation unit analyzes the server log data and focuses its investigation on parts where errors frequently occur. The investigation unit can also analyze monitoring data to identify time periods and conditions when abnormalities are likely to occur. This allows for focused analysis of parts that are prone to abnormalities, thereby quickly identifying the location of the failure. Some or all of the above-mentioned processing by the investigation unit may be performed using, for example, AI, or may be performed without using AI. For example, the investigation unit can input the server log data and monitoring data into the generation AI and have the generation AI perform an analysis of parts that are prone to abnormalities.

[0074] The investigation unit can analyze server log data and monitoring data in real time and immediately identify the location of a failure. For example, the investigation unit analyzes server log data in real time and immediately identify the location of a failure if an abnormality is detected. The investigation unit can also analyze monitoring data in real time and immediately identify the location of a failure if an abnormality occurs. The investigation unit can also perform an integrated analysis of log data and monitoring data in real time and quickly identify the location of a failure. This allows for real-time analysis to quickly identify the location of a failure and respond immediately. Some or all of the above-mentioned processing in the investigation unit may be performed using, for example, AI, or may be performed without using AI. For example, the investigation unit can input log data and monitoring data acquired in real time into a generation AI and have the generation AI identify the location of a failure.

[0075] The research unit can estimate the user's emotions and prioritize the research results based on the estimated user emotions. For example, the research unit can estimate the user's emotions and prioritize the research results based on the estimated user emotions. When the user is feeling stressed, the research unit can prioritize displaying important research results. When the user is relaxed, the research unit can also prioritize displaying detailed research results. Furthermore, when the user is in a hurry, the research unit can quickly display the most important research results. This allows important information to be prioritized by prioritizing the research results based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the research unit can be performed using, for example, AI, or without AI. For example, the research unit can input user emotion data into the generation AI and have the generation AI determine the priority of the research results.

[0076] The investigation unit can analyze network traffic data in addition to server log data and monitoring data. For example, the investigation unit analyzes network traffic data in addition to server log data and monitoring data to detect anomalies. The investigation unit analyzes network traffic data to identify network problems related to server anomalies. The investigation unit can also perform an integrated analysis of log data, monitoring data, and network traffic data to identify the cause of anomalies. In this way, by analyzing network traffic data as well, anomalies can be identified based on a wider range of data. Some or all of the above-mentioned processing in the investigation unit may be performed using, for example, AI, or may be performed without using AI. For example, the investigation unit can input network traffic data into a generation AI and have the generation AI detect and identify anomalies.

[0077] When analyzing server log data and monitoring data, the investigation department can also refer to data from other similar systems. For example, the investigation department refers to log data and monitoring data from other similar systems to identify abnormality patterns. The investigation department quickly identifies server abnormalities based on data from other systems. The investigation department can also analyze data from other systems to identify the cause of the server abnormality. By referring to data from other similar systems, the abnormality pattern can be more accurately identified. Some or all of the above-mentioned processing by the investigation department may be performed using, for example, AI, or may be performed without using AI. For example, the investigation department can input data from other similar systems into the generation AI and have the generation AI identify abnormality patterns.

[0078] The presentation unit can estimate the user's emotions and adjust the presentation method of the recovery methods based on the estimated user emotions. For example, the presentation unit can estimate the user's emotions and adjust the presentation method of the recovery methods based on the estimated user emotions. When the user is feeling stressed, the presentation unit presents simple, highly visible recovery methods. When the user is relaxed, the presentation unit can also present detailed recovery methods. When the user is in a hurry, the presentation unit can also present recovery methods that focus on the main points. This allows the presentation method of the recovery methods to be adjusted based on the user's emotions, making it easy for the user to understand. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the presentation unit may be performed using an AI, for example, or without an AI. For example, the presentation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the presentation method of the recovery methods.

[0079] The presentation unit can prioritize suggesting methods with a particularly high success rate from among past failure response histories and best practices. The presentation unit, for example, analyzes past failure response histories and prioritizes suggesting recovery methods with a high success rate. The presentation unit proposes the optimal recovery method based on best practices. The presentation unit can also create a database of methods with high success rates and prioritize suggesting them. This improves the success rate of recovery by prioritizing the suggestion of methods with a high success rate. Some or all of the above-mentioned processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input past failure response histories into a generation AI and cause the generation AI to suggest recovery methods with a high success rate.

