system

Abstract

The system according to the embodiment aims to efficiently identify the main cause from a large amount of alarm information. [Solution] A system according to an embodiment includes a collection unit, a filtering unit, an analysis unit, a summarization unit, an identification unit, and a provision unit. The collection unit collects alarm information. The filtering unit filters the alarm information collected by the collection unit. The analysis unit analyzes the alarm information filtered by the filtering unit and groups related alarms. The summarization unit summarizes the alarm information grouped by the analysis unit. The identification unit identifies a root cause based on the information summarized by the summarization unit. The provision unit provides the root cause identified by the identification unit to a maintenance technician.

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it was difficult to identify the main cause from a large amount of alarm information, which resulted in a decrease in the efficiency of maintenance work.

[0005] The system according to the embodiment aims to efficiently identify the main cause from a large amount of alarm information. [Means for solving the problem]

[0006] A system according to an embodiment includes a collection unit, a filtering unit, an analysis unit, a summarization unit, an identification unit, and a provision unit. The collection unit collects alarm information. The filtering unit filters the alarm information collected by the collection unit. The analysis unit analyzes the alarm information filtered by the filtering unit and groups related alarms. The summarization unit summarizes the alarm information grouped by the analysis unit. The identification unit identifies a root cause based on the information summarized by the summarization unit. The provision unit provides the root cause identified by the identification unit to a maintenance technician. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently identify the main cause from a large amount of alarm information. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

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

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

[0028] (Example 1) A system according to an embodiment of the present invention addresses the problem of network and system equipment maintenance, where a large number of equipment and devices are connected and a large number of alarms are generated when a failure occurs, making it difficult to identify the root cause. This system utilizes a generation AI to summarize information and identify the root cause. For example, alarm information generated by each equipment or device is collected, and the generation AI analyzes this information. The generation AI then groups related alarms based on information such as the alarm content, occurrence time, and occurrence location, and summarizes the information. Furthermore, the generation AI identifies the root cause based on the summarized information. This allows maintenance personnel to quickly identify the root cause and respond without being overwhelmed by the large amount of alarm information. This system is expected to improve the efficiency of response to failures in network and system equipment maintenance, reduce downtime, and improve system stability.

[0029] A maintenance support system according to an embodiment includes a collection unit, a filtering unit, an analysis unit, a summarization unit, an identification unit, and a provision unit. The collection unit collects alarm information. The collection unit collects alarm information from, for example, network devices, servers, storage devices, etc. The collection unit can also collect alarm information in real time. The collection unit can also collect alarm information periodically. The filtering unit filters the alarm information collected by the collection unit. For example, the filtering unit passes only important alarm information to the analysis unit. The filtering unit can also perform filtering based on the importance of the alarm information. The filtering unit can also perform filtering according to the category of the alarm information. The analysis unit analyzes the alarm information filtered by the filtering unit and groups related alarms. The analysis unit determines the relevance based on information such as the content, time of occurrence, and location of the alarm, and groups the alarms. The analysis unit can also perform analysis based on the interrelationship of the alarm information. The analysis unit can also perform analysis based on the frequency of occurrence of the alarm information. The summarization unit summarizes the alarm information grouped by the analysis unit. The summarizing unit summarizes, for example, grouped alarm information. The summarizing unit can also perform summarization based on the importance of the alarm information. Furthermore, the summarizing unit can also perform summarization according to the category of the alarm information. The identifying unit identifies a main cause based on the information summarized by the summarizing unit. The identifying unit identifies a main cause based on, for example, the summarized information. The identifying unit can also identify a main cause based on a correlation between the alarm information. Furthermore, the identifying unit can also identify a main cause based on the frequency of occurrence of the alarm information. The providing unit provides the main cause identified by the identifying unit to a maintenance technician. The providing unit provides the identified main cause to a maintenance technician, for example. The providing unit can also adjust the level of detail of the provided information based on the importance of the main cause. Furthermore, the providing unit can adjust the level of detail of the provided information according to the category of the main cause.As a result, the maintenance support system according to the embodiment can efficiently collect, filter, analyze, summarize, identify the main cause of, and provide alarm information.

[0030] The collection unit can collect alarm information from network devices, servers, and storage devices. The collection unit collects alarm information from, for example, network devices. Network devices include routers, switches, firewalls, etc. The collection unit can also collect alarm information from servers. Servers include physical servers, virtual servers, cloud servers, etc. The collection unit can also collect alarm information from storage devices. Storage devices include hard disk drives (HDDs), solid-state drives (SSDs), network-attached storage (NAS), etc. This enables comprehensive monitoring by collecting alarm information from a variety of devices.

[0031] The filtering unit can pass only important alarm information to the analysis unit. The filtering unit performs filtering based on the importance of the alarm information, for example. Criteria for evaluating the importance include the severity of the error and the scope of the impact. The filtering unit can also perform filtering according to the category of the alarm information. Categories include error messages, warning messages, and notification messages. The filtering unit can also perform filtering based on the time at which the alarm information occurred. The time at which the alarm information occurred includes a timestamp, a time period, and so on. This improves the efficiency of analysis by analyzing only important alarm information.

[0032] The analysis unit can determine relevance based on information about the alarm content, occurrence time, and occurrence location, and group the alarms. The analysis unit can determine relevance based on the alarm content, for example. The alarm content includes the type of error message, error code, etc. The analysis unit can also determine relevance based on the time the alarm occurred. The occurrence time includes a timestamp, time period, etc. The analysis unit can also determine relevance based on the location where the alarm occurred. The occurrence location includes geographical location information, location within the facility, etc. By grouping related alarms, it becomes easier to identify the main cause.

[0033] The summarization unit can summarize the grouped alarm information. For example, the summarization unit summarizes the grouped alarm information. Specific summarization methods include the length of the sentence, the importance of the information to be summarized, and the like. The summarization unit can also perform summarization based on the importance of the alarm information. Criteria for evaluating the importance include the severity of the error and the scope of the impact. Furthermore, the summarization unit can also perform summarization according to the category of the alarm information. Categories include error messages, warning messages, notification messages, and the like. This makes it easier to organize the information by summarizing the grouped alarm information.

[0034] The identification unit can identify the main cause based on the summarized information. The identification unit identifies the main cause based on, for example, the summarized information. Methods for identifying the main cause include cause evaluation criteria, identification algorithms, etc. The identification unit can also identify the main cause based on the correlation between alarm information. Criteria for evaluating the correlation include common causes, scope of impact, etc. The identification unit can also identify the main cause based on the frequency of occurrence of alarm information. Specific details of the frequency of occurrence include the number of occurrences, the number of occurrences per hour, etc. This makes it possible to respond quickly by identifying the main cause based on summarized information.

[0035] The providing unit can provide the identified main cause to a maintenance person. For example, the providing unit provides the identified main cause to a maintenance person. Specific methods of providing the information include the timing of providing the information and details of the providing method. The providing unit can also adjust the level of detail of the information to be provided based on the importance of the main cause. Evaluation criteria for the level of detail include the granularity of the information and the comprehensiveness of the information. The providing unit can also adjust the level of detail of the information to be provided depending on the category of the main cause. Categories include network equipment, servers, storage devices, etc. This allows the identified main cause to be provided to a maintenance person, enabling a prompt response.

[0036] The collection unit monitors the operating status of each device in real time and can immediately collect alarm information if an abnormality occurs. For example, the collection unit monitors the operating status of network devices in real time and immediately collects alarm information if an abnormality occurs. The collection unit can also monitor the operating status of servers in real time and immediately collect alarm information if an abnormality occurs. Furthermore, the collection unit can monitor the operating status of storage devices in real time and immediately collect alarm information if an abnormality occurs. This allows for rapid response by detecting abnormalities in real time and immediately collecting alarm information.

[0037] When collecting alarm information, the collection unit can determine the priority of collection by referring to the past failure history of each device. For example, the collection unit refers to the past failure history of each device and prioritizes collecting alarm information about devices that have frequently failed. The collection unit can also refer to the past failure history of each device and prioritize collecting alarm information about devices that have experienced a serious failure. Furthermore, the collection unit can also refer to the past failure history of each device and prioritize collecting alarm information about devices that have recently experienced a failure. In this way, by referring to the past failure history, important alarm information can be collected preferentially.

[0038] When collecting alarm information, the collection unit can adjust the collection range based on network topology information. For example, the collection unit prioritizes the collection of alarm information from important nodes based on the network topology information. The collection unit can also collect alarm information taking into account the impact range of a failure based on the network topology information. Furthermore, the collection unit can also prioritize the collection of alarm information from devices with redundant configurations based on the network topology information. This enables efficient information collection by optimizing the collection range based on the network topology information.

