system

Abstract

The system according to this embodiment aims to autonomously detect system abnormalities using AI and perform corrective or preventative maintenance. [Solution] The system according to the embodiment comprises a detection unit, a correction unit, a warning unit, and a scheduling unit. The detection unit detects abnormalities. The correction unit performs corrections and adjustments based on the abnormalities detected by the detection unit. The warning unit issues a warning based on the results of the corrections and adjustments performed by the correction unit. The scheduling unit schedules preventive maintenance based on the warnings issued by the warning unit.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the detection and correction of system anomalies depend on the experience and intuition of administrators, and there is a problem that efficient management is difficult.

[0005] The system according to the embodiment aims to autonomously detect system anomalies by utilizing AI and perform corrections and preventive maintenance.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a detection unit, a correction unit, a warning unit, and a scheduling unit. The detection unit detects abnormalities. The correction unit performs corrections and adjustments based on the abnormalities detected by the detection unit. The warning unit issues a warning based on the results of the corrections and adjustments performed by the correction unit. The scheduling unit schedules preventive maintenance based on the warnings issued by the warning unit. [Effects of the Invention]

[0007] The system according to this embodiment can use AI to autonomously detect system abnormalities and perform corrective or preventative maintenance. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between multiple computers. Examples of communication standards applicable to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction 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 a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The system monitoring agent according to the embodiment of the present invention is an innovative solution that supports the monitoring of various systems, from conventional IT infrastructure to the latest general-purpose AI and LLM. This system monitoring agent detects anomalies using a data-driven approach that leverages AI algorithms. When an anomaly is detected, it automatically corrects and adjusts, improving system uptime while minimizing administrator intervention. Furthermore, when a general-purpose AI takes unexpected actions, it issues an early warning and provides appropriate countermeasures, minimizing the risk of AI malfunction. This significantly advances the safe operation and social acceptance of AI. In addition, the autonomous AI agent collaborates with other systems and AI agents within the enterprise to perform cross-system anomaly detection and response, thereby strengthening the security of the entire system. Furthermore, an AI agent with planning capabilities predicts system performance and automatically schedules preventative maintenance, minimizing system downtime. For example, the system monitoring agent analyzes system performance data and detects anomalous patterns. Next, when the system monitoring agent detects an anomaly, it automatically changes system settings or reallocates resources. This improves system uptime while minimizing administrator intervention. Furthermore, the system monitoring agent issues early warnings and provides appropriate countermeasures when the general-purpose AI behaves unexpectedly. For example, if the AI ​​detects abnormal behavior, it warns the administrator and suggests countermeasures. This minimizes the risk of the AI ​​running amok. The system monitoring agent also collaborates with other systems and AI agents within the enterprise to perform cross-system anomaly detection and response. For example, it shares data across multiple systems and coordinates responses when an anomaly is detected. This enhances the security of the entire system. In addition, the system monitoring agent has an AI agent with planning capabilities that predicts system performance and automatically schedules preventative maintenance. For example, it analyzes system performance data to predict future performance degradation and schedule maintenance accordingly.This minimizes system downtime. As a result, system monitoring agents can improve system uptime and significantly advance the secure operation and social acceptance of AI.

[0029] The system monitoring agent according to the embodiment comprises a detection unit, a correction unit, a warning unit, and a scheduling unit. The detection unit detects anomalies. The detection unit, for example, analyzes system performance data and detects abnormal patterns. The detection unit can, for example, monitor system resource utilization and error logs to detect abnormal operation. The detection unit can also, for example, monitor system response time and throughput to detect abnormal performance degradation. The correction unit performs corrections and adjustments based on the anomalies detected by the detection unit. The correction unit, for example, automatically changes system settings. The correction unit can, for example, reallocate system resources. The correction unit can, for example, adjust system parameters to correct anomalies. The warning unit issues warnings based on the results of corrections and adjustments made by the correction unit. The warning unit, for example, issues a warning to the administrator when it detects abnormal operation and suggests countermeasures. The warning unit can, for example, send email notifications or display alerts. The warning unit can, for example, display warning messages on the system dashboard. The scheduling unit schedules preventative maintenance based on warnings issued by the warning unit. The scheduling unit can, for example, analyze system performance data to predict future performance degradation and schedule maintenance accordingly. The scheduling unit can also schedule, for example, periodic software updates and hardware inspections. The scheduling unit can also adjust the timing of maintenance according to the system's operating status. As a result, the system monitoring agent according to the embodiment can automate a series of processes from anomaly detection to correction, warning, and maintenance scheduling, thereby improving system uptime.

[0030] The detection unit detects anomalies. For example, the detection unit analyzes system performance data and detects abnormal patterns. Specifically, it can monitor system resource usage and error logs to detect abnormal behavior. For example, it can detect abnormal patterns in real time, such as a sudden increase in CPU usage, abnormally high memory usage, or excessive disk I / O. Furthermore, it can monitor system response time and throughput to detect abnormal performance degradation. For example, it continuously monitors performance indicators such as web server response times being longer than usual or database query processing times being delayed. The detection unit collects this data and performs anomaly detection using AI algorithms. The AI ​​compares it with past normal operation data to identify abnormal patterns. For example, it uses machine learning models to learn normal operation patterns and detect anomalies in real time. This allows the detection unit to quickly and accurately detect system anomalies and maintain system stability. Furthermore, the detection unit continuously learns to improve the accuracy of anomaly detection and to be able to respond to new anomaly patterns. This enables the detection unit to detect system anomalies early and respond quickly.

[0031] The correction unit performs corrections and adjustments based on anomalies detected by the detection unit. For example, the correction unit can automatically change system settings. Specifically, it can reallocate system resources. For instance, it can dynamically change CPU and memory allocations to prevent excessive resource usage. It can also adjust system parameters to correct anomalies. For example, it can improve system performance by adjusting database cache size or optimizing network bandwidth. The correction unit uses scripts and automation tools to automate these correction tasks. For example, when an anomaly is detected, it executes a predefined script to perform the necessary corrections. The correction unit also uses AI to optimize correction tasks. The AI ​​analyzes past correction history and system status to propose the optimal correction method. This allows the correction unit to correct anomalies quickly and effectively, maintaining system stability. Furthermore, the correction unit can record the results of correction tasks to help with future anomaly response. This allows the correction unit to quickly correct system anomalies and improve system uptime.

[0032] The warning unit issues warnings based on the results of corrections and adjustments made by the correction unit. For example, the warning unit will warn administrators when it detects abnormal operation and suggest countermeasures. Specifically, it can send email notifications or display alerts. For example, it can display warning messages on the system dashboard to provide administrators with detailed information about the anomaly. The warning unit can also propose specific countermeasures to administrators when an anomaly occurs. For example, it can suggest specific actions such as restarting the system, stopping specific services, or changing settings. The warning unit sends these warnings in real time to enable administrators to respond quickly. Furthermore, the warning unit can set warning priorities and use different notification methods depending on the severity. For example, in the case of a serious anomaly, it can notify via voice call or SMS to encourage a quick response. The warning unit can also record past warning history and analyze trends in anomaly occurrence. This allows the warning unit to support early detection and rapid response to anomalies, maintaining system stability.

[0033] The scheduling unit schedules preventative maintenance based on warnings issued by the warning unit. For example, the scheduling unit analyzes system performance data to predict future performance degradation and schedule maintenance accordingly. Specifically, it can schedule regular software updates and hardware inspections. For instance, it adjusts the optimal maintenance timing based on the system's operating status. The scheduling unit uses scheduling tools to automate these maintenance tasks. For example, it uses a calendar function to manage maintenance schedules and set reminders. Furthermore, the scheduling unit uses AI to optimize maintenance. The AI ​​analyzes past maintenance history and system status to propose the optimal maintenance schedule. This allows the scheduling unit to efficiently perform preventative maintenance and improve system uptime. Additionally, the scheduling unit can record the results of maintenance work and use this information to inform future maintenance plans. This allows the scheduling unit to maintain system stability and improve long-term operational efficiency.

