Intelligent analysis method for operation and maintenance of enterprise information system
By using intelligent analysis methods to collect and analyze real-time data from enterprise information systems, automatically adjust equipment and generate operation and maintenance logs, the problems of low operation and maintenance efficiency and poor accuracy in existing technologies are solved, and efficient and intelligent operation and maintenance is achieved.
Patent Information
- Application Number
- CN202410925433.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-11
- Publication Date
- 2024-11-12
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In existing technologies, the operation and maintenance strategies of enterprise information systems are fixed and rely on manual judgment, resulting in low operation and maintenance efficiency, poor accuracy, and difficulty in responding to dynamic changes in enterprise business.
By employing intelligent analysis methods, the system continuously collects standardized real-time data from core network devices, performs algorithmic calculations and modeling analysis, automatically adjusts devices or generates operation and maintenance logs, and achieves intelligent early warning and rapid processing.
It enables proactive prediction and rapid post-event processing, reduces the workload of operations and maintenance personnel, improves operational efficiency and the completeness of log generation, and overcomes the subjectivity of manually generating operations and maintenance logs.
Smart Images

Figure CN118941266A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of operation and maintenance analysis, and in particular to an intelligent analysis method for operation and maintenance of an enterprise information system. Background Art
[0002] Intelligent operation and maintenance refers to an operation and maintenance method that automatically learns and summarizes rules from massive operation and maintenance data and makes decisions through artificial intelligence algorithms such as machine learning. The concept of intelligent operation and maintenance was first proposed by . It integrates artificial intelligence technology into the operation and maintenance system. Based on big data and machine learning, it collects massive data (including logs, business data, system data, etc.) from various data sources for real-time or offline analysis. Through proactive, humanized and dynamic visualization, it enhances the capabilities of traditional operation and maintenance. Although intelligent operation and maintenance is the latest technology in the field of operation and maintenance, the artificial intelligence industry to which it is applied is also a sunrise industry at present, and the technical maturity still needs to be improved, but it does not hinder the powerful productivity generated by intelligent operation and maintenance; After searching, the invention with patent number "CN115439166A" provides "a method and device for enterprise classification, belonging to the field of information technology services, the method comprising: obtaining first relevant data and second relevant data of the target enterprise, the first relevant data comprising indicator data of the comprehensive enterprise operation and maintenance service capabilities of the target enterprise, and the second relevant data comprising indicator data of the enterprise development market potential of the target enterprise; based on the first relevant data and the second relevant data, determining the coordinates of the target enterprise in the two-dimensional four-quadrant classification model", but there are the following problems: the operation and maintenance strategy adopted is relatively rigid. When an abnormal problem occurs and causes the status of the core network equipment to be unavailable, the network operation and maintenance personnel are required to manually judge the equipment and then restart the equipment manually. This method is relatively cumbersome and the original operation and maintenance system based on personnel monitoring and manual processing has uneven personal levels of operation and maintenance personnel and lacks reasonable standard specifications for the intensity of monitoring of different systems. It is difficult to cope with the dynamic changes in the actual business of the enterprise in terms of the accuracy and efficiency of judging the system operation status. Summary of the invention
[0003] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides an enterprise information system operation and maintenance intelligent analysis method to solve the problems raised in the above-mentioned background technology.