[0080] The presentation unit can collect feedback on the presented recovery method and reflect it in the next proposal. The presentation unit, for example, collects feedback from an operator and reflects it in the next proposal. The presentation unit evaluates the effectiveness of the recovery method and makes improvements based on the feedback. The presentation unit can also create a database of feedback and use it in the next proposal. In this way, by collecting feedback and reflecting it in the next proposal, the accuracy of the proposal is improved. Some or all of the above-mentioned processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input feedback data from an operator into the generation AI and cause the generation AI to execute processing to reflect the feedback in the next proposal.

[0081] The presentation unit can estimate the user's emotions and adjust the level of detail of the recovery method based on the estimated user's emotions. For example, the presentation unit can estimate the user's emotions and adjust the level of detail of the recovery method based on the estimated user's emotions. When the user is stressed, the presentation unit presents a simple and to-the-point recovery method. When the user is relaxed, the presentation unit can also present a detailed recovery method. Furthermore, when the user is in a hurry, the presentation unit can present a recovery method that can be quickly implemented. This allows the user to receive an optimal amount of information by adjusting the level of detail of the recovery method based on the user's emotions. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the presentation unit can be performed using an AI, for example, or without an AI. For example, the presentation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the level of detail of the recovery method.

[0082] The presentation unit can refer to the opinions of external experts in addition to past failure response history and best practices. For example, the presentation unit refers to the opinions of external experts and proposes an optimal recovery method. The presentation unit creates a database of expert opinions and uses them to propose recovery methods. The presentation unit can also improve the recovery method based on the expert opinions. In this way, by also referring to the opinions of external experts, it is possible to propose a more reliable recovery method. Some or all of the above-mentioned processing in the presentation unit may be performed using, for example, AI, or may be performed without using AI. For example, the presentation unit can input the opinion data of external experts into the generation AI and cause the generation AI to execute processing to reflect the opinion data in the proposed recovery method.

[0083] The presentation unit can present multiple options for the proposed recovery method, allowing the operator to select one. The presentation unit, for example, presents multiple recovery methods, allowing the operator to select the optimal method. The presentation unit presents the advantages and disadvantages of each recovery method, making it easier for the operator to select. The presentation unit can also reflect the operator's selection in the next proposal. In this way, by presenting multiple options, the operator can select the optimal method. Some or all of the above-mentioned processing in the presentation unit may be performed, for example, using AI, or may be performed without using AI. For example, the presentation unit can input data of multiple recovery methods into the generation AI and cause the generation AI to present the options.

[0084] The execution unit can estimate the user's emotions and adjust the progress speed of the execution procedure based on the estimated user emotions. For example, the execution unit can estimate the user's emotions and adjust the progress speed of the execution procedure based on the estimated user emotions. If the user is feeling stressed, the execution unit can slow down the progress speed of the execution procedure to reduce the user's burden. The execution unit can also maintain the progress speed of the execution procedure at a normal level if the user is relaxed. Furthermore, if the user is in a hurry, the execution unit can speed up the progress speed of the execution procedure to quickly complete execution. This reduces the user's burden and enables efficient execution by adjusting the progress speed of the execution procedure based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the execution unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the execution unit can input the user's emotional data into the generation AI and cause the generation AI to adjust the progress speed of the execution procedure.

[0085] The execution unit can highlight particularly important steps in the execution procedure and prompt the operator to confirm them. For example, the execution unit can highlight particularly important steps in the execution procedure and prompt the operator to confirm them. The execution unit can display a pop-up for an important step requesting the operator's confirmation. The execution unit can also send a message requesting the operator's confirmation before executing an important step. By highlighting important steps in this way, the operator can be sure to confirm them and prevent mistakes. Some or all of the above-mentioned processing in the execution unit may be performed using AI, for example, or may be performed without using AI. For example, the execution unit can input information about important steps into the generation AI and have the generation AI execute processing to prompt confirmation.

[0086] The execution unit records the results of the execution procedure in detail, which can be used to respond to the next failure. For example, the execution unit records the results of each step of the execution procedure in detail, which can be used to respond to the next failure. The execution unit creates a database of the results of the execution procedure, which can be referenced by operators. The execution unit can also analyze the results of the execution procedure and reflect them in the next proposal. In this way, by recording the results of the execution procedure in detail, it can be used to respond to the next failure. Some or all of the above-mentioned processing in the execution unit may be performed using, for example, AI, or may be performed without using AI. For example, the execution unit can input result data of the execution procedure into a generation AI and have the generation AI execute processing to be used to respond to the next failure.