[0039] When collecting alarm information, the collection unit can prioritize collecting highly relevant information based on the geographical location information of each device. For example, the collection unit prioritizes collecting alarm information from nearby devices based on the geographical location information of each device. The collection unit can also prioritize collecting alarm information within a specific area based on the geographical location information of each device. Furthermore, the collection unit can also prioritize collecting alarm information from areas with a wide impact range based on the geographical location information of each device. This enables efficient information collection by prioritized collection of highly relevant information based on geographical location information.

[0040] When collecting alarm information, the collection unit can analyze the social media activity of each device and collect related information. For example, the collection unit analyzes the social media activity of each device and collects related alarm information. The collection unit can also analyze the social media activity of each device and collect alarm information based on user feedback. Furthermore, the collection unit can analyze the social media activity of each device and collect alarm information based on trend information. This makes it possible to efficiently collect related information by analyzing social media activity.

[0041] When collecting alarm information, the collection unit can customize the collection method based on past feedback from each device. For example, the collection unit customizes the collection method based on past feedback from each device and prioritizes the collection of important alarm information. The collection unit can also customize the collection method and adjust the collection frequency based on past feedback from each device. Furthermore, the collection unit can customize the collection method and optimize the collection range based on past feedback from each device. In this way, efficient information collection is possible by customizing the collection method based on past feedback.

[0042] The filtering unit can adjust the level of detail of filtering based on the importance of the alarm information when filtering. For example, the filtering unit filters alarm information of high importance in detail and filters alarm information of low importance in a simplified manner. The filtering unit can also filter alarm information of high importance with priority and postpone filtering of alarm information of low importance. Furthermore, the filtering unit can filter alarm information of high importance in detail and omit alarm information of low importance. In this way, adjusting the level of detail of filtering based on the importance of the alarm information enables efficient information filtering.

[0043] The filtering unit can apply different filtering algorithms depending on the category of alarm information when filtering. For example, the filtering unit applies a filtering algorithm dedicated to networks to alarm information about network devices. The filtering unit can also apply a filtering algorithm dedicated to servers to alarm information about servers. Furthermore, the filtering unit can also apply a filtering algorithm dedicated to storage to alarm information about storage devices. This allows for efficient information filtering by applying different filtering algorithms depending on the category of alarm information.

[0044] The filtering unit can improve the accuracy of filtering based on past filtering results during filtering. For example, the filtering unit adjusts the filtering algorithm based on past filtering results to improve accuracy. The filtering unit can also adjust the filtering criteria based on past filtering results to improve accuracy. Furthermore, the filtering unit can adjust the filtering priority based on past filtering results to improve accuracy. In this way, by improving the filtering accuracy based on past filtering results, more accurate information filtering is possible.

[0045] During filtering, the filtering unit can determine the filtering priority based on the time when the alarm information occurred. For example, the filtering unit preferentially filters recently occurring alarm information and postpones older alarm information. The filtering unit can also preferentially filter alarm information that occurred during a specific time period. Furthermore, the filtering unit can also preferentially filter alarm information when an important event occurred. In this way, by determining the filtering priority based on the time when the alarm information occurred, efficient information filtering is possible.

[0046] The filtering unit can adjust the filtering order based on the relevance of the alarm information during filtering. For example, the filtering unit preferentially filters highly relevant alarm information and postpones less relevant alarm information. The filtering unit can also filter highly relevant alarm information in detail and filter less relevant alarm information simply. Furthermore, the filtering unit can also filter highly relevant alarm information preferentially and omit less relevant alarm information. In this way, adjusting the filtering order based on the relevance of the alarm information enables efficient information filtering.

[0047] When filtering, the filtering unit can adjust the filtering criteria according to the location where the alarm information occurred. For example, the filtering unit preferentially filters alarm information within a specific area. The filtering unit can also preferentially filter alarm information in areas with a wide range of impact. Furthermore, the filtering unit can also preferentially filter alarm information in areas where important nodes are located. This allows for efficient information filtering by adjusting the filtering criteria according to the location where the alarm information occurred.

[0048] During analysis, the analysis unit can improve the accuracy of the analysis based on the interrelationships between alarm information. For example, the analysis unit groups related alarms and analyzes them based on the interrelationships between alarm information. The analysis unit can also identify and analyze the relationship between cause and effect based on the interrelationships between alarm information. Furthermore, the analysis unit can also identify and analyze a common cause when multiple alarms occur simultaneously based on the interrelationships between alarm information. In this way, by improving the accuracy of the analysis based on the interrelationships between alarm information, more accurate information analysis becomes possible.

[0049] During analysis, the analysis unit can perform the analysis based on attribute information of the person who generated the alarm information. For example, if the person who generated the alarm information is a specific device, the analysis unit performs the analysis based on attribute information of that device. Furthermore, if the person who generated the alarm information is a specific network segment, the analysis unit can also perform the analysis based on attribute information of that segment. Furthermore, if the person who generated the alarm information is a specific user, the analysis unit can also perform the analysis based on attribute information of that user. This enables more accurate information analysis by performing the analysis based on attribute information of the person who generated the alarm information.

[0050] During analysis, the analysis unit can weight the analysis based on the occurrence frequency of alarm information. For example, the analysis unit prioritizes analysis of alarm information with a high occurrence frequency and postpones analysis of alarm information with a low occurrence frequency. The analysis unit can also analyze alarm information with a high occurrence frequency in detail and analyze alarm information with a low occurrence frequency in a simplified manner. Furthermore, the analysis unit can weight and analyze alarm information with a high occurrence frequency and downplay alarm information with a low occurrence frequency. Thus, weighting the analysis based on the occurrence frequency of alarm information enables efficient information analysis.

[0051] During analysis, the analysis unit can perform the analysis based on the geographic distribution of the alarm information. For example, the analysis unit prioritizes analysis of alarms within a specific area based on the geographic distribution of the alarm information. The analysis unit can also prioritize analysis of alarms in areas with a wide range of impact based on the geographic distribution of the alarm information. Furthermore, the analysis unit can also prioritize analysis of alarms in areas where important nodes are located based on the geographic distribution of the alarm information. This enables more accurate information analysis by performing analysis based on the geographic distribution of the alarm information.

[0052] During analysis, the analysis unit can improve the accuracy of the analysis by referring to literature related to the alarm information. For example, the analysis unit improves the accuracy of the analysis by referring to literature related to the alarm information. The analysis unit can also improve the accuracy of the analysis by referring to technical literature related to the alarm information. Furthermore, the analysis unit can also improve the accuracy of the analysis by referring to past cases related to the alarm information. As a result, by referring to literature related to the alarm information, more accurate information analysis is possible.

[0053] When analyzing, the analysis unit can perform the analysis based on the market value of the alarm information. For example, the analysis unit prioritizes the analysis of alarms with high importance based on the market value of the alarm information. The analysis unit can also prioritize the analysis of alarms with a wide impact range based on the market value of the alarm information. Furthermore, the analysis unit can also prioritize the analysis of alarms that have important nodes based on the market value of the alarm information. In this way, by performing the analysis based on the market value of the alarm information, more accurate information analysis is possible.

[0054] The summarization unit can adjust the level of detail of the summary based on the importance of the alarm information when generating the summary. For example, the summarization unit summarizes alarm information of high importance in detail and alarm information of low importance in a simplified manner. The summarization unit can also prioritize summarizing alarm information of high importance and postpone summarizing alarm information of low importance. Furthermore, the summarization unit can summarize alarm information of high importance in detail and omit alarm information of low importance. In this way, adjusting the level of detail of the summary based on the importance of the alarm information enables efficient information summarization.

[0055] The summarization unit can apply different summarization algorithms depending on the category of alarm information when generating a summary. For example, the summarization unit applies a network-specific summarization algorithm to alarm information of network devices. The summarization unit can also apply a server-specific summarization algorithm to alarm information of servers. Furthermore, the summarization unit can also apply a storage-specific summarization algorithm to alarm information of storage devices. This enables efficient information summarization by applying different summarization algorithms depending on the category of alarm information.

[0056] When generating a summary, the summarization unit can improve the accuracy of the summary based on past summarization results. For example, the summarization unit can adjust the summarization algorithm based on past summarization results to improve accuracy. The summarization unit can also adjust the summarization criteria based on past summarization results to improve accuracy. Furthermore, the summarization unit can adjust the summary priority based on past summarization results to improve accuracy. In this way, by improving the accuracy of the summary based on past summarization results, more accurate information summarization is possible.