[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a method for intelligent analysis of enterprise information system operation and maintenance, including an enterprise information system operation and maintenance intelligent analysis subject, including the following steps: S1. The collection equipment continuously collects real-time standardized data from core network devices; S2, the analysis module performs algorithm calculations on the collected data and conducts modeling and comparative analysis on the linear fluctuations of the data range; S3. The standardized data analysis results of the equipment show abnormalities, and the abnormality type is analyzed / the standardized data analysis results of the equipment are normal; S4, the control device adjusts the control core network device according to the abnormal signal transmitted by the analysis module; S5. Collect the appearance image of the core device to which the abnormal signal that cannot be adjusted belongs / self-adjust the abnormal data through the core network device to restore the normal data; S6. Perform fault analysis on the collected appearance images / send the analysis results to the administrator; S7. Record the operation and maintenance logs, and log the exceptions and operation and maintenance processes; In a preferred embodiment, the S1 specifically includes: determining data collection rules and collection scope, initially collecting comprehensive and intuitive basic data of the operation of each core network device system, classifying the data according to the characteristics of the data, so that the collection equipment continuously collects real-time data of the core network equipment, the selection of collected data should be analyzed in combination with the records in the actual operation and maintenance work, the variables selected at the information level should be able to reflect the service performance of the system as a whole, the variables selected at the data level should have trend and self-volatility, and then the initial data collected is judged, and a trend standardized data module is established, the S2 includes: the analysis module performs algorithm calculation on the collected data, the analysis engine includes a data mining module and a data operation module, the analysis engine analyzes the association, classification, and similar aggregation of the data, and generates C PU utilization, future available time of disk space, and packet loss rate are analyzed. By defining the mining model, the data mining task is divided into model definition, model training, and model use. The work done by the mining module always revolves around the mining model. The data mining module uses type definition primitives, model training primitives, and model use primitives. Based on qualitative analysis, the relationship measurement theory is used to combine the correlation table, correlation graph, and calculation of correlation coefficients with judgment coefficients. Formulas are used in a large number of abstract data sources to collect and analyze the basic data of intuitive information within the same logical association range. For data modules with unclear overall fluctuation trends, the data modules are sorted and processed in combination with parallel algorithms. Its association rule is a discovery model based on large transaction data sets. Let I = {i1, i2, ..., id} is a set of all items in the transaction data set, where an item refers to the attribute corresponding to each column of the transaction. A binary representation method is used, and a set consisting of 0 or more items is called an item set. An important property of an item set is its support count, that is, the number of transactions containing a specific item set. It is converted into a linear data set. The parallel algorithm is used to convert the data module into a linear fluctuation modeling and perform comparative analysis. The S3 includes: establishing a processable fault association set, dividing the N linear data established in the early stage into each fault association set through a fault association set establishment method; for each fault association set, setting a trigger threshold of the fault for each element therein, and setting a monitoring priority and processing strategy when a fault occurs, and performing comparative analysis on the linear fluctuation modeling of the CPU utilization, the future available time of the disk space, and the packet loss rate data conversion. The abnormal fault association situation in the standardized data analysis results of the equipment triggers the subsequent processing strategy, and the abnormal type is analyzed. When the standardized data analysis results of the equipment are normal, the above process is repeated at the beginning to ensure normal system utilization; In a preferred embodiment, the S4 and S5 specifically include: after the abnormal fault association is triggered, according to the processing strategy obtained by analysis, the core network device to which the CPU utilization, the future available time of the disk space, and the packet loss rate are abnormal is shut down or restarted, or the control core network device to which it belongs is self-adjusted; when the abnormal data of the core network device to which the abnormality belongs is restored to normal after self-adjustment or shutdown or restart, all the above steps are repeated to ensure the normal system utilization rate; when the abnormal signal does not return to normal data after self-adjustment, the control device uses an automatic tracking camera to collect appearance images of the core network device to which the abnormal data connected to the network end belongs; the S6 and S7 specifically include: from the collected abnormal The predicted operation and maintenance fault type corresponding to the faulty network equipment is analyzed from the appearance image of the core network equipment to which the data belongs, and the data is sent to the administrator. The operation and maintenance process of the operation and maintenance personnel repairing the faulty substation is video captured, and the operation and maintenance process parameters are extracted from the captured operation and maintenance process video. After the operation and maintenance is completed, the appearance image of the faulty network equipment is captured through the automatic tracking camera to obtain the appearance image of the faulty substation after the operation and maintenance is completed. The operation and maintenance log is automatically generated, and the analysis server in the operation and maintenance log generation control component automatically generates an operation and maintenance log for the abnormal data corresponding to this operation and maintenance, the abnormal data self-adjustment process, the operation and maintenance personnel, the name of the faulty network equipment, the predicted operation and maintenance fault type, the operation and maintenance process parameters, and the appearance image of the faulty network equipment before and after the operation and maintenance.