[0034] The system monitoring agent according to this embodiment includes a collaboration unit that cooperates with other systems and AI agents. The collaboration unit, for example, shares data among multiple systems and cooperates to respond when an anomaly is detected. The collaboration unit can cooperate with monitoring systems and data analysis agents to perform anomaly detection and response. The collaboration unit can also share data among systems in real time and detect anomalies early. This enables cross-system anomaly detection and response by coordinating with other systems and AI agents. Some or all of the above-described processing in the collaboration unit may be performed using AI, for example, or without AI. For example, the collaboration unit can optimize data sharing with other systems and AI agents using AI.

[0035] The system monitoring agent according to the embodiment includes a prediction unit that predicts the performance of the system. The prediction unit, for example, analyzes system performance data and predicts future performance degradation. The prediction unit can, for example, analyze system resource utilization and response time to predict future load increases. The prediction unit can also, for example, analyze system traffic patterns to predict future traffic increases. This allows for the automatic scheduling of preventative maintenance by predicting system performance. Some or all of the above-described processes in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can analyze system performance data using AI to predict future performance degradation.

[0036] The detection unit can analyze system performance data and detect abnormal patterns. For example, the detection unit can monitor system resource utilization and error logs to detect abnormal behavior. The detection unit can also monitor system response time and throughput to detect abnormal performance degradation. This makes it easier to detect abnormal patterns by analyzing system performance data. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can analyze system performance data using AI to detect abnormal patterns.

[0037] The correction unit can automatically change system settings. For example, the correction unit can adjust system parameters and correct anomalies. For example, the correction unit can automatically update system configuration files. For example, the correction unit can optimize system settings and correct anomalies. This allows for a rapid response to anomalies by automatically changing system settings. Some or all of the above-described processes in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can optimize system setting changes using AI.

[0038] The modification unit can reallocate resources. For example, the modification unit can reallocate resources by changing the allocation of the system's CPU and memory. The modification unit can also reallocate the system's storage resources. The modification unit can also reallocate the system's network resources. By reallocating resources in this way, the system's utilization can be optimized. Some or all of the above processing in the modification unit may be performed using AI, for example, or without AI. For example, the modification unit can optimize resource reallocation using AI.

[0039] The warning unit can alert administrators and suggest countermeasures when it detects abnormal behavior. For example, the warning unit can send email notifications or display alerts. The warning unit can also display warning messages on the system dashboard. For example, the warning unit can send voice alerts or SMS notifications. This enables a quick response by alerting administrators and suggesting countermeasures when abnormal behavior is detected. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, when the warning unit detects abnormal behavior, it can use AI to suggest the optimal countermeasure.

[0040] The collaboration unit can share data between multiple systems and coordinate responses when an anomaly is detected. For example, the collaboration unit can collaborate with monitoring systems and data analysis agents to detect and respond to anomalies. The collaboration unit can also share data between systems in real time to detect anomalies early. For example, when an anomaly is detected, the collaboration unit can coordinate with other systems to execute countermeasures. This strengthens the overall system security by sharing data between multiple systems and coordinating responses when an anomaly is detected. Some or all of the above-described processes in the collaboration unit may be performed using AI, for example, or without AI. For example, the collaboration unit can optimize data sharing with other systems and AI agents using AI.

[0041] The prediction unit can analyze system performance data and predict future performance degradation. For example, the prediction unit can analyze system resource utilization and response time to predict future load increases. The prediction unit can also analyze system traffic patterns to predict future traffic increases. For example, the prediction unit can predict future performance degradation based on system performance data and schedule preventative maintenance. This allows for the planning of preventative maintenance by analyzing system performance data and predicting future performance degradation. Some or all of the above processing in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can analyze system performance data using AI to predict future performance degradation.

[0042] The detection unit can improve detection accuracy by learning anomaly patterns by referring to past anomaly data from the system when detecting an anomaly. For example, the detection unit can improve detection accuracy by learning the frequency and patterns of anomalies based on past anomaly data. The detection unit can also improve detection accuracy by clustering anomaly data and applying different detection algorithms for each type of anomaly. The detection unit can also improve detection accuracy by analyzing anomaly data over time and predicting the timing of anomaly occurrence. In this way, the accuracy of anomaly detection is improved by learning anomaly patterns by referring to past anomaly data. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can learn anomaly patterns by analyzing past anomaly data using AI.

[0043] The detection unit can adjust the frequency of anomaly detection according to the system's operating status and load when detecting an anomaly. For example, if the system load is high, the detection unit can increase the frequency of anomaly detection to respond quickly. For example, if the system load is low, the detection unit can also reduce the frequency of anomaly detection to conserve resources. The detection unit can also dynamically adjust the frequency of anomaly detection according to the system's operating status to perform optimal detection. This allows for resource optimization by adjusting the frequency of anomaly detection according to the system's operating status and load. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can analyze the system's operating status and load using AI and dynamically adjust the frequency of anomaly detection.

[0044] The correction unit can select the optimal correction method by referring to the system's past correction history when correcting an anomaly. For example, the correction unit can select the optimal correction method based on the past correction history. The correction unit can also cluster the correction history and apply different correction methods to each type of anomaly. The correction unit can also analyze the correction history over time to identify the optimal correction timing. This improves the accuracy of corrections by selecting the optimal correction method by referring to the past correction history. Some or all of the above processes in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can analyze the past correction history using AI and select the optimal correction method.

[0045] The correction unit can adjust the timing of corrections according to the current system load when correcting anomalies. For example, if the system load is high, the correction unit can delay the timing of corrections to conserve resources. For example, if the system load is low, the correction unit can also advance the timing of corrections to respond quickly. For example, the correction unit can dynamically adjust the timing of corrections according to the system load to perform the optimal correction. This allows for resource optimization by adjusting the timing of corrections according to the system load. Some or all of the above processing in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can analyze the system load using AI and dynamically adjust the timing of corrections.

[0046] The warning unit can improve the accuracy of warnings by referring to the system's past warning data when issuing a warning. For example, the warning unit can learn the frequency and patterns of warning occurrences based on past warning data to improve warning accuracy. The warning unit can also cluster the warning data and apply different warning algorithms to each type of warning. For example, the warning unit can analyze the warning data over time to predict the timing of warning occurrences and improve warning accuracy. This allows for more accurate warnings by improving warning accuracy by referring to past warning data. Some or all of the above processes in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can analyze past warning data using AI to improve warning accuracy.

[0047] The warning unit can adjust the timing of warnings according to the current operating status of the system when issuing a warning. For example, if the system's operating status is high, the warning unit can advance the warning timing to allow for a quicker response. For example, if the system's operating status is low, the warning unit can delay the warning timing to conserve resources. The warning unit can also dynamically adjust the warning timing according to the system's operating status to provide the most appropriate warning. This allows for resource optimization by adjusting the warning timing according to the system's operating status. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can analyze the system's operating status using AI and dynamically adjust the warning timing.

[0048] The scheduling unit can create an optimal maintenance schedule by referring to the system's past maintenance data. For example, the scheduling unit can create an optimal maintenance schedule based on past maintenance data. The scheduling unit can also cluster maintenance data and create an optimal schedule for each different system. The scheduling unit can also analyze maintenance data over time to identify the optimal maintenance timing. This improves the accuracy of maintenance by creating an optimal schedule by referring to past maintenance data. Some or all of the above processes in the scheduling unit may be performed using AI, for example, or without AI. For example, the scheduling unit can analyze past maintenance data using AI to create an optimal maintenance schedule.