[0057] When generating summaries, the summarization unit can determine the priority of summaries based on the time when alarm information occurred. For example, the summarization unit prioritizes summarizing recently occurring alarm information and postpones older alarm information. The summarization unit can also prioritize summarizing alarm information that occurred during a specific time period. Furthermore, the summarization unit can prioritize summarizing alarm information during a time when an important event occurred. In this way, by determining the priority of summaries based on the time when alarm information occurred, efficient information summarization is possible.

[0058] The summarization unit can adjust the order of summaries based on the relevance of the alarm information when generating summaries. For example, the summarization unit prioritizes summarizing highly relevant alarm information and postpones less relevant alarm information. The summarization unit can also summarize highly relevant alarm information in detail and summarize less relevant alarm information in a simplified manner. Furthermore, the summarization unit can prioritize summarizing highly relevant alarm information and omit less relevant alarm information. This enables efficient information summarization by adjusting the order of summaries based on the relevance of the alarm information.

[0059] When generating a summary, the summarization unit can adjust the way the summary is expressed depending on the location where the alarm information occurred. For example, the summarization unit prioritizes summarization of alarm information within a specific area. The summarization unit can also prioritize summarization of alarm information in areas with a wide range of impact. Furthermore, the summarization unit can also prioritize summarization of alarm information in areas where important nodes exist. This allows for efficient information summarization by adjusting the way the summary is expressed depending on the location where the alarm information occurred.

[0060] When identifying a main cause, the identification unit can improve the accuracy of identification based on the interrelationships between alarm information. For example, the identification unit identifies the main cause by grouping related alarms based on the interrelationships between alarm information. The identification unit can also identify the main cause by identifying the cause-effect relationship based on the interrelationships between alarm information. Furthermore, the identification unit can also identify the main cause by identifying a common cause when multiple alarms occur simultaneously based on the interrelationships between alarm information. This makes it possible to identify information more accurately by improving the accuracy of identification based on the interrelationships between alarm information.

[0061] When identifying the main cause, the identification unit can perform the identification based on attribute information of the person who generated the alarm information. For example, if the person who generated the alarm information is a specific device, the identification unit can identify the main cause based on attribute information of that device. Furthermore, if the person who generated the alarm information is a specific network segment, the identification unit can also identify the main cause based on attribute information of that segment. Furthermore, if the person who generated the alarm information is a specific user, the identification unit can also identify the main cause based on attribute information of that user. As a result, more accurate information identification is possible by performing the identification based on attribute information of the person who generated the alarm information.

[0062] When identifying the main cause, the identifying unit can assign specific weights based on the occurrence frequency of alarm information. For example, the identifying unit prioritizes identifying alarm information with a high occurrence frequency and postpones identifying alarm information with a low occurrence frequency. The identifying unit can also identify alarm information with a high occurrence frequency in detail and identify alarm information with a low occurrence frequency in a simplified manner. Furthermore, the identifying unit can assign weights to identify alarm information with a high occurrence frequency and downplay alarm information with a low occurrence frequency. In this way, by assigning specific weights based on the occurrence frequency of alarm information, efficient information identification is possible.

[0063] When identifying the main cause, the identifying unit can perform the identification based on the geographic distribution of the alarm information. For example, the identifying unit preferentially identifies main causes within a specific area based on the geographic distribution of the alarm information. The identifying unit can also preferentially identify main causes in areas with a wide range of impact based on the geographic distribution of the alarm information. Furthermore, the identifying unit can also preferentially identify main causes in areas where important nodes are located based on the geographic distribution of the alarm information. This enables more accurate information identification by performing identification based on the geographic distribution of the alarm information.

[0064] When identifying the main cause, the identifying unit can improve the accuracy of the identification by referring to literature related to the alarm information. For example, the identifying unit improves the accuracy of the identification by referring to literature related to the alarm information. The identifying unit can also improve the accuracy of the identification by referring to technical literature related to the alarm information. Furthermore, the identifying unit can also improve the accuracy of the identification by referring to past cases related to the alarm information. As a result, by referring to literature related to the alarm information, more accurate information identification is possible.

[0065] When identifying a main cause, the identification unit can perform the identification based on the market value of the alarm information. For example, the identification unit prioritizes identifying main causes with high importance based on the market value of the alarm information. The identification unit can also prioritize identifying main causes with a wide range of impact based on the market value of the alarm information. Furthermore, the identification unit can also prioritize identifying main causes for which important nodes exist based on the market value of the alarm information. As a result, more accurate information identification is possible by performing identification based on the market value of the alarm information.

[0066] The providing unit can adjust the level of detail of the provided information based on the importance of the main cause when providing the information. For example, the providing unit provides detailed information for main causes with high importance and provides simple information for main causes with low importance. The providing unit can also provide main causes with high importance first and postpone main causes with low importance. Furthermore, the providing unit can provide detailed information for main causes with high importance and omit information for main causes with low importance. In this way, by adjusting the level of detail of the provided information based on the importance of the main cause, efficient information provision is possible.

[0067] The providing unit can apply different providing algorithms depending on the category of the main cause when providing information. For example, the providing unit applies a providing algorithm dedicated to the network to the main cause of a network device. The providing unit can also apply a providing algorithm dedicated to the server to the main cause of a server. Furthermore, the providing unit can also apply a providing algorithm dedicated to storage to the main cause of a storage device. This makes it possible to provide information efficiently by applying different providing algorithms depending on the category of the main cause.

[0068] The providing unit can improve the accuracy of the information provided based on past provision results at the time of providing the information. For example, the providing unit can adjust the providing algorithm based on past provision results to improve the accuracy. The providing unit can also adjust the provision criteria based on past provision results to improve the accuracy. Furthermore, the providing unit can adjust the provision priority based on past provision results to improve the accuracy. In this way, by improving the accuracy of the information provided based on past provision results, more accurate information can be provided.

[0069] The providing unit can determine the priority of the information to be provided based on the time when the main cause occurred when providing the information. For example, the providing unit can provide information about a main cause that occurred recently with priority, and information about an older main cause with priority. The providing unit can also provide information about a main cause that occurred during a specific time period with priority. Furthermore, the providing unit can also provide information about a main cause at the time when an important event occurred with priority. In this way, by determining the priority of the information to be provided based on the time when the main cause occurred, efficient information provision is possible.

[0070] The providing unit can adjust the order of the information to be provided based on the relevance of the main causes when providing the information. For example, the providing unit can provide information about highly relevant main causes with priority and provide information about less relevant main causes later. The providing unit can also provide detailed information about highly relevant main causes and provide simplified information about less relevant main causes. Furthermore, the providing unit can also provide information about highly relevant main causes with priority and omit information about less relevant main causes. In this way, adjusting the order of the information to be provided based on the relevance of the main causes enables efficient information provision.

[0071] The providing unit can adjust the way the provided information is presented depending on the location where the main cause occurred when providing the information. For example, the providing unit can provide information about main causes in a specific area with priority. The providing unit can also provide information about main causes in an area with a wide range of impact with priority. Furthermore, the providing unit can also provide information about main causes in an area where important nodes are located with priority. This allows for efficient information provision by adjusting the way the information is presented depending on the location where the main cause occurred.

[0072] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0073] The maintenance support system can further include a prediction unit. The prediction unit can predict future failures based on collected alarm information and past failure data. For example, if the frequency of failures of a particular device is increasing, the prediction unit can predict the possibility that the device will fail in the near future. The prediction unit can also analyze failure trends by season or time of day, and identify devices that are prone to failure at certain times of the year. Furthermore, the prediction unit can analyze traffic patterns across the entire network and predict the possibility that a sudden increase in traffic will cause a failure. This allows maintenance personnel to take measures in advance, improving system stability.

[0074] The collection unit can also collect data from environmental sensors. Environmental sensors provide information such as temperature, humidity, and vibration. For example, if the temperature in a server room is abnormally high, the collection unit collects that information along with alarm information. If a vibration sensor detects abnormal vibration, that information is also collected. Furthermore, if a humidity sensor detects high humidity, the collection unit collects that information and can evaluate the risk of equipment failure. This makes it possible to prevent failures caused by environmental factors.

[0075] The filtering unit can further improve the accuracy of filtering by using machine learning algorithms. For example, it can learn from past alarm data and automatically classify alarms into important and non-important ones. The filtering unit can also use anomaly detection algorithms to detect alarms with unusual patterns and reassess their importance. Furthermore, the filtering unit can dynamically adjust filtering criteria based on user feedback. This improves filtering accuracy and reduces the risk of important alarm information being overlooked.