[0005] In a preferred embodiment, the enterprise information system operation and maintenance intelligent analysis body is internally installed with a collection device and a control module, a data transmission connection terminal 1 is installed at one end of the right side of the collection device near the top, and a data transmission connection terminal 1 is installed at one end of the right side of the collection device near the bottom, an analysis engine is installed at the rear end of the control module, a network device connection terminal is installed at the rear end of the analysis engine, and a transmission cable is installed on the side of the network device connection terminal, a data mining connection terminal is provided on the right side of the analysis engine, a data calculation connection terminal is installed at the rear end of the data mining connection terminal, an algorithm connection terminal is provided below the data calculation connection terminal, a log storage terminal is installed on the side of the algorithm connection terminal, and a model comparison library is installed on the side of the log storage terminal, the adjustment component includes a front drive end, a guide rod 2 and a guide groove, the output end of the front drive end is installed with a guide rod 2, the top side of the guide rod 2 is installed with an adjustment seat, the end of the guide rod 2 is installed with a limit platform, and the side of the limit platform is installed with a guide groove.
[0006] Technical effects and advantages of the present invention: 1. The present invention sets data collection rules and data collection scope, so that the collection equipment can continuously collect real-time data of core network equipment, establish a trend-based standardized data module, analyze the generated CPU utilization, future available time of disk space, and packet loss rate, integrate and model them, and establish a processable fault association set. The N linear data established in the early stage are divided into each fault association set through the fault association set establishment method; for each fault association set, a trigger threshold of the fault is set for each element therein, and a monitoring priority and processing strategy are set when a fault occurs, forming an operation and maintenance service analysis platform of an intelligent operation and maintenance service system based on intelligent collection, intelligent early warning, and intelligent analysis, so as to achieve an intelligent and efficient operation and maintenance effect that can realize pre-prediction and post-processing quickly.
[0007] 2. After being triggered by abnormal fault association, according to the processing strategy obtained through analysis, the core network equipment to which the abnormal CPU utilization, future available disk space time, and packet loss rate belong is shut down or restarted, or the control core network equipment to which it belongs is self-adjusted. When the abnormal data returns to normal after the core network equipment to which the abnormality belongs is self-adjusted or shut down or restarted, all the above steps are repeated to ensure normal system utilization and reduce the labor intensity of operation and maintenance personnel. At the same time, when the abnormal signal does not return to normal data after self-adjustment, the control device uses an automatic tracking camera to collect appearance images of the core network equipment to which the abnormal data belongs that is connected to the network end, so as to facilitate normal operation and maintenance of the enterprise information system.
[0008] 3. Through the operation and maintenance log generation terminal in the enterprise information system, the identity information of the operation and maintenance personnel is identified, and then the name of the operation and maintenance personnel is obtained, and the appearance of the operation and maintenance process of the operation and maintenance personnel repairing the faulty network equipment is collected, so as to extract the operation and maintenance process parameters from the collected operation and maintenance process video, and at the same time, the appearance image of the faulty network equipment before and after the operation and maintenance is obtained, so as to automatically generate an operation and maintenance log with the abnormal data corresponding to the operation and maintenance, the abnormal data self-adjustment process, the operation and maintenance personnel, the name of the faulty network equipment, the predicted operation and maintenance fault type, the operation and maintenance process parameters and the appearance image of the faulty network equipment before and after the operation and maintenance, so as to realize the intelligent analysis and generation of daily operation and maintenance logs of enterprise information system equipment, improve the completeness of operation and maintenance log generation, and overcome the disadvantages of forgetting or missing generation due to the large subjectivity of manual generation of operation and maintenance logs. BRIEF DESCRIPTION OF THE DRAWINGS
[0009] Figure 1 It is a schematic diagram of the intelligent analysis process of enterprise information system operation and maintenance of the present invention; Figure 2 It is a front view structural diagram of the enterprise information system operation and maintenance intelligent analysis module of the present invention; Figure 3It is a rear view structural diagram of the enterprise information system operation and maintenance intelligent analysis module of the present invention; Figure 4 This is a schematic diagram of the modular distribution of operation and maintenance data of the present invention.