[0087] The execution unit can estimate the user's emotions and determine the priority of execution steps based on the estimated user emotions. For example, the execution unit can estimate the user's emotions and determine the priority of execution steps based on the estimated user emotions. When the user is feeling stressed, the execution unit can prioritize important execution steps. When the user is relaxed, the execution unit can also proceed with execution steps with normal priority. Furthermore, when the user is in a hurry, the execution unit can quickly execute the most important execution steps. This allows important steps to be prioritized by determining the priority of execution steps based on the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the execution unit can be performed using an AI, for example, or without an AI. For example, the execution unit can input the user's emotion data into the generation AI and have the generation AI determine the priority of execution steps.

[0088] The execution unit can present, in addition to the execution procedure, auxiliary procedures that the operator should perform manually. For example, the execution unit presents, in addition to the execution procedure, auxiliary procedures that the operator should perform manually. The execution unit explains the auxiliary procedures in detail to make it easier for the operator to understand. The execution unit can also present points to note when performing the auxiliary procedures and prompt the operator to check them. In this way, by presenting the auxiliary procedures, the operator can easily understand the procedures that should be performed manually. Some or all of the above-mentioned processing in the execution unit may be performed using, for example, AI, or may be performed without using AI. For example, the execution unit can input information about the auxiliary procedures to a generation AI and have the generation AI perform the presentation.

[0089] The execution unit can include, in the execution procedure, a procedure that takes into account cooperation with other systems and devices. For example, the execution unit includes, in the execution procedure, a procedure that takes into account cooperation with other systems and devices. The execution unit refers to the configuration information of the systems and devices that are to be linked and proposes an optimal procedure. The execution unit can also monitor the status of the systems and devices that are to be linked and adjust the procedure as necessary. This makes it possible to execute a more comprehensive recovery procedure by taking into account cooperation with other systems and devices. Some or all of the above-mentioned processing in the execution unit may be performed using, for example, AI, or may be performed without using AI. For example, the execution unit can input information about other systems and devices into the generation AI and cause the generation AI to execute a procedure that takes into account cooperation. === Hard Collateral 1-1 === Each of the multiple elements including the learning unit, investigation unit, presentation unit, and execution unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the smart device 14 and studies the server configuration diagram and design documents. The investigation unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes the server log data and monitoring data to identify the fault location. The presentation unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and proposes an optimal recovery method. The execution unit is realized, for example, by the control unit 46A of the smart device 14 and automatically executes the approved recovery procedure. === Hard Collateral 1-2 === Each of the multiple elements including the learning unit, investigation unit, presentation unit, and execution unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the smart glasses 214 and learns the server configuration diagram and design document. The investigation unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes the server log data and monitoring data to identify the fault location. The presentation unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and proposes an optimal recovery method. The execution unit is realized, for example, by the control unit 46A of the smart glasses 214 and automatically executes the approved recovery procedure. === Hard Collateral 1-3 === Each of the multiple elements including the learning unit, investigation unit, presentation unit, and execution unit described above is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the headset type terminal 314 and studies the server configuration diagram and design documents. The investigation unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes the server log data and monitoring data to identify the fault location. The presentation unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and proposes an optimal recovery method. The execution unit is realized, for example, by the control unit 46A of the headset type terminal 314 and automatically executes the approved recovery procedure. === Hard Collateral 1-4 === Each of the multiple elements including the learning unit, investigation unit, presentation unit, and execution unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the learning unit is realized by the control unit 46A of the robot 414 and studies the server configuration diagram and design documents. The investigation unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and analyzes the server log data and monitoring data to identify the fault location. The presentation unit is realized, for example, by the identification processing unit 290 of the data processing device 12 and proposes an optimal recovery method. The execution unit is realized, for example, by the control unit 46A of the robot 414 and automatically executes the approved recovery procedure.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The learning unit can study the server's operation manual and troubleshooting guide in addition to the server configuration diagram and design document. For example, the learning unit studies the server's operation manual to understand operation procedures and best practices. The learning unit studies the troubleshooting guide to learn how to respond when a failure occurs. The learning unit can also grasp the overall picture of the server based on the operation manual and troubleshooting guide. In this way, by studying the server's operation manual and troubleshooting guide, more comprehensive knowledge can be acquired. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, AI, or may be performed without using AI. For example, the learning unit can input data from the server's operation manual and troubleshooting guide into the generation AI and have the generation AI perform learning.