[0076] The analysis unit can further analyze alarm information using natural language processing technology. For example, it can analyze the content of alarm messages and extract common keywords and phrases. The analysis unit can also analyze the text data of alarm information and group similar alarms. Furthermore, the analysis unit can understand the context of alarm information and identify related alarms. This improves the accuracy of alarm information analysis and makes it easier to identify the root cause.

[0077] The summary section can also be equipped with a visual summary function. The visual summary function visually displays alarm information as graphs or charts. For example, it can graph the frequency of alarm occurrences along a time axis. It can also display the locations of alarm occurrences on a map to visually show which areas are experiencing the most alarms. Furthermore, alarm types and severity can be displayed in different colors, making the information easier to understand. This makes it easier for maintenance personnel to visually grasp the information and respond quickly.

[0078] The identification unit can further be equipped with a causal analysis function. The causal analysis function analyzes the causal relationships of alarm information and identifies the main cause and its impact. For example, it analyzes how a specific alarm affects the occurrence of other alarms. The causal analysis function can also identify the common cause when multiple alarms occur simultaneously. Furthermore, the causal analysis function can predict future failures based on past data. This allows maintenance personnel to more accurately identify the main cause and take appropriate measures.

[0079] The providing unit may further include a voice assistant function. The voice assistant function provides information to the maintenance personnel by voice. For example, the identified primary cause may be explained by voice. The voice assistant function may also answer questions from the maintenance personnel in real time. Furthermore, the voice assistant function improves work efficiency by enabling the maintenance personnel to obtain information without using their hands. This allows the maintenance personnel to obtain information and respond quickly and efficiently.

[0080] The processing flow of the first embodiment will be briefly explained below.

[0081] Step 1: The collection unit collects alarm information. The collection unit collects alarm information from, for example, network devices, servers, storage devices, etc. The collection unit can also collect alarm information in real time. Furthermore, the collection unit can also collect alarm information periodically. Step 2: The filtering unit filters the alarm information collected by the collection unit. For example, the filtering unit passes only important alarm information to the analysis unit. The filtering unit can also perform filtering based on the importance of the alarm information. Furthermore, the filtering unit can also perform filtering based on the category of the alarm information. Step 3: The analysis unit analyzes the alarm information filtered by the filtering unit and groups related alarms. The analysis unit determines the relevance based on information such as the content of the alarm, the time of occurrence, and the location of occurrence, and groups the alarms. The analysis unit can also perform analysis based on the correlation between the alarm information. Furthermore, the analysis unit can also perform analysis based on the frequency of occurrence of the alarm information. Step 4: The summarizing unit summarizes the alarm information grouped by the analyzing unit. For example, the summarizing unit summarizes the grouped alarm information. The summarizing unit can also summarize based on the importance of the alarm information. Furthermore, the summarizing unit can summarize based on the category of the alarm information. Step 5: The identifying unit identifies the main cause based on the information summarized by the summarizing unit. The identifying unit identifies the main cause based on, for example, the summarized information. The identifying unit can also identify the main cause based on the correlation between alarm information. Furthermore, the identifying unit can also identify the main cause based on the frequency of occurrence of alarm information. Step 6: The providing unit provides the main cause identified by the identifying unit to the maintenance person. For example, the providing unit provides the identified main cause to the maintenance person. The providing unit can also adjust the level of detail of the provided information based on the importance of the main cause. Furthermore, the providing unit can also adjust the level of detail of the provided information depending on the category of the main cause.

[0082] (Example 2) A system according to an embodiment of the present invention addresses the problem of network and system equipment maintenance, where a large number of equipment and devices are connected and a large number of alarms are generated when a failure occurs, making it difficult to identify the root cause. This system utilizes a generation AI to summarize information and identify the root cause. For example, alarm information generated by each equipment or device is collected, and the generation AI analyzes this information. The generation AI then groups related alarms based on information such as the alarm content, occurrence time, and occurrence location, and summarizes the information. Furthermore, the generation AI identifies the root cause based on the summarized information. This allows maintenance personnel to quickly identify the root cause and respond without being overwhelmed by the large amount of alarm information. This system is expected to improve the efficiency of response to failures in network and system equipment maintenance, reduce downtime, and improve system stability.

[0083] A maintenance support system according to an embodiment includes a collection unit, a filtering unit, an analysis unit, a summarization unit, an identification unit, and a provision unit. The collection unit collects alarm information. The collection unit collects alarm information from, for example, network devices, servers, storage devices, etc. The collection unit can also collect alarm information in real time. The collection unit can also collect alarm information periodically. The filtering unit filters the alarm information collected by the collection unit. For example, the filtering unit passes only important alarm information to the analysis unit. The filtering unit can also perform filtering based on the importance of the alarm information. The filtering unit can also perform filtering according to the category of the alarm information. The analysis unit analyzes the alarm information filtered by the filtering unit and groups related alarms. The analysis unit determines the relevance based on information such as the content, time of occurrence, and location of the alarm, and groups the alarms. The analysis unit can also perform analysis based on the interrelationship of the alarm information. The analysis unit can also perform analysis based on the frequency of occurrence of the alarm information. The summarization unit summarizes the alarm information grouped by the analysis unit. The summarizing unit summarizes, for example, grouped alarm information. The summarizing unit can also perform summarization based on the importance of the alarm information. Furthermore, the summarizing unit can also perform summarization according to the category of the alarm information. The identifying unit identifies a main cause based on the information summarized by the summarizing unit. The identifying unit identifies a main cause based on, for example, the summarized information. The identifying unit can also identify a main cause based on a correlation between the alarm information. Furthermore, the identifying unit can also identify a main cause based on the frequency of occurrence of the alarm information. The providing unit provides the main cause identified by the identifying unit to a maintenance technician. The providing unit provides the identified main cause to a maintenance technician, for example. The providing unit can also adjust the level of detail of the provided information based on the importance of the main cause. Furthermore, the providing unit can adjust the level of detail of the provided information according to the category of the main cause.As a result, the maintenance support system according to the embodiment can efficiently collect, filter, analyze, summarize, identify the main cause of, and provide alarm information.

[0084] The collection unit can collect alarm information from network devices, servers, and storage devices. The collection unit collects alarm information from, for example, network devices. Network devices include routers, switches, firewalls, etc. The collection unit can also collect alarm information from servers. Servers include physical servers, virtual servers, cloud servers, etc. The collection unit can also collect alarm information from storage devices. Storage devices include hard disk drives (HDDs), solid-state drives (SSDs), network-attached storage (NAS), etc. This enables comprehensive monitoring by collecting alarm information from a variety of devices.

[0085] The filtering unit can pass only important alarm information to the analysis unit. The filtering unit performs filtering based on the importance of the alarm information, for example. Criteria for evaluating the importance include the severity of the error and the scope of the impact. The filtering unit can also perform filtering according to the category of the alarm information. Categories include error messages, warning messages, and notification messages. The filtering unit can also perform filtering based on the time at which the alarm information occurred. The time at which the alarm information occurred includes a timestamp, a time period, and so on. This improves the efficiency of analysis by analyzing only important alarm information.

[0086] The analysis unit can determine relevance based on information about the alarm content, occurrence time, and occurrence location, and group the alarms. The analysis unit can determine relevance based on the alarm content, for example. The alarm content includes the type of error message, error code, etc. The analysis unit can also determine relevance based on the time the alarm occurred. The occurrence time includes a timestamp, time period, etc. The analysis unit can also determine relevance based on the location where the alarm occurred. The occurrence location includes geographical location information, location within the facility, etc. By grouping related alarms, it becomes easier to identify the main cause.

[0087] The summarization unit can summarize the grouped alarm information. For example, the summarization unit summarizes the grouped alarm information. Specific summarization methods include the length of the sentence, the importance of the information to be summarized, and the like. The summarization unit can also perform summarization based on the importance of the alarm information. Criteria for evaluating the importance include the severity of the error and the scope of the impact. Furthermore, the summarization unit can also perform summarization according to the category of the alarm information. Categories include error messages, warning messages, notification messages, and the like. This makes it easier to organize the information by summarizing the grouped alarm information.

[0088] The identification unit can identify the main cause based on the summarized information. The identification unit identifies the main cause based on, for example, the summarized information. Methods for identifying the main cause include cause evaluation criteria, identification algorithms, etc. The identification unit can also identify the main cause based on the correlation between alarm information. Criteria for evaluating the correlation include common causes, scope of impact, etc. The identification unit can also identify the main cause based on the frequency of occurrence of alarm information. Specific details of the frequency of occurrence include the number of occurrences, the number of occurrences per hour, etc. This makes it possible to respond quickly by identifying the main cause based on summarized information.