[0010] The accompanying drawings are marked as follows: 1. Enterprise information system operation and maintenance intelligent analysis subject; 11. Collection equipment; 12. Analysis engine; 13. Network equipment connection terminal; 14. Transmission cable; 15. Data mining connection terminal; 16. Data transmission connection terminal one; 17. Data transmission connection terminal one; 18. Identification framework; 19. Control module; 110. Data mining connection terminal; 111. Data calculation connection terminal; 112. Algorithm connection terminal; 113. Log storage terminal; 114. Model comparison library. DETAILED DESCRIPTION
[0011] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0012] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by those skilled in the art to which the present invention belongs.
[0013] according to Figure 1-4 As shown, a method for intelligent analysis of enterprise information system operation and maintenance includes an enterprise information system operation and maintenance intelligent analysis subject 1, and includes the following steps: S1. The collection equipment continuously collects real-time standardized data from core network devices; S2, the analysis module performs algorithm calculations on the collected data and conducts modeling and comparative analysis on the linear fluctuations of the data range; S3. The standardized data analysis results of the equipment show abnormalities, and the abnormality type is analyzed / the standardized data analysis results of the equipment are normal; S4, the control device adjusts the control core network device according to the abnormal signal transmitted by the analysis module; S5. Collect the appearance image of the core device to which the abnormal signal that cannot be adjusted belongs / self-adjust the abnormal data through the core network device to restore the normal data; S6. Perform fault analysis on the collected appearance images / send the analysis results to the administrator; S7. Record the operation and maintenance logs, and log the exceptions and operation and maintenance processes; Specifically, S1 includes: determining the data collection rules and scope, initially collecting comprehensive and intuitive basic data on the operation of each core network device system, classifying the data according to the characteristics of the data, so that the collection equipment can continuously collect real-time data from the core network equipment, and the selection of collected data should be analyzed in combination with the records in the actual operation and maintenance work. The variables selected at the information level must be able to reflect the service performance of the system as a whole, and the variables selected at the data level must have trends and their own volatility. Then, the initial data collected is judged and a trend-based standardized data module is established.
[0014] Specifically, S2 includes: the analysis module performs algorithm calculation on the collected data, the analysis engine includes a data mining module and a data operation module, the analysis engine analyzes the association, classification, and similar clustering of the data, and analyzes the generated CPU utilization, the future available time of the disk space, and the packet loss rate. By defining the mining model, the data mining task is divided into model definition, model training, and model use. The work done by the mining module always revolves around the mining model. The data mining module uses type definition primitives, model training primitives, and model use primitives. Using the relationship measurement theory, on the basis of qualitative analysis, through correlation tables, correlation graphs, and calculation of correlation coefficients and judgment coefficients, formulas are used in a large number of abstract data sources to collect and analyze the basic data of intuitive information within the same logical association range. For data modules with no obvious overall fluctuation trend, the data modules are sorted and combined with parallel algorithms to process the data. Its association rule is a discovery mode based on large transaction data sets. Let I = {i1, i2, ..., id} is the set of all items in the transaction data set, where an item refers to the attribute corresponding to each column of the transaction. A binary representation method is used, and a set consisting of 0 or more items is called an itemset. An important property of an itemset is its support count, that is, the number of transactions containing a specific itemset. It is converted into a linear data set, and the parallel algorithm is used to convert the data module into a linear fluctuation model for comparative analysis.