[0049] The scheduling unit can adjust the timing of maintenance schedules according to the current system operating status. For example, if the system operating status is high, the scheduling unit can delay the maintenance schedule to conserve resources. For example, if the system operating status is low, the scheduling unit can also advance the maintenance schedule to respond quickly. For example, the scheduling unit can dynamically adjust the timing of the maintenance schedule according to the system operating status to perform optimal maintenance. This allows for resource optimization by adjusting the timing of the schedule according to the system operating status. Some or all of the above processing in the scheduling unit may be performed using AI, for example, or without AI. For example, the scheduling unit can analyze the system operating status using AI and dynamically adjust the timing of the maintenance schedule.

[0050] The scheduling unit can determine the scope of maintenance impact by considering the geographical distribution of the system when scheduling maintenance. For example, the scheduling unit can determine the scope of impact based on geographical information of the locations where maintenance is needed. For example, the scheduling unit can extend the scope of impact by performing maintenance on systems surrounding the locations where maintenance is needed. For example, the scheduling unit can visualize the geographical distribution of the locations where maintenance is needed and determine the scope of impact. This allows for more appropriate maintenance by determining the scope of maintenance impact by considering the geographical distribution of the system. Some or all of the above processing in the scheduling unit may be performed using AI, for example, or without AI. For example, the scheduling unit can analyze the geographical distribution of the system using AI and determine the scope of maintenance impact.

[0051] The scheduling unit can improve the accuracy of its maintenance schedule by referring to relevant system performance data. For example, the scheduling unit can create an optimal maintenance schedule based on performance data. The scheduling unit can also cluster performance data and create an optimal schedule for different systems. For example, the scheduling unit can analyze performance data over time to identify the optimal maintenance timing. This allows for more appropriate maintenance by improving the accuracy of the schedule by referring to relevant system performance data. Some or all of the above processes in the scheduling unit may be performed using AI, for example, or without AI. For example, the scheduling unit can analyze system performance data using AI and create an optimal maintenance schedule.

[0052] The integration unit can select the optimal integration method by referring to past integration data of other systems when integrating with other systems. For example, the integration unit can select the optimal integration method based on past integration data. The integration unit can also cluster the integration data and select the optimal integration method for each different system. The integration unit can also analyze the integration data over time to identify the optimal integration timing. By selecting the optimal integration method by referring to past integration data, the accuracy of the integration is improved. Some or all of the above processing in the integration unit may be performed using AI, for example, or without AI. For example, the integration unit can analyze past integration data using AI and select the optimal integration method.

[0053] The integration unit can identify the scope of impact of integration by considering the geographical distribution of systems when integrating with other systems. For example, the integration unit can identify the scope of impact based on geographical information of the locations where integration is required. The integration unit can also extend its scope of impact by integrating with systems surrounding the locations where integration is required. For example, the integration unit can visualize the geographical distribution of the locations where integration is required and identify the scope of impact. This allows for more appropriate integration by identifying the scope of impact of integration by considering the geographical distribution of systems. Some or all of the above processing in the integration unit may be performed using AI, for example, or without AI. For example, the integration unit can analyze the geographical distribution of systems using AI and identify the scope of impact of integration.

[0054] The integration unit can improve the accuracy of integration by referring to relevant log data from other systems when integrating with them. For example, the integration unit can analyze log data that requires integration and select the optimal integration method. The integration unit can also cluster log data and select the optimal integration method for each different system. The integration unit can also perform time-series analysis of log data to identify the optimal integration timing. By improving the accuracy of integration by referring to relevant log data from the systems, more appropriate integration becomes possible. Some or all of the above-described processes in the integration unit may be performed using AI, for example, or without AI. For example, the integration unit can analyze the system's log data using AI and select the optimal integration method.

[0055] The prediction unit can improve the accuracy of its predictions by referring to the system's past performance data when predicting performance. For example, the prediction unit can provide an optimal prediction method based on past performance data. The prediction unit can also cluster the performance data and provide an optimal prediction method for each different system. The prediction unit can also analyze the performance data over time to identify the optimal prediction timing. This allows for more accurate predictions by improving the accuracy of predictions by referring to past performance data. Some or all of the above processes in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can analyze past performance data using AI to improve the accuracy of predictions.

[0056] The prediction unit can identify the scope of impact of its predictions by considering the geographical distribution of the system when predicting performance. For example, the prediction unit identifies the scope of impact based on geographical information of the location where the prediction is needed. The prediction unit can also extend the scope of impact by making predictions to systems surrounding the location where the prediction is needed. The prediction unit can also visualize the geographical distribution of the location where the prediction is needed and identify the scope of impact. This allows for more accurate predictions by considering the geographical distribution of the system and identifying the scope of impact. Some or all of the above processing in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can analyze the geographical distribution of the system using AI and identify the scope of impact of the prediction.

[0057] The prediction unit can improve the accuracy of its predictions by referring to relevant system performance data when predicting performance. For example, the prediction unit can provide an optimal prediction method based on performance data. The prediction unit can also cluster performance data and provide an optimal prediction method for each different system. The prediction unit can also perform time-series analysis of performance data to identify the optimal prediction timing. This allows for more accurate predictions by improving the accuracy of predictions by referring to relevant system performance data. Some or all of the above processes in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can analyze the system's performance data using AI to improve the accuracy of its predictions.

[0058] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0059] System monitoring agents can improve detection accuracy by learning patterns of past system anomaly data when detecting anomalies. For example, they can improve detection accuracy by learning the frequency and patterns of anomalies based on past anomaly data. They can also cluster anomaly data and apply different detection algorithms to each type of anomaly. Furthermore, they can improve detection accuracy by analyzing anomaly data over time to predict the timing of anomaly occurrences. In this way, the accuracy of anomaly detection is improved by learning patterns of anomalies by referring to past anomaly data.

[0060] The system monitoring agent can adjust the frequency of anomaly detection according to the system's operating status and load. For example, when the system load is high, the frequency of anomaly detection can be increased for a quicker response. When the system load is low, the frequency of anomaly detection can be decreased to conserve resources. The frequency of anomaly detection can also be dynamically adjusted according to the system's operating status to ensure optimal detection. This allows for resource optimization by adjusting the frequency of anomaly detection according to the system's operating status and load.

[0061] The system monitoring agent can select the optimal correction method when fixing an anomaly by referring to the system's past correction history. For example, it can select the optimal correction method based on past correction history. It can also cluster the correction history and apply different correction methods to each type of anomaly. It can also analyze the correction history chronologically to identify the optimal timing for correction. As a result, the accuracy of corrections is improved by selecting the optimal correction method by referring to past correction history.

[0062] System monitoring agents can improve the accuracy of warnings by referencing past warning data from the system. For example, they can learn the frequency and patterns of warnings based on past warning data to improve warning accuracy. They can also cluster warning data and apply different warning algorithms to each type of warning. Furthermore, they can analyze warning data over time to predict when warnings will occur and improve warning accuracy. By referencing past warning data to improve warning accuracy, more precise warnings become possible.

[0063] System monitoring agents can create optimal maintenance schedules by referencing historical system maintenance data. For example, they can create optimal maintenance schedules based on past maintenance data. They can also cluster maintenance data to create optimal schedules for different systems. They can also analyze maintenance data over time to identify optimal maintenance timings. This improves the accuracy of maintenance by creating optimal schedules based on historical maintenance data.

[0064] The following briefly describes the processing flow for example form 1.

[0065] Step 1: The detection unit detects anomalies. For example, it analyzes system performance data and detects abnormal patterns. It can also monitor system resource utilization and error logs to detect abnormal behavior. Furthermore, it can monitor system response time and throughput to detect abnormal performance degradation. Step 2: The correction unit performs corrections and adjustments based on the anomalies detected by the detection unit. For example, it can automatically change system settings, reallocate system resources, and adjust system parameters to correct anomalies. Step 3: The warning unit issues warnings based on the corrections and adjustments made by the correction unit. For example, if it detects abnormal behavior, it will warn the administrator and suggest countermeasures. It can send email notifications or display alerts, and it can also display warning messages on the system dashboard. Step 4: The scheduling unit schedules preventative maintenance based on warnings issued by the warning unit. For example, it analyzes system performance data to predict future performance degradation and schedule maintenance accordingly. It can also schedule regular software updates and hardware inspections, and adjust the timing of maintenance according to the system's operational status.