[0089] The providing unit can provide the identified main cause to a maintenance person. For example, the providing unit provides the identified main cause to a maintenance person. Specific methods of providing the information include the timing of providing the information and details of the providing method. The providing unit can also adjust the level of detail of the information to be provided based on the importance of the main cause. Evaluation criteria for the level of detail include the granularity of the information and the comprehensiveness of the information. The providing unit can also adjust the level of detail of the information to be provided depending on the category of the main cause. Categories include network equipment, servers, storage devices, etc. This allows the identified main cause to be provided to a maintenance person, enabling a prompt response.

[0090] The collection unit can estimate the user's emotions and adjust the timing of collecting alarm information based on the estimated user emotions. For example, when the user is feeling stressed, the collection unit reduces the frequency of collecting alarm information and collects only important alarms. The collection unit can also collect alarm information at a normal collection frequency when the user is relaxed. Furthermore, when the user is in a hurry, the collection unit can collect alarm information in real time to enable immediate response. This enables more appropriate information collection by adjusting the timing of collecting alarm information according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0091] The collection unit monitors the operating status of each device in real time and can immediately collect alarm information if an abnormality occurs. For example, the collection unit monitors the operating status of network devices in real time and immediately collects alarm information if an abnormality occurs. The collection unit can also monitor the operating status of servers in real time and immediately collect alarm information if an abnormality occurs. Furthermore, the collection unit can monitor the operating status of storage devices in real time and immediately collect alarm information if an abnormality occurs. This allows for rapid response by detecting abnormalities in real time and immediately collecting alarm information.

[0092] When collecting alarm information, the collection unit can determine the priority of collection by referring to the past failure history of each device. For example, the collection unit refers to the past failure history of each device and prioritizes collecting alarm information about devices that have frequently failed. The collection unit can also refer to the past failure history of each device and prioritize collecting alarm information about devices that have experienced a serious failure. Furthermore, the collection unit can also refer to the past failure history of each device and prioritize collecting alarm information about devices that have recently experienced a failure. In this way, by referring to the past failure history, important alarm information can be collected preferentially.

[0093] When collecting alarm information, the collection unit can adjust the collection range based on network topology information. For example, the collection unit prioritizes the collection of alarm information from important nodes based on the network topology information. The collection unit can also collect alarm information taking into account the impact range of a failure based on the network topology information. Furthermore, the collection unit can also prioritize the collection of alarm information from devices with redundant configurations based on the network topology information. This enables efficient information collection by optimizing the collection range based on the network topology information.

[0094] The collection unit can estimate the user's emotions and determine the priority of alarm information to be collected based on the estimated user emotions. For example, when the user is feeling stressed, the collection unit prioritizes collecting only alarm information with high importance. In addition, when the user is relaxed, the collection unit can also collect alarm information with normal priority. Furthermore, when the user is in a hurry, the collection unit can prioritize collecting important alarm information in real time. This enables more appropriate information collection by determining the priority of alarm information according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0095] When collecting alarm information, the collection unit can prioritize collecting highly relevant information based on the geographical location information of each device. For example, the collection unit prioritizes collecting alarm information from nearby devices based on the geographical location information of each device. The collection unit can also prioritize collecting alarm information within a specific area based on the geographical location information of each device. Furthermore, the collection unit can also prioritize collecting alarm information from areas with a wide impact range based on the geographical location information of each device. This enables efficient information collection by prioritized collection of highly relevant information based on geographical location information.

[0096] When collecting alarm information, the collection unit can analyze the social media activity of each device and collect related information. For example, the collection unit analyzes the social media activity of each device and collects related alarm information. The collection unit can also analyze the social media activity of each device and collect alarm information based on user feedback. Furthermore, the collection unit can analyze the social media activity of each device and collect alarm information based on trend information. This makes it possible to efficiently collect related information by analyzing social media activity.

[0097] When collecting alarm information, the collection unit can customize the collection method based on past feedback from each device. For example, the collection unit customizes the collection method based on past feedback from each device and prioritizes the collection of important alarm information. The collection unit can also customize the collection method and adjust the collection frequency based on past feedback from each device. Furthermore, the collection unit can customize the collection method and optimize the collection range based on past feedback from each device. In this way, efficient information collection is possible by customizing the collection method based on past feedback.

[0098] The filtering unit can estimate the user's emotions and adjust filtering criteria based on the estimated user emotions. For example, if the user is feeling stressed, the filtering unit filters only alarm information with high importance. Also, if the user is relaxed, the filtering unit can filter alarm information using normal filtering criteria. Furthermore, if the user is in a hurry, the filtering unit can filter important alarm information in real time. This enables more appropriate information filtering by adjusting the filtering criteria according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0099] The filtering unit can adjust the level of detail of filtering based on the importance of the alarm information when filtering. For example, the filtering unit filters alarm information of high importance in detail and filters alarm information of low importance in a simplified manner. The filtering unit can also filter alarm information of high importance with priority and postpone filtering of alarm information of low importance. Furthermore, the filtering unit can filter alarm information of high importance in detail and omit alarm information of low importance. In this way, adjusting the level of detail of filtering based on the importance of the alarm information enables efficient information filtering.

[0100] The filtering unit can apply different filtering algorithms depending on the category of alarm information when filtering. For example, the filtering unit applies a filtering algorithm dedicated to networks to alarm information about network devices. The filtering unit can also apply a filtering algorithm dedicated to servers to alarm information about servers. Furthermore, the filtering unit can also apply a filtering algorithm dedicated to storage to alarm information about storage devices. This allows for efficient information filtering by applying different filtering algorithms depending on the category of alarm information.

[0101] The filtering unit can improve the accuracy of filtering based on past filtering results during filtering. For example, the filtering unit adjusts the filtering algorithm based on past filtering results to improve accuracy. The filtering unit can also adjust the filtering criteria based on past filtering results to improve accuracy. Furthermore, the filtering unit can adjust the filtering priority based on past filtering results to improve accuracy. In this way, by improving the filtering accuracy based on past filtering results, more accurate information filtering is possible.

[0102] The filtering unit can estimate the user's emotions and determine filtering priorities based on the estimated user emotions. For example, when the user is feeling stressed, the filtering unit prioritizes filtering of alarm information with high importance. The filtering unit can also filter alarm information with normal priority when the user is relaxed. Furthermore, when the user is in a hurry, the filtering unit can also prioritize filtering of important alarm information in real time. This enables more appropriate information filtering by determining filtering priorities according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0103] During filtering, the filtering unit can determine the filtering priority based on the time when the alarm information occurred. For example, the filtering unit preferentially filters recently occurring alarm information and postpones older alarm information. The filtering unit can also preferentially filter alarm information that occurred during a specific time period. Furthermore, the filtering unit can also preferentially filter alarm information when an important event occurred. In this way, by determining the filtering priority based on the time when the alarm information occurred, efficient information filtering is possible.

[0104] The filtering unit can adjust the filtering order based on the relevance of the alarm information during filtering. For example, the filtering unit preferentially filters highly relevant alarm information and postpones less relevant alarm information. The filtering unit can also filter highly relevant alarm information in detail and filter less relevant alarm information simply. Furthermore, the filtering unit can also filter highly relevant alarm information preferentially and omit less relevant alarm information. In this way, adjusting the filtering order based on the relevance of the alarm information enables efficient information filtering.

[0105] When filtering, the filtering unit can adjust the filtering criteria according to the location where the alarm information occurred. For example, the filtering unit preferentially filters alarm information within a specific area. The filtering unit can also preferentially filter alarm information in areas with a wide range of impact. Furthermore, the filtering unit can also preferentially filter alarm information in areas where important nodes are located. This allows for efficient information filtering by adjusting the filtering criteria according to the location where the alarm information occurred.

[0106] The analysis unit can estimate the user's emotions and adjust the analysis criteria based on the estimated user emotions. For example, if the user is feeling stressed, the analysis unit prioritizes analysis of alarm information with high importance. The analysis unit can also analyze alarm information using normal analysis criteria when the user is relaxed. Furthermore, if the user is in a hurry, the analysis unit can prioritize analysis of important alarm information in real time. This enables more appropriate information analysis by adjusting the analysis criteria according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0107] During analysis, the analysis unit can improve the accuracy of the analysis based on the interrelationships between alarm information. For example, the analysis unit groups related alarms and analyzes them based on the interrelationships between alarm information. The analysis unit can also identify and analyze the relationship between cause and effect based on the interrelationships between alarm information. Furthermore, the analysis unit can also identify and analyze a common cause when multiple alarms occur simultaneously based on the interrelationships between alarm information. In this way, by improving the accuracy of the analysis based on the interrelationships between alarm information, more accurate information analysis becomes possible.