[0092] The investigation unit can analyze network traffic data in addition to server log data and monitoring data. For example, the investigation unit analyzes network traffic data in addition to server log data and monitoring data to detect anomalies. The investigation unit analyzes network traffic data to identify network problems related to server anomalies. The investigation unit can also perform an integrated analysis of log data, monitoring data, and network traffic data to identify the cause of anomalies. In this way, by analyzing network traffic data as well, anomalies can be identified based on a wider range of data. Some or all of the above-mentioned processing in the investigation unit may be performed using, for example, AI, or may be performed without using AI. For example, the investigation unit can input network traffic data to a generation AI and have the generation AI detect and identify anomalies.

[0093] The presentation unit can present multiple options for the proposed recovery method, allowing the operator to select the most suitable method. For example, the presentation unit can present multiple recovery methods, allowing the operator to select the most suitable method. The presentation unit can present the advantages and disadvantages of each recovery method, making it easier for the operator to select. The presentation unit can also reflect the operator's selection in the next proposal. In this way, by presenting multiple options, the operator can select the most suitable method. Some or all of the above-described processing in the presentation unit may be performed using, or without, AI, for example. For example, the presentation unit can input data on multiple recovery methods into the generation AI and cause the generation AI to present the options.

[0094] The execution unit can highlight particularly important steps in the execution procedure and prompt the operator to confirm them. For example, the execution unit can highlight particularly important steps in the execution procedure and prompt the operator to confirm them. The execution unit can display a pop-up for an important step requesting the operator's confirmation. The execution unit can also send a message requesting the operator's confirmation before executing an important step. By highlighting important steps in this way, the operator can be sure to confirm them and prevent mistakes. Some or all of the above-mentioned processing in the execution unit may be performed using AI, for example, or may be performed without using AI. For example, the execution unit can input information about important steps into the generation AI and have the generation AI execute processing to prompt confirmation.

[0095] The execution unit records the results of the execution procedure in detail, which can be used to respond to the next failure. For example, the execution unit records the results of each step of the execution procedure in detail, which can be used to respond to the next failure. The execution unit creates a database of the results of the execution procedure, which can be referenced by operators. The execution unit can also analyze the results of the execution procedure and reflect them in the next proposal. In this way, by recording the results of the execution procedure in detail, it can be used to respond to the next failure. Some or all of the above-mentioned processing in the execution unit may be performed using, for example, AI, or may be performed without using AI. For example, the execution unit can input result data of the execution procedure into a generation AI and have the generation AI execute processing to be used to respond to the next failure.

[0096] The learning unit can estimate a user's emotions and prioritize the learning data based on the estimated user emotions. For example, the learning unit estimates a user's emotions and prioritizes the learning data based on the estimated user emotions. When a user is stressed, the learning unit prioritizes learning of important server configuration diagrams and design documents. Furthermore, when a user is relaxed, the learning unit can prioritize learning of detailed design documents and supplementary materials. Furthermore, when a user is in a hurry, the learning unit can quickly learn the most important information and postpone other information. This enables optimal learning tailored to the user's situation by prioritizing the learning data based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the learning unit may be performed using, for example, an AI, or without an AI. For example, the learning unit can input user emotion data into the generation AI and have the generation AI determine the priorities of the learning data.

[0097] The research unit can estimate the user's emotions and adjust the display method of the survey results based on the estimated user emotions. For example, the research unit estimates the user's emotions and adjusts the display method of the survey results based on the estimated user emotions. If the user is feeling stressed, the research unit provides a simple, highly visible display method. If the user is relaxed, the research unit can provide a display method that includes detailed information. If the user is in a hurry, the research unit can provide a display method that focuses on the main points. This allows the display method of the survey results to be adjusted based on the user's emotions, making it easy for the user to view. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the research unit can be performed using AI, for example, or without AI. For example, the research unit can input user emotion data into the generation AI and have the generation AI adjust the display method of the survey results.

[0098] The presentation unit can estimate the user's emotions and adjust the presentation method of the recovery methods based on the estimated user emotions. For example, the presentation unit can estimate the user's emotions and adjust the presentation method of the recovery methods based on the estimated user emotions. When the user is feeling stressed, the presentation unit presents simple, highly visible recovery methods. When the user is relaxed, the presentation unit can also present detailed recovery methods. When the user is in a hurry, the presentation unit can also present recovery methods that focus on the main points. This allows the presentation method of the recovery methods to be adjusted based on the user's emotions, making it easier for the user to understand. The emotion estimation is realized using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-described processing in the presentation unit can be performed using, for example, an AI, or can be performed without using an AI. For example, the presentation unit can input the user's emotion data into the generation AI and cause the generation AI to adjust the presentation method of the recovery methods.