[0066] (Example of form 2) The system monitoring agent according to the embodiment of the present invention is an innovative solution that supports the monitoring of various systems, from conventional IT infrastructure to the latest general-purpose AI and LLM. This system monitoring agent detects anomalies using a data-driven approach that leverages AI algorithms. When an anomaly is detected, it automatically corrects and adjusts, improving system uptime while minimizing administrator intervention. Furthermore, when a general-purpose AI takes unexpected actions, it issues an early warning and provides appropriate countermeasures, minimizing the risk of AI malfunction. This significantly advances the safe operation and social acceptance of AI. In addition, the autonomous AI agent collaborates with other systems and AI agents within the enterprise to perform cross-system anomaly detection and response, thereby strengthening the security of the entire system. Furthermore, an AI agent with planning capabilities predicts system performance and automatically schedules preventative maintenance, minimizing system downtime. For example, the system monitoring agent analyzes system performance data and detects anomalous patterns. Next, when the system monitoring agent detects an anomaly, it automatically changes system settings or reallocates resources. This improves system uptime while minimizing administrator intervention. Furthermore, the system monitoring agent issues early warnings and provides appropriate countermeasures when the general-purpose AI behaves unexpectedly. For example, if the AI ​​detects abnormal behavior, it warns the administrator and suggests countermeasures. This minimizes the risk of the AI ​​running amok. The system monitoring agent also collaborates with other systems and AI agents within the enterprise to perform cross-system anomaly detection and response. For example, it shares data across multiple systems and coordinates responses when an anomaly is detected. This enhances the security of the entire system. In addition, the system monitoring agent has an AI agent with planning capabilities that predicts system performance and automatically schedules preventative maintenance. For example, it analyzes system performance data to predict future performance degradation and schedule maintenance accordingly.This minimizes system downtime. As a result, system monitoring agents can improve system uptime and significantly advance the secure operation and social acceptance of AI.

[0067] The system monitoring agent according to the embodiment comprises a detection unit, a correction unit, a warning unit, and a scheduling unit. The detection unit detects anomalies. The detection unit, for example, analyzes system performance data and detects abnormal patterns. The detection unit can, for example, monitor system resource utilization and error logs to detect abnormal operation. The detection unit can also, for example, monitor system response time and throughput to detect abnormal performance degradation. The correction unit performs corrections and adjustments based on the anomalies detected by the detection unit. The correction unit, for example, automatically changes system settings. The correction unit can, for example, reallocate system resources. The correction unit can, for example, adjust system parameters to correct anomalies. The warning unit issues warnings based on the results of corrections and adjustments made by the correction unit. The warning unit, for example, issues a warning to the administrator when it detects abnormal operation and suggests countermeasures. The warning unit can, for example, send email notifications or display alerts. The warning unit can, for example, display warning messages on the system dashboard. The scheduling unit schedules preventative maintenance based on warnings issued by the warning unit. The scheduling unit can, for example, analyze system performance data to predict future performance degradation and schedule maintenance accordingly. The scheduling unit can also schedule, for example, periodic software updates and hardware inspections. The scheduling unit can also adjust the timing of maintenance according to the system's operating status. As a result, the system monitoring agent according to the embodiment can automate a series of processes from anomaly detection to correction, warning, and maintenance scheduling, thereby improving system uptime.

[0068] The detection unit detects anomalies. For example, the detection unit analyzes system performance data and detects abnormal patterns. Specifically, it can monitor system resource usage and error logs to detect abnormal behavior. For example, it can detect abnormal patterns in real time, such as a sudden increase in CPU usage, abnormally high memory usage, or excessive disk I / O. Furthermore, it can monitor system response time and throughput to detect abnormal performance degradation. For example, it continuously monitors performance indicators such as web server response times being longer than usual or database query processing times being delayed. The detection unit collects this data and performs anomaly detection using AI algorithms. The AI ​​compares it with past normal operation data to identify abnormal patterns. For example, it uses machine learning models to learn normal operation patterns and detect anomalies in real time. This allows the detection unit to quickly and accurately detect system anomalies and maintain system stability. Furthermore, the detection unit continuously learns to improve the accuracy of anomaly detection and to be able to respond to new anomaly patterns. This enables the detection unit to detect system anomalies early and respond quickly.

[0069] The correction unit performs corrections and adjustments based on anomalies detected by the detection unit. For example, the correction unit can automatically change system settings. Specifically, it can reallocate system resources. For instance, it can dynamically change CPU and memory allocations to prevent excessive resource usage. It can also adjust system parameters to correct anomalies. For example, it can improve system performance by adjusting database cache size or optimizing network bandwidth. The correction unit uses scripts and automation tools to automate these correction tasks. For example, when an anomaly is detected, it executes a predefined script to perform the necessary corrections. The correction unit also uses AI to optimize correction tasks. The AI ​​analyzes past correction history and system status to propose the optimal correction method. This allows the correction unit to correct anomalies quickly and effectively, maintaining system stability. Furthermore, the correction unit can record the results of correction tasks to help with future anomaly response. This allows the correction unit to quickly correct system anomalies and improve system uptime.

[0070] The warning unit issues warnings based on the results of corrections and adjustments made by the correction unit. For example, the warning unit will warn administrators when it detects abnormal operation and suggest countermeasures. Specifically, it can send email notifications or display alerts. For example, it can display warning messages on the system dashboard to provide administrators with detailed information about the anomaly. The warning unit can also propose specific countermeasures to administrators when an anomaly occurs. For example, it can suggest specific actions such as restarting the system, stopping specific services, or changing settings. The warning unit sends these warnings in real time to enable administrators to respond quickly. Furthermore, the warning unit can set warning priorities and use different notification methods depending on the severity. For example, in the case of a serious anomaly, it can notify via voice call or SMS to encourage a quick response. The warning unit can also record past warning history and analyze trends in anomaly occurrence. This allows the warning unit to support early detection and rapid response to anomalies, maintaining system stability.

[0071] The scheduling unit schedules preventative maintenance based on warnings issued by the warning unit. For example, the scheduling unit analyzes system performance data to predict future performance degradation and schedule maintenance accordingly. Specifically, it can schedule regular software updates and hardware inspections. For instance, it adjusts the optimal maintenance timing based on the system's operating status. The scheduling unit uses scheduling tools to automate these maintenance tasks. For example, it uses a calendar function to manage maintenance schedules and set reminders. Furthermore, the scheduling unit uses AI to optimize maintenance. The AI ​​analyzes past maintenance history and system status to propose the optimal maintenance schedule. This allows the scheduling unit to efficiently perform preventative maintenance and improve system uptime. Additionally, the scheduling unit can record the results of maintenance work and use this information to inform future maintenance plans. This allows the scheduling unit to maintain system stability and improve long-term operational efficiency.

[0072] The system monitoring agent according to this embodiment includes a collaboration unit that cooperates with other systems and AI agents. The collaboration unit, for example, shares data among multiple systems and cooperates to respond when an anomaly is detected. The collaboration unit can cooperate with monitoring systems and data analysis agents to perform anomaly detection and response. The collaboration unit can also share data among systems in real time and detect anomalies early. This enables cross-system anomaly detection and response by coordinating with other systems and AI agents. Some or all of the above-described processing in the collaboration unit may be performed using AI, for example, or without AI. For example, the collaboration unit can optimize data sharing with other systems and AI agents using AI.

[0073] The system monitoring agent according to the embodiment includes a prediction unit that predicts the performance of the system. The prediction unit, for example, analyzes system performance data and predicts future performance degradation. The prediction unit can, for example, analyze system resource utilization and response time to predict future load increases. The prediction unit can also, for example, analyze system traffic patterns to predict future traffic increases. This allows for the automatic scheduling of preventative maintenance by predicting system performance. Some or all of the above-described processes in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can analyze system performance data using AI to predict future performance degradation.