[0108] During analysis, the analysis unit can perform the analysis based on attribute information of the person who generated the alarm information. For example, if the person who generated the alarm information is a specific device, the analysis unit performs the analysis based on attribute information of that device. Furthermore, if the person who generated the alarm information is a specific network segment, the analysis unit can also perform the analysis based on attribute information of that segment. Furthermore, if the person who generated the alarm information is a specific user, the analysis unit can also perform the analysis based on attribute information of that user. This enables more accurate information analysis by performing the analysis based on attribute information of the person who generated the alarm information.

[0109] During analysis, the analysis unit can weight the analysis based on the occurrence frequency of alarm information. For example, the analysis unit prioritizes analysis of alarm information with a high occurrence frequency and postpones analysis of alarm information with a low occurrence frequency. The analysis unit can also analyze alarm information with a high occurrence frequency in detail and analyze alarm information with a low occurrence frequency in a simplified manner. Furthermore, the analysis unit can weight and analyze alarm information with a high occurrence frequency and downplay alarm information with a low occurrence frequency. Thus, weighting the analysis based on the occurrence frequency of alarm information enables efficient information analysis.

[0110] The analysis unit can estimate the user's emotions and adjust the display order of the analysis results based on the estimated user emotions. For example, when the user is feeling stressed, the analysis unit can prioritize displaying analysis results with high importance. The analysis unit can also display analysis results in a normal display order when the user is relaxed. Furthermore, when the user is in a hurry, the analysis unit can prioritize displaying important analysis results in real time. This allows for more appropriate information display by adjusting the display order of the analysis results according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0111] During analysis, the analysis unit can perform the analysis based on the geographic distribution of the alarm information. For example, the analysis unit prioritizes analysis of alarms within a specific area based on the geographic distribution of the alarm information. The analysis unit can also prioritize analysis of alarms in areas with a wide range of impact based on the geographic distribution of the alarm information. Furthermore, the analysis unit can also prioritize analysis of alarms in areas where important nodes are located based on the geographic distribution of the alarm information. This enables more accurate information analysis by performing analysis based on the geographic distribution of the alarm information.

[0112] During analysis, the analysis unit can improve the accuracy of the analysis by referring to literature related to the alarm information. For example, the analysis unit improves the accuracy of the analysis by referring to literature related to the alarm information. The analysis unit can also improve the accuracy of the analysis by referring to technical literature related to the alarm information. Furthermore, the analysis unit can also improve the accuracy of the analysis by referring to past cases related to the alarm information. As a result, by referring to literature related to the alarm information, more accurate information analysis is possible.

[0113] When analyzing, the analysis unit can perform the analysis based on the market value of the alarm information. For example, the analysis unit prioritizes the analysis of alarms with high importance based on the market value of the alarm information. The analysis unit can also prioritize the analysis of alarms with a wide impact range based on the market value of the alarm information. Furthermore, the analysis unit can also prioritize the analysis of alarms that have important nodes based on the market value of the alarm information. In this way, by performing the analysis based on the market value of the alarm information, more accurate information analysis is possible.

[0114] The summarization unit can estimate the user's emotions and adjust the way the summary is presented based on the estimated user emotions. For example, if the user is feeling stressed, the summarization unit can provide a concise and to-the-point summary. If the user is relaxed, the summarization unit can also provide a summary that includes detailed information. Furthermore, if the user is in a hurry, the summarization unit can also provide a summary that can be quickly understood. This enables more appropriate information summarization by adjusting the way the summary is presented according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0115] The summarization unit can adjust the level of detail of the summary based on the importance of the alarm information when generating the summary. For example, the summarization unit summarizes alarm information of high importance in detail and alarm information of low importance in a simplified manner. The summarization unit can also prioritize summarizing alarm information of high importance and postpone summarizing alarm information of low importance. Furthermore, the summarization unit can summarize alarm information of high importance in detail and omit alarm information of low importance. In this way, adjusting the level of detail of the summary based on the importance of the alarm information enables efficient information summarization.

[0116] The summarization unit can apply different summarization algorithms depending on the category of alarm information when generating a summary. For example, the summarization unit applies a network-specific summarization algorithm to alarm information of network devices. The summarization unit can also apply a server-specific summarization algorithm to alarm information of servers. Furthermore, the summarization unit can also apply a storage-specific summarization algorithm to alarm information of storage devices. This enables efficient information summarization by applying different summarization algorithms depending on the category of alarm information.

[0117] When generating a summary, the summarization unit can improve the accuracy of the summary based on past summarization results. For example, the summarization unit can adjust the summarization algorithm based on past summarization results to improve accuracy. The summarization unit can also adjust the summarization criteria based on past summarization results to improve accuracy. Furthermore, the summarization unit can adjust the summary priority based on past summarization results to improve accuracy. In this way, by improving the accuracy of the summary based on past summarization results, more accurate information summarization is possible.

[0118] The summarization unit can estimate the user's emotions and adjust the length of the summary based on the estimated user emotions. For example, if the user is stressed, the summarization unit can provide a short, concise summary. If the user is relaxed, the summarization unit can also provide a longer summary with detailed explanations. Furthermore, if the user is in a hurry, the summarization unit can also provide a short summary that can be quickly understood. This allows for more appropriate information summarization by adjusting the length of the summary according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0119] When generating summaries, the summarization unit can determine the priority of summaries based on the time when alarm information occurred. For example, the summarization unit prioritizes summarizing recently occurring alarm information and postpones older alarm information. The summarization unit can also prioritize summarizing alarm information that occurred during a specific time period. Furthermore, the summarization unit can prioritize summarizing alarm information during a time when an important event occurred. In this way, by determining the priority of summaries based on the time when alarm information occurred, efficient information summarization is possible.

[0120] The summarization unit can adjust the order of summaries based on the relevance of the alarm information when generating summaries. For example, the summarization unit prioritizes summarizing highly relevant alarm information and postpones less relevant alarm information. The summarization unit can also summarize highly relevant alarm information in detail and summarize less relevant alarm information in a simplified manner. Furthermore, the summarization unit can prioritize summarizing highly relevant alarm information and omit less relevant alarm information. This enables efficient information summarization by adjusting the order of summaries based on the relevance of the alarm information.

[0121] When generating a summary, the summarization unit can adjust the way the summary is expressed depending on the location where the alarm information occurred. For example, the summarization unit prioritizes summarization of alarm information within a specific area. The summarization unit can also prioritize summarization of alarm information in areas with a wide range of impact. Furthermore, the summarization unit can also prioritize summarization of alarm information in areas where important nodes exist. This allows for efficient information summarization by adjusting the way the summary is expressed depending on the location where the alarm information occurred.

[0122] The identification unit can estimate the user's emotions and adjust the method for identifying the main cause based on the estimated user emotions. For example, if the user is feeling stressed, the identification unit can provide a concise and to-the-point identification method. If the user is relaxed, the identification unit can also provide a method for identifying that includes detailed information. Furthermore, if the user is in a hurry, the identification unit can also provide a method for identifying that is quickly understandable. This allows for more appropriate information identification by adjusting the method for identifying the main cause according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0123] When identifying a main cause, the identification unit can improve the accuracy of identification based on the interrelationships between alarm information. For example, the identification unit identifies the main cause by grouping related alarms based on the interrelationships between alarm information. The identification unit can also identify the main cause by identifying the cause-effect relationship based on the interrelationships between alarm information. Furthermore, the identification unit can also identify the main cause by identifying a common cause when multiple alarms occur simultaneously based on the interrelationships between alarm information. This makes it possible to identify information more accurately by improving the accuracy of identification based on the interrelationships between alarm information.

[0124] When identifying the main cause, the identification unit can perform the identification based on attribute information of the person who generated the alarm information. For example, if the person who generated the alarm information is a specific device, the identification unit can identify the main cause based on attribute information of that device. Furthermore, if the person who generated the alarm information is a specific network segment, the identification unit can also identify the main cause based on attribute information of that segment. Furthermore, if the person who generated the alarm information is a specific user, the identification unit can also identify the main cause based on attribute information of that user. As a result, more accurate information identification is possible by performing the identification based on attribute information of the person who generated the alarm information.