[0015] Specifically, S3 includes: establishing a processable fault association set, dividing the N linear data established in the early stage into each fault association set through the fault association set establishment method; for each fault association set, setting the trigger threshold of the fault for each element therein, and setting the monitoring priority and processing strategy when the fault occurs, and performing comparative analysis on the linear fluctuation modeling of CPU utilization, future available time of disk space, and packet loss rate data conversion. When abnormal fault association occurs in the standardized data analysis results of the equipment, subsequent processing strategies are triggered, and the abnormal type is analyzed. When the standardized data analysis results of the equipment are normal, return to the starting stage and repeat the above process to ensure normal system utilization.
[0016] See also Figure 1-4As shown, as another implementation of the present analysis method, a collection device 11 and a control module 19 are installed inside the main body 1 of intelligent analysis of enterprise information system operation and maintenance. A data transmission connection terminal 16 is installed at one end of the right side of the collection device 11 near the top, and a data transmission connection terminal 17 is installed at one end of the right side of the collection device 11 near the bottom. An analysis engine 12 is installed at the rear end of the control module 19, and a network device connection terminal 13 is installed at the rear end of the analysis engine 12. A transmission cable 14 is installed on the side of the network device connection terminal 13. A data mining connection terminal 15 is provided on the right side of the analysis engine 12. A data operation connection terminal 111 is installed at the rear end of the mining connection terminal 15, an algorithm connection terminal 112 is provided below the data operation connection terminal 111, a log storage terminal 113 is installed on the side of the algorithm connection terminal 112, a model comparison library 114 is installed on the side of the log storage terminal 113, the adjustment component 6 includes a front drive end 65, a guide rod 62 and a guide groove 63, the output end of the front drive end 65 is installed with a guide rod 62, the top side of the guide rod 62 is installed with an adjustment seat 61, the end of the guide rod 62 is installed with a limit platform 64, and the side of the limit platform 64 is installed with a guide groove 63, S4 and S5 specifically include: after the abnormal fault association is triggered, according to the processing strategy obtained through analysis, the core network device to which the abnormal CPU utilization, future available disk space time, and packet loss rate belong is shut down or restarted, or the control core network device to which it belongs is self-adjusted; when the abnormal data returns to normal after the core network device to which the abnormality belongs is self-adjusted or shut down or restarted, all the above steps are repeated to ensure normal system utilization; when the abnormal signal does not return to normal data after self-adjustment, the control device uses an automatic tracking camera to collect appearance images of the core network device to which the abnormal data connected to the network end belongs.
[0017] Specifically, S6 and S7 specifically include: analyzing the predicted operation and maintenance fault type corresponding to the faulty network equipment from the appearance image of the core network equipment to which the collected abnormal data belongs, sending the data to the administrator, capturing video of the operation and maintenance process of the operation and maintenance personnel repairing the faulty substation equipment, and extracting operation and maintenance process parameters from the collected operation and maintenance process video, and after the operation and maintenance is completed, capturing appearance images of the faulty network equipment through an automatic tracking camera to obtain the appearance image of the faulty substation equipment after the operation and maintenance is completed, and automatically generating an operation and maintenance log, and automatically generating an operation and maintenance log through the analysis server in the operation and maintenance log generation control component using the abnormal data corresponding to the operation and maintenance, the abnormal data self-adjustment process, the operation and maintenance personnel, the name of the faulty network equipment, the predicted operation and maintenance fault type, the operation and maintenance process parameters, and the appearance image of the faulty network equipment before and after the operation and maintenance.