[0074] The detection unit can analyze system performance data and detect abnormal patterns. For example, the detection unit can monitor system resource utilization and error logs to detect abnormal behavior. The detection unit can also monitor system response time and throughput to detect abnormal performance degradation. This makes it easier to detect abnormal patterns by analyzing system performance data. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can analyze system performance data using AI to detect abnormal patterns.

[0075] The correction unit can automatically change system settings. For example, the correction unit can adjust system parameters and correct anomalies. For example, the correction unit can automatically update system configuration files. For example, the correction unit can optimize system settings and correct anomalies. This allows for a rapid response to anomalies by automatically changing system settings. Some or all of the above-described processes in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can optimize system setting changes using AI.

[0076] The modification unit can reallocate resources. For example, the modification unit can reallocate resources by changing the allocation of the system's CPU and memory. The modification unit can also reallocate the system's storage resources. The modification unit can also reallocate the system's network resources. By reallocating resources in this way, the system's utilization can be optimized. Some or all of the above processing in the modification unit may be performed using AI, for example, or without AI. For example, the modification unit can optimize resource reallocation using AI.

[0077] The warning unit can alert administrators and suggest countermeasures when it detects abnormal behavior. For example, the warning unit can send email notifications or display alerts. The warning unit can also display warning messages on the system dashboard. For example, the warning unit can send voice alerts or SMS notifications. This enables a quick response by alerting administrators and suggesting countermeasures when abnormal behavior is detected. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, when the warning unit detects abnormal behavior, it can use AI to suggest the optimal countermeasure.

[0078] The collaboration unit can share data between multiple systems and coordinate responses when an anomaly is detected. For example, the collaboration unit can collaborate with monitoring systems and data analysis agents to detect and respond to anomalies. The collaboration unit can also share data between systems in real time to detect anomalies early. For example, when an anomaly is detected, the collaboration unit can coordinate with other systems to execute countermeasures. This strengthens the overall system security by sharing data between multiple systems and coordinating responses when an anomaly is detected. Some or all of the above-described processes in the collaboration unit may be performed using AI, for example, or without AI. For example, the collaboration unit can optimize data sharing with other systems and AI agents using AI.

[0079] The prediction unit can analyze system performance data and predict future performance degradation. For example, the prediction unit can analyze system resource utilization and response time to predict future load increases. The prediction unit can also analyze system traffic patterns to predict future traffic increases. For example, the prediction unit can predict future performance degradation based on system performance data and schedule preventative maintenance. This allows for the planning of preventative maintenance by analyzing system performance data and predicting future performance degradation. Some or all of the above processing in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can analyze system performance data using AI to predict future performance degradation.

[0080] The detection unit can estimate the user's emotions and dynamically adjust the anomaly detection threshold based on the estimated emotions. For example, if the user is stressed, the detection unit can set the anomaly detection threshold low to detect anomalies early. For example, if the user is relaxed, the detection unit can set the anomaly detection threshold high to reduce unnecessary warnings. For example, if the user is in a hurry, the detection unit can set the anomaly detection threshold appropriately to allow for a quick response. This enables more appropriate anomaly detection by dynamically adjusting the anomaly detection threshold based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can analyze the user's emotion data using AI and dynamically adjust the anomaly detection threshold.

[0081] The detection unit can improve detection accuracy by learning anomaly patterns by referring to past anomaly data from the system when detecting an anomaly. For example, the detection unit can improve detection accuracy by learning the frequency and patterns of anomalies based on past anomaly data. The detection unit can also improve detection accuracy by clustering anomaly data and applying different detection algorithms for each type of anomaly. The detection unit can also improve detection accuracy by analyzing anomaly data over time and predicting the timing of anomaly occurrence. In this way, the accuracy of anomaly detection is improved by learning anomaly patterns by referring to past anomaly data. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can learn anomaly patterns by analyzing past anomaly data using AI.

[0082] The detection unit can adjust the frequency of anomaly detection according to the system's operating status and load when detecting an anomaly. For example, if the system load is high, the detection unit can increase the frequency of anomaly detection to respond quickly. For example, if the system load is low, the detection unit can also reduce the frequency of anomaly detection to conserve resources. The detection unit can also dynamically adjust the frequency of anomaly detection according to the system's operating status to perform optimal detection. This allows for resource optimization by adjusting the frequency of anomaly detection according to the system's operating status and load. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can analyze the system's operating status and load using AI and dynamically adjust the frequency of anomaly detection.

[0083] The correction unit can estimate the user's emotions and select a correction method based on the estimated emotions. For example, if the user is stressed, the correction unit may select a quick and simple correction method. For example, if the user is relaxed, the correction unit may select a more detailed correction method. For example, if the user is in a hurry, the correction unit may select a correction method that can be addressed quickly. This allows for more appropriate corrections by selecting a correction method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit may analyze the user's emotion data using AI and select a correction method.

[0084] The correction unit can select the optimal correction method by referring to the system's past correction history when correcting an anomaly. For example, the correction unit can select the optimal correction method based on the past correction history. The correction unit can also cluster the correction history and apply different correction methods to each type of anomaly. The correction unit can also analyze the correction history over time to identify the optimal correction timing. This improves the accuracy of corrections by selecting the optimal correction method by referring to the past correction history. Some or all of the above processes in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can analyze the past correction history using AI and select the optimal correction method.

[0085] The correction unit can adjust the timing of corrections according to the current system load when correcting anomalies. For example, if the system load is high, the correction unit can delay the timing of corrections to conserve resources. For example, if the system load is low, the correction unit can also advance the timing of corrections to respond quickly. For example, the correction unit can dynamically adjust the timing of corrections according to the system load to perform the optimal correction. This allows for resource optimization by adjusting the timing of corrections according to the system load. Some or all of the above processing in the correction unit may be performed using AI, for example, or without AI. For example, the correction unit can analyze the system load using AI and dynamically adjust the timing of corrections.

[0086] The warning unit can estimate the user's emotions and adjust the way the warning is expressed based on the estimated emotions. For example, if the user is tense, the warning unit will issue a warning in a calm manner. For example, if the user is relaxed, the warning unit may issue a warning in a manner that includes detailed information. For example, if the user is in a hurry, the warning unit may issue a warning in a concise and quick manner. This allows for more appropriate warnings by adjusting the way the warning is expressed based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the warning unit may be performed using AI, for example, or not using AI. For example, the warning unit can analyze the user's emotion data using AI and adjust the way the warning is expressed.

[0087] The warning unit can improve the accuracy of warnings by referring to the system's past warning data when issuing a warning. For example, the warning unit can learn the frequency and patterns of warning occurrences based on past warning data to improve warning accuracy. The warning unit can also cluster the warning data and apply different warning algorithms to each type of warning. For example, the warning unit can analyze the warning data over time to predict the timing of warning occurrences and improve warning accuracy. This allows for more accurate warnings by improving warning accuracy by referring to past warning data. Some or all of the above processes in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can analyze past warning data using AI to improve warning accuracy.

[0088] The warning unit can adjust the timing of warnings according to the current operating status of the system when issuing a warning. For example, if the system's operating status is high, the warning unit can advance the warning timing to allow for a quicker response. For example, if the system's operating status is low, the warning unit can delay the warning timing to conserve resources. The warning unit can also dynamically adjust the warning timing according to the system's operating status to provide the most appropriate warning. This allows for resource optimization by adjusting the warning timing according to the system's operating status. Some or all of the above processing in the warning unit may be performed using AI, for example, or without AI. For example, the warning unit can analyze the system's operating status using AI and dynamically adjust the warning timing.