[0125] When identifying the main cause, the identifying unit can assign specific weights based on the occurrence frequency of alarm information. For example, the identifying unit prioritizes identifying alarm information with a high occurrence frequency and postpones identifying alarm information with a low occurrence frequency. The identifying unit can also identify alarm information with a high occurrence frequency in detail and identify alarm information with a low occurrence frequency in a simplified manner. Furthermore, the identifying unit can assign weights to identify alarm information with a high occurrence frequency and downplay alarm information with a low occurrence frequency. In this way, by assigning specific weights based on the occurrence frequency of alarm information, efficient information identification is possible.

[0126] The identification unit can estimate the user's emotion and adjust the display method of the main cause based on the estimated user emotion. For example, if the user is feeling stressed, the identification unit can provide a concise and to-the-point display method. If the user is relaxed, the identification unit can also provide a display method including detailed information. Furthermore, if the user is in a hurry, the identification unit can also provide a display method that can be quickly understood. This enables more appropriate information display by adjusting the display method of the main cause according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples.

[0127] When identifying the main cause, the identifying unit can perform the identification based on the geographic distribution of the alarm information. For example, the identifying unit preferentially identifies main causes within a specific area based on the geographic distribution of the alarm information. The identifying unit can also preferentially identify main causes in areas with a wide range of impact based on the geographic distribution of the alarm information. Furthermore, the identifying unit can also preferentially identify main causes in areas where important nodes are located based on the geographic distribution of the alarm information. This enables more accurate information identification by performing identification based on the geographic distribution of the alarm information.

[0128] When identifying the main cause, the identifying unit can improve the accuracy of the identification by referring to literature related to the alarm information. For example, the identifying unit improves the accuracy of the identification by referring to literature related to the alarm information. The identifying unit can also improve the accuracy of the identification by referring to technical literature related to the alarm information. Furthermore, the identifying unit can also improve the accuracy of the identification by referring to past cases related to the alarm information. As a result, by referring to literature related to the alarm information, more accurate information identification is possible.

[0129] When identifying a main cause, the identification unit can perform the identification based on the market value of the alarm information. For example, the identification unit prioritizes identifying main causes with high importance based on the market value of the alarm information. The identification unit can also prioritize identifying main causes with a wide range of impact based on the market value of the alarm information. Furthermore, the identification unit can also prioritize identifying main causes for which important nodes exist based on the market value of the alarm information. As a result, more accurate information identification is possible by performing identification based on the market value of the alarm information.

[0130] The providing unit can estimate the user's emotions and adjust the way information is presented based on the estimated user's emotions. For example, if the user is feeling stressed, the providing unit can provide concise, to-the-point information. Furthermore, if the user is relaxed, the providing unit can also provide a way of providing information that includes detailed information. Furthermore, if the user is in a hurry, the providing unit can also provide information that can be quickly understood. This allows for more appropriate information to be provided by adjusting the way information is presented according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0131] The providing unit can adjust the level of detail of the provided information based on the importance of the main cause when providing the information. For example, the providing unit provides detailed information for main causes with high importance and provides simple information for main causes with low importance. The providing unit can also provide main causes with high importance first and postpone main causes with low importance. Furthermore, the providing unit can provide detailed information for main causes with high importance and omit information for main causes with low importance. In this way, by adjusting the level of detail of the provided information based on the importance of the main cause, efficient information provision is possible.

[0132] The providing unit can apply different providing algorithms depending on the category of the main cause when providing information. For example, the providing unit applies a providing algorithm dedicated to the network to the main cause of a network device. The providing unit can also apply a providing algorithm dedicated to the server to the main cause of a server. Furthermore, the providing unit can also apply a providing algorithm dedicated to storage to the main cause of a storage device. This makes it possible to provide information efficiently by applying different providing algorithms depending on the category of the main cause.

[0133] The providing unit can improve the accuracy of the information provided based on past provision results at the time of providing the information. For example, the providing unit can adjust the providing algorithm based on past provision results to improve the accuracy. The providing unit can also adjust the provision criteria based on past provision results to improve the accuracy. Furthermore, the providing unit can adjust the provision priority based on past provision results to improve the accuracy. In this way, by improving the accuracy of the information provided based on past provision results, more accurate information can be provided.

[0134] The providing unit can estimate the user's emotions and adjust the length of the information to be provided based on the estimated user emotions. For example, if the user is feeling stressed, the providing unit can provide short, to-the-point information. If the user is relaxed, the providing unit can also provide longer information with detailed explanations. Furthermore, if the user is in a hurry, the providing unit can also provide short information that can be quickly understood. This allows for more appropriate information to be provided by adjusting the length of the information to be provided according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0135] The providing unit can determine the priority of the information to be provided based on the time when the main cause occurred when providing the information. For example, the providing unit can provide information about a main cause that occurred recently with priority, and information about an older main cause with priority. The providing unit can also provide information about a main cause that occurred during a specific time period with priority. Furthermore, the providing unit can also provide information about a main cause at the time when an important event occurred with priority. In this way, by determining the priority of the information to be provided based on the time when the main cause occurred, efficient information provision is possible.

[0136] The providing unit can adjust the order of the information to be provided based on the relevance of the main causes when providing the information. For example, the providing unit can provide information about highly relevant main causes with priority and provide information about less relevant main causes later. The providing unit can also provide detailed information about highly relevant main causes and provide simplified information about less relevant main causes. Furthermore, the providing unit can also provide information about highly relevant main causes with priority and omit information about less relevant main causes. In this way, adjusting the order of the information to be provided based on the relevance of the main causes enables efficient information provision.

[0137] The providing unit can adjust the way the provided information is presented depending on the location where the main cause occurred when providing the information. For example, the providing unit can provide information about main causes in a specific area with priority. The providing unit can also provide information about main causes in an area with a wide range of impact with priority. Furthermore, the providing unit can also provide information about main causes in an area where important nodes are located with priority. This allows for efficient information provision by adjusting the way the information is presented depending on the location where the main cause occurred. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, filtering unit, analysis unit, summarization unit, identification unit, and provision unit, described above, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects alarm information via the control unit 46A of the smart device 14, and the alarm information is analyzed by the identification processing unit 290 of the data processing device 12. The filtering unit is realized by the identification processing unit 290 of the data processing device 12 and passes only important alarm information to the analysis unit. The analysis unit groups the alarm information via the identification processing unit 290 of the data processing device 12, and the summarization unit summarizes the alarm information via the identification processing unit 290 of the data processing device 12. The identification unit identifies the main cause via the identification processing unit 290 of the data processing device 12, and the provision unit provides the identified cause to a maintenance technician via the control unit 46A of the smart device 14. The collection unit can estimate the user's emotion and adjust the timing of collecting alarm information based on the estimated emotion. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, filtering unit, analysis unit, summarization unit, identification unit, and provision unit, described above, is realized, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects alarm information via the control unit 46A of the smart glasses 214, and the alarm information is analyzed by the identification processing unit 290 of the data processing device 12. The filtering unit is realized by the identification processing unit 290 of the data processing device 12 and passes only important alarm information to the analysis unit. The analysis unit groups the alarm information via the identification processing unit 290 of the data processing device 12, and the summarization unit summarizes the alarm information via the identification processing unit 290 of the data processing device 12. The identification unit identifies the main cause via the identification processing unit 290 of the data processing device 12, and the provision unit provides the identified cause to a maintenance technician via the control unit 46A of the smart glasses 214. The collection unit can estimate the user's emotion and adjust the timing of collecting alarm information based on the estimated emotion. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned collection unit, filtering unit, analysis unit, summarization unit, identification unit, and provision unit is realized, for example, in at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit collects alarm information via the control unit 46A of the headset type terminal 314, and the alarm information is analyzed by the identification processing unit 290 of the data processing device 12. The filtering unit is realized by the identification processing unit 290 of the data processing device 12 and passes only important alarm information to the analysis unit. The analysis unit groups the alarm information via the identification processing unit 290 of the data processing device 12, and the summarization unit summarizes the alarm information via the identification processing unit 290 of the data processing device 12. The identification unit identifies the main cause via the identification processing unit 290 of the data processing device 12, and the provision unit provides the identified cause to a maintenance technician via the control unit 46A of the headset type terminal 314. The collection unit can estimate the user's emotion and adjust the timing of collecting alarm information based on the estimated emotion. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned collection unit, filtering unit, analysis unit, summarization unit, identification unit, and provision unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects alarm information via the control unit 46A of the robot 414, and the alarm information is analyzed by the identification processing unit 290 of the data processing device 12. The filtering unit is realized by the identification processing unit 290 of the data processing device 12 and passes only important alarm information to the analysis unit. The analysis unit groups the alarm information via the identification processing unit 290 of the data processing device 12, and the summarization unit summarizes the alarm information via the identification processing unit 290 of the data processing device 12. The identification unit identifies the main cause via the identification processing unit 290 of the data processing device 12, and the provision unit provides the identified cause to a maintenance technician via the control unit 46A of the robot 414. The collection unit can estimate the user's emotion and adjust the timing of collecting alarm information based on the estimated emotion.