[0099] The execution unit can estimate the user's emotions and adjust the speed at which the execution procedure proceeds based on the estimated user emotions. For example, the execution unit can estimate the user's emotions and adjust the speed at which the execution procedure proceeds based on the estimated user emotions. If the user is feeling stressed, the execution unit can slow down the speed at which the execution procedure proceeds to reduce the user's burden. The execution unit can also maintain the normal speed at which the execution procedure proceeds when the user is relaxed. Furthermore, if the user is in a hurry, the execution unit can speed up the speed at which the execution procedure proceeds to quickly complete the execution. This reduces the user's burden and enables efficient execution by adjusting the speed at which the execution procedure proceeds based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the execution unit can be performed using, for example, an AI, or without an AI. For example, the execution unit can input the user's emotional data into the generation AI and cause the generation AI to adjust the progress speed of the execution procedure.

[0100] The execution unit can estimate the user's emotions and prioritize the execution steps based on the estimated user emotions. For example, the execution unit can estimate the user's emotions and prioritize the execution steps based on the estimated user emotions. When the user is stressed, the execution unit can prioritize important execution steps. When the user is relaxed, the execution unit can also proceed with execution steps with normal priority. Furthermore, when the user is in a hurry, the execution unit can quickly execute the most important execution steps. This allows important steps to be prioritized by prioritizing the execution steps based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above-mentioned processing in the execution unit can be performed using an AI, for example, or without an AI. For example, the execution unit can input the user's emotion data into the generation AI and have the generation AI determine the priority of the execution steps.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The learning unit studies the server's configuration diagrams and design documents. For example, the learning unit studies the server's configuration diagrams and design documents as PDFs, image data, or text data. The learning unit analyzes these documents and acquires knowledge about the server's configuration and design. For example, by studying the server's hardware configuration and software settings, the learning unit can grasp the overall picture of the server. Step 2: The investigation unit investigates the location of the server failure based on the information learned by the learning unit. For example, the investigation unit analyzes the server log data and monitoring data and identifies the location of the failure using an anomaly detection algorithm. The investigation unit can extract error messages from the server log data and identify the location of the failure. This allows the cause of the failure to be quickly identified. Step 3: The presentation unit presents a recovery method based on the fault location identified by the investigation unit. For example, the presentation unit may create a database of past failure response history and best practices to propose the optimal recovery method. For specific error messages, the presentation unit can present specific recovery procedures such as rebooting or changing settings. Step 4: The execution unit, where a human operator checks the recovery methods presented by the presentation unit, automatically executes the operations that have been approved. For example, the execution unit automatically executes the proposed recovery procedures after receiving approval from the operator. The execution unit can automatically restart the server or change settings to recover from the failure.

[0103] 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.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0105] 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.

[0106] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[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] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0123] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0124] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification 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 identification processing unit 290 using these models.

[0134] 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.

[0135] 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.

[0136] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0137] 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.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0151] 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.

[0152] 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.

[0153] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0154] 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.

[0155] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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."

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] [Explanation of symbols]

[0175] 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 unit that learns a server configuration diagram or design document; an investigation unit that investigates the location of a failure in the server based on the information learned by the learning unit; a presentation unit that presents a recovery method based on the failure location investigated by the investigation unit; an execution unit that allows a human operator to confirm the recovery method presented by the presentation unit and automatically executes the approved operation. A system characterized by:

2. The learning unit Study server configuration diagrams or design documents as PDF, image data, or text data 2. The system of claim 1.

3. The research department Analyzes server log data or monitoring data and identifies the location of the failure using an anomaly detection algorithm 2. The system of claim 1.

4. The presentation unit We create a database of past failure response history and best practices to propose optimal recovery methods.

2. The system of claim 1.

5. The execution unit: With operator approval, the proposed recovery steps are automatically executed 2. The system of claim 1.

6. The execution unit: Use automated tools to perform recovery procedures 2. The system of claim 1.

7. The learning unit Estimate user emotions and prioritize training data based on the estimated user emotions.

2. The system of claim 1.

8. The learning unit Track the update history of server configuration diagrams or design documents to always learn the latest information 2. The system of claim 1.

Images