[0089] The scheduling unit can estimate the user's emotions and adjust the maintenance schedule based on the estimated emotions. For example, if the user is stressed, the scheduling unit can accelerate the maintenance schedule to respond quickly. For example, if the user is relaxed, the scheduling unit can delay the maintenance schedule to conserve resources. For example, if the user is in a hurry, the scheduling unit can set a maintenance schedule that allows for a quick response. This allows for more appropriate maintenance by adjusting the maintenance schedule based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the scheduling unit may be performed using AI, for example, or not using AI. For example, the scheduling unit can analyze user emotion data using AI and adjust the maintenance schedule.

[0090] The scheduling unit can create an optimal maintenance schedule by referring to the system's past maintenance data. For example, the scheduling unit can create an optimal maintenance schedule based on past maintenance data. The scheduling unit can also cluster maintenance data and create an optimal schedule for each different system. The scheduling unit can also analyze maintenance data over time to identify the optimal maintenance timing. This improves the accuracy of maintenance by creating an optimal schedule by referring to past maintenance data. Some or all of the above processes in the scheduling unit may be performed using AI, for example, or without AI. For example, the scheduling unit can analyze past maintenance data using AI to create an optimal maintenance schedule.

[0091] The scheduling unit can adjust the timing of maintenance schedules according to the current system operating status. For example, if the system operating status is high, the scheduling unit can delay the maintenance schedule to conserve resources. For example, if the system operating status is low, the scheduling unit can also advance the maintenance schedule to respond quickly. For example, the scheduling unit can dynamically adjust the timing of the maintenance schedule according to the system operating status to perform optimal maintenance. This allows for resource optimization by adjusting the timing of the schedule according to the system operating status. Some or all of the above processing in the scheduling unit may be performed using AI, for example, or without AI. For example, the scheduling unit can analyze the system operating status using AI and dynamically adjust the timing of the maintenance schedule.

[0092] The scheduling unit can estimate the user's emotions and determine maintenance priorities based on those estimated emotions. For example, if the user is stressed, the scheduling unit will prioritize important maintenance. If the user is relaxed, the scheduling unit can also perform minor maintenance. If the user is in a hurry, the scheduling unit can also prioritize maintenance that requires immediate attention. This allows for more appropriate maintenance by prioritizing maintenance based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the scheduling unit may be performed using AI, or not. For example, the scheduling unit can analyze user emotion data using AI to determine maintenance priorities.

[0093] The scheduling unit can determine the scope of maintenance impact by considering the geographical distribution of the system when scheduling maintenance. For example, the scheduling unit can determine the scope of impact based on geographical information of the locations where maintenance is needed. For example, the scheduling unit can extend the scope of impact by performing maintenance on systems surrounding the locations where maintenance is needed. For example, the scheduling unit can visualize the geographical distribution of the locations where maintenance is needed and determine the scope of impact. This allows for more appropriate maintenance by determining the scope of maintenance impact by considering the geographical distribution of the system. Some or all of the above processing in the scheduling unit may be performed using AI, for example, or without AI. For example, the scheduling unit can analyze the geographical distribution of the system using AI and determine the scope of maintenance impact.

[0094] The scheduling unit can improve the accuracy of its maintenance schedule by referring to relevant system performance data. For example, the scheduling unit can create an optimal maintenance schedule based on performance data. The scheduling unit can also cluster performance data and create an optimal schedule for different systems. For example, the scheduling unit can analyze performance data over time to identify the optimal maintenance timing. This allows for more appropriate maintenance by improving the accuracy of the schedule by referring to relevant system performance data. Some or all of the above processes in the scheduling unit may be performed using AI, for example, or without AI. For example, the scheduling unit can analyze system performance data using AI and create an optimal maintenance schedule.

[0095] The interaction unit can estimate the user's emotions and adjust the interaction method based on the estimated emotions. For example, if the user is stressed, the interaction unit can provide a simple interaction method. For example, if the user is relaxed, the interaction unit can also provide a more detailed interaction method. For example, if the user is in a hurry, the interaction unit can also provide a quick-response interaction method. This allows for more appropriate interaction by adjusting the interaction method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the interaction unit may be performed using AI, for example, or without AI. For example, the interaction unit can analyze the user's emotion data using AI and adjust the interaction method.

[0096] The integration unit can select the optimal integration method by referring to past integration data of other systems when integrating with other systems. For example, the integration unit can select the optimal integration method based on past integration data. The integration unit can also cluster the integration data and select the optimal integration method for each different system. The integration unit can also analyze the integration data over time to identify the optimal integration timing. By selecting the optimal integration method by referring to past integration data, the accuracy of the integration is improved. Some or all of the above processing in the integration unit may be performed using AI, for example, or without AI. For example, the integration unit can analyze past integration data using AI and select the optimal integration method.

[0097] The collaboration unit can estimate the user's emotions and determine the priority of collaborations based on the estimated emotions. For example, if the user is stressed, the collaboration unit will prioritize important collaborations. For example, if the user is relaxed, the collaboration unit can also perform minor collaborations. For example, if the user is in a hurry, the collaboration unit can also prioritize collaborations that require a quick response. This allows for more appropriate collaborations by determining the priority of collaborations based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the collaboration unit may be performed using AI, for example, or not using AI. For example, the collaboration unit can analyze the user's emotion data using AI to determine the priority of collaborations.

[0098] The integration unit can identify the scope of impact of integration by considering the geographical distribution of systems when integrating with other systems. For example, the integration unit can identify the scope of impact based on geographical information of the locations where integration is required. The integration unit can also extend its scope of impact by integrating with systems surrounding the locations where integration is required. For example, the integration unit can visualize the geographical distribution of the locations where integration is required and identify the scope of impact. This allows for more appropriate integration by identifying the scope of impact of integration by considering the geographical distribution of systems. Some or all of the above processing in the integration unit may be performed using AI, for example, or without AI. For example, the integration unit can analyze the geographical distribution of systems using AI and identify the scope of impact of integration.

[0099] The integration unit can improve the accuracy of integration by referring to relevant log data from other systems when integrating with them. For example, the integration unit can analyze log data that requires integration and select the optimal integration method. The integration unit can also cluster log data and select the optimal integration method for each different system. The integration unit can also perform time-series analysis of log data to identify the optimal integration timing. By improving the accuracy of integration by referring to relevant log data from the systems, more appropriate integration becomes possible. Some or all of the above-described processes in the integration unit may be performed using AI, for example, or without AI. For example, the integration unit can analyze the system's log data using AI and select the optimal integration method.

[0100] The prediction unit can estimate the user's emotions and adjust the performance prediction method based on the estimated user emotions. For example, if the user is stressed, the prediction unit can provide a quick and simple prediction method. For example, if the user is relaxed, the prediction unit can also provide a detailed prediction method. For example, if the user is in a hurry, the prediction unit can also provide a prediction method that allows for a quick response. This allows for more accurate predictions by adjusting the performance prediction method based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the prediction unit may be performed using AI, for example, or not using AI. For example, the prediction unit can analyze user emotion data using AI and adjust the performance prediction method.

[0101] The prediction unit can improve the accuracy of its predictions by referring to the system's past performance data when predicting performance. For example, the prediction unit can provide an optimal prediction method based on past performance data. The prediction unit can also cluster the performance data and provide an optimal prediction method for each different system. The prediction unit can also analyze the performance data over time to identify the optimal prediction timing. This allows for more accurate predictions by improving the accuracy of predictions by referring to past performance data. Some or all of the above processes in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can analyze past performance data using AI to improve the accuracy of predictions.

[0102] The prediction unit can estimate the user's emotions and determine the priority of predictions based on the estimated emotions. For example, if the user is stressed, the prediction unit will prioritize important predictions. For example, if the user is relaxed, the prediction unit can also make minor predictions. For example, if the user is in a hurry, the prediction unit can also prioritize predictions that require a quick response. This allows for more appropriate predictions by prioritizing predictions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can analyze the user's emotion data using AI to determine the priority of predictions.