[0138] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0139] The maintenance support system can further include a prediction unit. The prediction unit can predict future failures based on collected alarm information and past failure data. For example, if the frequency of failures of a particular device is increasing, the prediction unit can predict the possibility that the device will fail in the near future. The prediction unit can also analyze failure trends by season or time of day, and identify devices that are prone to failure at certain times of the year. Furthermore, the prediction unit can analyze traffic patterns across the entire network and predict the possibility that a sudden increase in traffic will cause a failure. This allows maintenance personnel to take measures in advance, improving system stability.

[0140] The collection unit can also collect data from environmental sensors. Environmental sensors provide information such as temperature, humidity, and vibration. For example, if the temperature in a server room is abnormally high, the collection unit collects that information along with alarm information. If a vibration sensor detects abnormal vibration, that information is also collected. Furthermore, if a humidity sensor detects high humidity, the collection unit collects that information and can evaluate the risk of equipment failure. This makes it possible to prevent failures caused by environmental factors.

[0141] The filtering unit can further improve the accuracy of filtering by using machine learning algorithms. For example, it can learn from past alarm data and automatically classify alarms into important and non-important ones. The filtering unit can also use anomaly detection algorithms to detect alarms with unusual patterns and reassess their importance. Furthermore, the filtering unit can dynamically adjust filtering criteria based on user feedback. This improves filtering accuracy and reduces the risk of important alarm information being overlooked.

[0142] The analysis unit can further analyze alarm information using natural language processing technology. For example, it can analyze the content of alarm messages and extract common keywords and phrases. The analysis unit can also analyze the text data of alarm information and group similar alarms. Furthermore, the analysis unit can understand the context of alarm information and identify related alarms. This improves the accuracy of alarm information analysis and makes it easier to identify the root cause.

[0143] The summary section can also be equipped with a visual summary function. The visual summary function visually displays alarm information as graphs or charts. For example, it can graph the frequency of alarm occurrences along a time axis. It can also display the locations of alarm occurrences on a map to visually show which areas are experiencing the most alarms. Furthermore, alarm types and severity can be displayed in different colors, making the information easier to understand. This makes it easier for maintenance personnel to visually grasp the information and respond quickly.

[0144] The identification unit can further be equipped with a causal analysis function. The causal analysis function analyzes the causal relationships of alarm information and identifies the main cause and its impact. For example, it analyzes how a specific alarm affects the occurrence of other alarms. The causal analysis function can also identify the common cause when multiple alarms occur simultaneously. Furthermore, the causal analysis function can predict future failures based on past data. This allows maintenance personnel to more accurately identify the main cause and take appropriate measures.

[0145] The providing unit may further include a voice assistant function. The voice assistant function provides information to the maintenance personnel by voice. For example, the identified primary cause may be explained by voice. The voice assistant function may also answer questions from the maintenance personnel in real time. Furthermore, the voice assistant function improves work efficiency by enabling the maintenance personnel to obtain information without using their hands. This allows the maintenance personnel to obtain information and respond quickly and efficiently.

[0146] The collection unit can estimate the user's emotions and adjust the timing of alarm information collection based on the estimated user emotions. For example, if the user is feeling stressed, the collection unit can reduce the frequency of alarm information collection and collect only important alarms. The collection unit can also collect alarm information at a normal collection frequency if the user is relaxed. Furthermore, if the user is in a hurry, the collection unit can collect alarm information in real time to enable an immediate response. This allows for more appropriate information collection by adjusting the timing of alarm information collection according to the user's emotions. The emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0147] The filtering unit can estimate the user's emotions and adjust filtering criteria based on the estimated user emotions. For example, if the user is feeling stressed, only alarm information with high importance is filtered. The filtering unit can also filter alarm information using normal filtering criteria when the user is relaxed. Furthermore, the filtering unit can also filter important alarm information in real time when the user is in a hurry. This enables more appropriate information filtering by adjusting filtering criteria according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI.

[0148] The analysis unit can estimate the user's emotions and adjust the analysis criteria based on the estimated user emotions. For example, if the user is feeling stressed, it prioritizes analysis of alarm information with high importance. The analysis unit can also analyze alarm information using normal analysis criteria when the user is relaxed. Furthermore, if the user is in a hurry, the analysis unit can prioritize analysis of important alarm information in real time. This allows for more appropriate information analysis by adjusting the analysis criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI can be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI.

[0149] The processing flow of the second embodiment will be briefly explained below.

[0150] Step 1: The collection unit collects alarm information. The collection unit collects alarm information from, for example, network devices, servers, storage devices, etc. The collection unit can also collect alarm information in real time. Furthermore, the collection unit can also collect alarm information periodically. Step 2: The filtering unit filters the alarm information collected by the collection unit. For example, the filtering unit passes only important alarm information to the analysis unit. The filtering unit can also perform filtering based on the importance of the alarm information. Furthermore, the filtering unit can also perform filtering based on the category of the alarm information. Step 3: The analysis unit analyzes the alarm information filtered by the filtering unit and groups related alarms. The analysis unit determines the relevance based on information such as the content of the alarm, the time of occurrence, and the location of occurrence, and groups the alarms. The analysis unit can also perform analysis based on the correlation between the alarm information. Furthermore, the analysis unit can also perform analysis based on the frequency of occurrence of the alarm information. Step 4: The summarizing unit summarizes the alarm information grouped by the analyzing unit. For example, the summarizing unit summarizes the grouped alarm information. The summarizing unit can also summarize based on the importance of the alarm information. Furthermore, the summarizing unit can summarize based on the category of the alarm information. Step 5: The identifying unit identifies the main cause based on the information summarized by the summarizing unit. The identifying unit identifies the main cause based on, for example, the summarized information. The identifying unit can also identify the main cause based on the correlation between alarm information. Furthermore, the identifying unit can also identify the main cause based on the frequency of occurrence of alarm information. Step 6: The providing unit provides the main cause identified by the identifying unit to the maintenance person. For example, the providing unit provides the identified main cause to the maintenance person. The providing unit can also adjust the level of detail of the provided information based on the importance of the main cause. Furthermore, the providing unit can also adjust the level of detail of the provided information depending on the category of the main cause.

[0151] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0152] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0153] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0156] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0157] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0158] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0159] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0160] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0161] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0162] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0163] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0164] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0165] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0166] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0167] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0168] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0169] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0170] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0171] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0172] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0173] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0174] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0175] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0176] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0177] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0178] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0179] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0180] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0181] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0182] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0183] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0184] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0185] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0186] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0187] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0188] 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.

[0189] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0190] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0191] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0192] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0193] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0194] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0195] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0196] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0197] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0198] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0199] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0200] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0201] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0202] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0203] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0204] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0205] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0206] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0207] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0208] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0209] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0210] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0211] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0212] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0213] 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.

[0214] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0215] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0216] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0217] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0218] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0219] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0220] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0221] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0222] [Explanation of symbols]

[0223] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects alarm information; a filtering unit that filters the alarm information collected by the collection unit; an analysis unit that analyzes the alarm information filtered by the filtering unit and groups related alarms; a summarizing unit that summarizes the alarm information grouped by the analyzing unit; an identification unit that identifies a main cause based on the information summarized by the summarization unit; a providing unit that provides a maintenance person with the main cause identified by the identifying unit; Equipped with A system characterized by:

2. The collecting unit Collect alarm information from network devices, servers, and storage devices 2. The system of claim 1.

3. The filtering unit Only important alarm information is passed to the analysis section 2. The system of claim 1.

4. The analysis unit Alarms are grouped based on their relevance based on the alarm content, occurrence time, and occurrence location.

2. The system of claim 1.

5. The summary section Summarize grouped alarm information 2. The system of claim 1.

6. The identification unit Identify the primary cause based on the summarized information 2. The system of claim 1.

7. The providing unit Provide identified root causes to maintenance personnel 2. The system of claim 1.

8. The collecting unit The method estimates the user's emotions and adjusts the timing of collecting alarm information based on the estimated user emotions.

2. The system of claim 1.

9. The collecting unit Monitor the operating status of each device in real time and immediately collect alarm information when an abnormality occurs.

2. The system of claim 1.

10. The collecting unit When collecting alarm information, the past failure history of each device is referenced to determine the priority of collection.

2. The system of claim 1.

Images