[0103] The prediction unit can identify the scope of impact of its predictions by considering the geographical distribution of the system when predicting performance. For example, the prediction unit identifies the scope of impact based on geographical information of the location where the prediction is needed. The prediction unit can also extend the scope of impact by making predictions to systems surrounding the location where the prediction is needed. The prediction unit can also visualize the geographical distribution of the location where the prediction is needed and identify the scope of impact. This allows for more accurate predictions by considering the geographical distribution of the system and identifying the scope of impact. Some or all of the above processing in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can analyze the geographical distribution of the system using AI and identify the scope of impact of the prediction.

[0104] The prediction unit can improve the accuracy of its predictions by referring to relevant system performance data when predicting performance. For example, the prediction unit can provide an optimal prediction method based on performance data. The prediction unit can also cluster performance data and provide an optimal prediction method for each different system. The prediction unit can also perform time-series analysis of performance data to identify the optimal prediction timing. This allows for more accurate predictions by improving the accuracy of predictions by referring to relevant system performance data. Some or all of the above processes in the prediction unit may be performed using AI, for example, or without AI. For example, the prediction unit can analyze the system's performance data using AI to improve the accuracy of its predictions.

[0105] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0106] The system monitoring agent can estimate the user's emotions when detecting anomalies and dynamically adjust the priority of the anomaly based on those emotions. For example, if the user is stressed, the anomaly priority can be set high for a quick response. If the user is relaxed, the anomaly priority can be set low to reduce unnecessary alerts. If the user is in a hurry, the anomaly priority can be set moderately to allow for a quick response. This allows for more appropriate anomaly response by dynamically adjusting the priority of anomalies based on the user's emotions.

[0107] System monitoring agents can improve detection accuracy by learning patterns of past system anomaly data when detecting anomalies. For example, they can improve detection accuracy by learning the frequency and patterns of anomalies based on past anomaly data. They can also cluster anomaly data and apply different detection algorithms to each type of anomaly. Furthermore, they can improve detection accuracy by analyzing anomaly data over time to predict the timing of anomaly occurrences. In this way, the accuracy of anomaly detection is improved by learning patterns of anomalies by referring to past anomaly data.

[0108] The system monitoring agent can adjust the frequency of anomaly detection according to the system's operating status and load. For example, when the system load is high, the frequency of anomaly detection can be increased for a quicker response. When the system load is low, the frequency of anomaly detection can be decreased to conserve resources. The frequency of anomaly detection can also be dynamically adjusted according to the system's operating status to ensure optimal detection. This allows for resource optimization by adjusting the frequency of anomaly detection according to the system's operating status and load.

[0109] The system monitoring agent can estimate the user's emotions when correcting anomalies and select a corrective action based on those emotions. For example, if the user is stressed, it can select a quick and easy corrective action. If the user is relaxed, it can select a more detailed corrective action. If the user is in a hurry, it can select a corrective action that allows for a quick response. By selecting a corrective action based on the user's emotions, more appropriate corrective actions can be achieved.

[0110] The system monitoring agent can select the optimal correction method when fixing an anomaly by referring to the system's past correction history. For example, it can select the optimal correction method based on past correction history. It can also cluster the correction history and apply different correction methods to each type of anomaly. It can also analyze the correction history chronologically to identify the optimal timing for correction. As a result, the accuracy of corrections is improved by selecting the optimal correction method by referring to past correction history.

[0111] The system monitoring agent can estimate the user's emotions when issuing a warning and adjust the warning's wording based on that estimation. For example, if the user is stressed, the warning will be issued in a calm tone. If the user is relaxed, the warning may be issued in a more detailed and informative tone. If the user is in a hurry, the warning may be issued in a concise and quick tone. By adjusting the warning's wording based on the user's emotions, more appropriate warnings can be provided.

[0112] System monitoring agents can improve the accuracy of warnings by referencing past warning data from the system. For example, they can learn the frequency and patterns of warnings based on past warning data to improve warning accuracy. They can also cluster warning data and apply different warning algorithms to each type of warning. Furthermore, they can analyze warning data over time to predict when warnings will occur and improve warning accuracy. By referencing past warning data to improve warning accuracy, more precise warnings become possible.

[0113] The system monitoring agent can estimate user emotions when scheduling maintenance and adjust the maintenance schedule based on those emotions. For example, if a user is stressed, the maintenance schedule can be brought forward for a quicker response. If a user is relaxed, the maintenance schedule can be delayed to conserve resources. If a user is in a hurry, a maintenance schedule that allows for a quick response can be set. This allows for more appropriate maintenance by adjusting the maintenance schedule based on user emotions.

[0114] System monitoring agents can create optimal maintenance schedules by referencing historical system maintenance data. For example, they can create optimal maintenance schedules based on past maintenance data. They can also cluster maintenance data to create optimal schedules for different systems. They can also analyze maintenance data over time to identify optimal maintenance timings. This improves the accuracy of maintenance by creating optimal schedules based on historical maintenance data.

[0115] The system monitoring agent can estimate the user's emotions when interacting with other systems and adjust the interaction method based on the estimated emotions. For example, if the user is stressed, it can provide a simpler interaction method. If the user is relaxed, it can provide a more detailed interaction method. If the user is in a hurry, it can provide an interaction method that allows for a quick response. By adjusting the interaction method based on the user's emotions, more appropriate interactions become possible.

[0116] The following briefly describes the processing flow for example form 2.

[0117] Step 1: The detection unit detects anomalies. For example, it analyzes system performance data and detects abnormal patterns. It can also monitor system resource utilization and error logs to detect abnormal behavior. Furthermore, it can monitor system response time and throughput to detect abnormal performance degradation. Step 2: The correction unit performs corrections and adjustments based on the anomalies detected by the detection unit. For example, it can automatically change system settings, reallocate system resources, and adjust system parameters to correct anomalies. Step 3: The warning unit issues warnings based on the corrections and adjustments made by the correction unit. For example, if it detects abnormal behavior, it will warn the administrator and suggest countermeasures. It can send email notifications or display alerts, and it can also display warning messages on the system dashboard. Step 4: The scheduling unit schedules preventative maintenance based on warnings issued by the warning unit. For example, it analyzes system performance data to predict future performance degradation and schedule maintenance accordingly. It can also schedule regular software updates and hardware inspections, and adjust the timing of maintenance according to the system's operational status.

[0118] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0119] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, 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), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0120] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, 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.

[0121] Each of the multiple elements described above, including the detection unit, correction unit, warning unit, scheduling unit, coordination unit, and prediction unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the detection unit is implemented by the control unit 46A of the smart device 14, which analyzes the system's performance data and detects abnormal patterns. The correction unit is implemented by the specific processing unit 290 of the data processing unit 12, which automatically changes the system settings based on the detected abnormality. The warning unit is implemented by the control unit 46A of the smart device 14, which issues a warning to the administrator and suggests countermeasures when abnormal operation is detected. The scheduling unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the system's performance data and schedules preventive maintenance. The coordination unit is implemented by the control unit 46A of the smart device 14, which shares data with other systems and AI agents and coordinates to respond when an abnormality is detected. The prediction unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, which analyzes the system's performance data and predicts future performance degradation. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0122] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0123] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0124] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0125] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0126] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0128] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0129] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0130] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0131] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0132] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0133] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0134] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0136] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0137] Each of the multiple elements described above, including the detection unit, correction unit, warning unit, scheduling unit, coordination unit, and prediction unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the detection unit is implemented by the control unit 46A of the smart glasses 214, which analyzes the system's performance data and detects abnormal patterns. The correction unit is implemented by the specific processing unit 290 of the data processing unit 12, which automatically changes the system settings based on the detected abnormality. The warning unit is implemented by the control unit 46A of the smart glasses 214, which issues a warning to the administrator and suggests countermeasures when abnormal operation is detected. The scheduling unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the system's performance data and schedules preventative maintenance. The coordination unit is implemented by the control unit 46A of the smart glasses 214, which shares data with other systems and AI agents and coordinates to respond when an abnormality is detected. The prediction unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, which analyzes the system's performance data and predicts future performance degradation. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0138] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0139] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0140] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0141] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0142] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0143] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0144] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0145] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0146] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0147] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0148] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0149] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0150] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0151] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0152] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0153] Each of the multiple elements described above, including the detection unit, correction unit, warning unit, scheduling unit, coordination unit, and prediction unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the detection unit is implemented by the control unit 46A of the headset terminal 314, which analyzes system performance data and detects abnormal patterns. The correction unit is implemented by the specific processing unit 290 of the data processing unit 12, which automatically changes system settings based on the detected abnormality. The warning unit is implemented by the control unit 46A of the headset terminal 314, which issues a warning to the administrator and suggests countermeasures when abnormal operation is detected. The scheduling unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes system performance data and schedules preventive maintenance. The coordination unit is implemented by the control unit 46A of the headset terminal 314, which shares data with other systems and AI agents and coordinates to respond when an abnormality is detected. The prediction unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, which analyzes the system's performance data and predicts future performance degradation. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0154] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0155] As shown in Figure 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.

[0156] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0157] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0158] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0159] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0160] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0161] The controlled 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 robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0162] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0163] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0164] Storage 32 stores the data generation model 58 and the 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 the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0165] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0166] Furthermore, other devices besides the data processing device 12 may also 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 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0167] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0168] The data generation model 58 is a so-called generative AI. An example of a 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 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0169] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0170] Each of the multiple elements described above, including the detection unit, correction unit, warning unit, scheduling unit, coordination unit, and prediction unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the detection unit is implemented by the control unit 46A of the robot 414, which analyzes the system's performance data and detects abnormal patterns. The correction unit is implemented by the specific processing unit 290 of the data processing unit 12, which automatically changes the system settings based on the detected abnormality. The warning unit is implemented by the control unit 46A of the robot 414, which issues a warning to the administrator and suggests countermeasures when abnormal operation is detected. The scheduling unit is implemented by the specific processing unit 290 of the data processing unit 12, which analyzes the system's performance data and schedules preventive maintenance. The coordination unit is implemented by the control unit 46A of the robot 414, which shares data with other systems and AI agents and coordinates to respond when an abnormality is detected. The prediction unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, which analyzes the system's performance data and predicts future performance degradation. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0171] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0172] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0173] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0174] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0175] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0176] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0177] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0178] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0179] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0180] 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.

[0181] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0182] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0183] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0184] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0185] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0186] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0187] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0188] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0189] (Note 1) A detection unit that detects abnormalities, A correction unit that performs corrections and adjustments based on the abnormality detected by the detection unit, A warning unit that issues a warning based on the results of the corrections and adjustments made by the correction unit, The system includes a scheduling unit that schedules preventative maintenance based on warnings issued by the aforementioned warning unit. A system characterized by the following features. (Note 2) It includes a connectivity unit that interacts with other systems and AI agents. The system described in Appendix 1, characterized by the features described herein. (Note 3) It includes a prediction unit that predicts the system's performance. The system described in Appendix 1, characterized by the features described herein. (Note 4) The detection unit is Analyze system performance data and detect abnormal patterns. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned modification section is, Automatically change system settings. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned modification section is, Reallocate resources The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned warning unit is If abnormal behavior is detected, an alert will be issued to the administrator, and countermeasures will be suggested. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned linkage unit is, Data is shared across multiple systems, and when an anomaly is detected, they coordinate to take appropriate action. The system described in Appendix 2, characterized by the features described herein. (Note 9) The prediction unit, Analyze system performance data and predict future performance degradation. The system described in Appendix 3, characterized by the features described herein. (Note 10) The detection unit is It estimates the user's emotions and dynamically adjusts the anomaly detection threshold based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The detection unit is When detecting anomalies, the system learns patterns of anomalies by referring to past anomaly data, thereby improving detection accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 12) The detection unit is When detecting anomalies, the frequency of anomaly detection is adjusted according to the system's operating status and load. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned modification section is, The system estimates the user's emotions and selects a corrective action based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned modification section is, When correcting an anomaly, the system's past correction history is referenced to select the most appropriate correction method. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned modification section is, When correcting anomalies, the timing of the correction will be adjusted according to the current system load. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned warning unit is The system estimates the user's emotions and adjusts the way warnings are presented based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned warning unit is When issuing a warning, the system references past warning data to improve the accuracy of the warning. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned warning unit is When issuing a warning, the timing of the warning will be adjusted according to the current operating status of the system. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned scheduling unit is The system estimates user sentiment and adjusts the maintenance schedule based on the estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned scheduling unit is When scheduling maintenance, refer to the system's past maintenance data to create the optimal schedule. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned scheduling unit is When scheduling maintenance, adjust the timing of the schedule according to the current operational status of the system. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned scheduling unit is It estimates user sentiment and determines maintenance priorities based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned scheduling unit is When scheduling maintenance, consider the geographical distribution of the system to determine the scope of the maintenance's impact. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned scheduling unit is When scheduling maintenance, referencing relevant system performance data improves the accuracy of the schedule. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned linkage unit is, It estimates the user's emotions and adjusts the interaction method based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 26) The aforementioned linkage unit is, When integrating with other systems, the system selects the optimal integration method by referring to past integration data. The system described in Appendix 2, characterized by the features described herein. (Note 27) The aforementioned linkage unit is, It estimates the user's emotions and determines the priority of collaborations based on the estimated user emotions. The system described in Appendix 2, characterized by the features described herein. (Note 28) The aforementioned linkage unit is, When integrating with other systems, the geographical distribution of the systems is taken into consideration to determine the scope of the integration's impact. The system described in Appendix 2, characterized by the features described herein. (Note 29) The aforementioned linkage unit is, When integrating with other systems, we improve the accuracy of the integration by referring to relevant log data from the systems. The system described in Appendix 2, characterized by the features described herein. (Note 30) The prediction unit, We estimate user sentiment and adjust the performance prediction method based on the estimated user sentiment. The system described in Appendix 3, characterized by the features described herein. (Note 31) The prediction unit, When predicting performance, we improve the accuracy of predictions by referring to the system's historical performance data. The system described in Appendix 3, characterized by the features described herein. (Note 32) The prediction unit, It estimates the user's emotions and determines the priority of predictions based on the estimated user emotions. The system described in Appendix 3, characterized by the features described herein. (Note 33) The prediction unit, When predicting performance, consider the geographical distribution of the system to identify the scope of the prediction's impact. The system described in Appendix 3, characterized by the features described herein. (Note 34) The prediction unit, When predicting performance, referencing relevant system performance data improves the accuracy of the prediction. The system described in Appendix 3, characterized by the features described herein. [Explanation of Symbols]

[0190] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A detection unit that detects abnormalities, A correction unit that performs corrections and adjustments based on the abnormality detected by the detection unit, A warning unit that issues a warning based on the results of the corrections and adjustments made by the correction unit, The system includes a scheduling unit that schedules preventative maintenance based on warnings issued by the aforementioned warning unit. A system characterized by the following features.

2. It includes a collaboration unit that can connect with other systems and AI agents. The system according to feature 1.

3. It includes a prediction unit that predicts the system's performance. The system according to feature 1.

4. The detection unit, Analyze system performance data and detect abnormal patterns. The system according to feature 1.

5. The aforementioned modification section is, Automatically change system settings. The system according to feature 1.

6. The aforementioned modification section is, Reallocate resources The system according to feature 1.

7. The aforementioned warning unit is If abnormal behavior is detected, an alert will be issued to the administrator, and countermeasures will be suggested. The system according to feature 1.

8. The aforementioned linkage unit is, Data is shared across multiple systems, and coordinated responses are made when an anomaly is detected. The system according to feature 2.

9. The prediction unit, Analyze system performance data to predict future performance degradation. The system according to claim 3.

Images