[0018] This analysis method provides a scientific, efficient and intelligent analysis theory for the operation of large-scale enterprise information systems: Through the set data collection rules and data collection scope, the collection equipment can continuously collect real-time data of core network equipment, establish a trend-based standardized data module, analyze the generated CPU utilization, future available time of disk space, and packet loss rate, integrate modeling and comparison, and establish a processable fault association set. The N linear data established in the early stage are divided into various fault association sets through the fault association set establishment method; for each fault association set, the trigger threshold of the fault is set for each element in it, and the monitoring priority and processing strategy when the fault occurs are set, forming an operation and maintenance service analysis platform based on intelligent collection, intelligent early warning, and intelligent analysis. The intelligent operation and maintenance service system can achieve intelligent and efficient operation and maintenance effects that can realize pre-prediction and post-processing quickly. After being triggered by abnormal fault association, according to the processing strategy obtained through analysis, the core network equipment with abnormal CPU utilization, future available time of disk space, and packet loss rate is shut down or restarted, or the control core network equipment is self-adjusted. When the abnormal data returns to normal after the core network equipment with abnormality is self-adjusted or shut down or restarted, all the above steps are repeated to ensure normal system utilization and reduce the labor intensity of operation and maintenance personnel. At the same time, when the abnormal signal does not return to normal data after self-adjustment, the control device uses an automatic tracking camera to collect appearance images of the core network equipment to which the abnormal data belongs connected to the network end, so as to facilitate normal operation and maintenance of the enterprise information system. Then, through the operation and maintenance log generation terminal in the enterprise information system, the identity information of the operation and maintenance personnel is identified, and the name of the operation and maintenance personnel is obtained, and the appearance of the operation and maintenance process of the operation and maintenance personnel repairing the faulty network equipment is collected, so as to extract the operation and maintenance process parameters from the collected operation and maintenance process video, and at the same time, the appearance image of the faulty network equipment before and after the operation and maintenance is obtained, so as to automatically generate an operation and maintenance log with the abnormal data corresponding to the operation and maintenance, the abnormal data self-adjustment process, the operation and maintenance personnel, the name of the faulty network equipment, the predicted operation and maintenance fault type, the operation and maintenance process parameters and the appearance image of the faulty network equipment before and after the operation and maintenance, thereby realizing the intelligent analysis and generation of daily operation and maintenance logs of enterprise information system equipment, improving the completeness of operation and maintenance log generation, and overcoming the disadvantages of manual generation of operation and maintenance logs due to large subjectivity and forgetfulness or omission.
[0019] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.
Claims
1. A method for intelligent analysis of enterprise information system operation and maintenance, comprising an enterprise information system operation and maintenance intelligent analysis subject (1), characterized in that: The steps include: S1. The collection equipment continuously collects real-time standardized data from core network devices; S2, the analysis module performs algorithm calculations on the collected data and conducts modeling and comparative analysis on the linear fluctuations of the data range; S3. The standardized data analysis results of the equipment show abnormalities, and the abnormality type is analyzed / the standardized data analysis results of the equipment are normal; S4, the control device adjusts the control core network device according to the abnormal signal transmitted by the analysis module; S5. Collect the appearance image of the core device to which the abnormal signal that cannot be adjusted belongs / self-adjust the abnormal data through the core network device to restore the normal data; S6. Perform fault analysis on the collected appearance images / send the analysis results to the administrator; S7. Record the operation and maintenance logs, and log the exceptions and operation and maintenance processes.
2. According to claim 1, the enterprise information system operation and maintenance intelligent analysis method is characterized in that S1 specifically includes: determining data collection rules and collection scope, initially collecting comprehensive and intuitive basic data of the operation of each core network device system, classifying the data according to the characteristics of the data, so that the collection equipment can continuously collect real-time data of the core network equipment, and the selection of collected data should be analyzed in combination with the records in the actual operation and maintenance work. The variables selected at the information level must be able to reflect the service performance of the system as a whole, and the variables selected at the data level must have trend and self-volatility, and then make judgments on the initial data collected, and establish a trend-based standardized data module; The S2 includes: the analysis module performs algorithmic calculations on the collected data, the analysis engine includes a data mining module and a data operation module, the analysis engine analyzes the association, classification, and similar aggregation of the data, and analyzes the generated CPU utilization, the future available time of the disk space, and the packet loss rate. By defining the mining model, the data mining task is divided into model definition, model training, and model use. The work done by the mining module always revolves around the mining model. The data mining module uses type definition primitives, model training primitives, and model use primitives, and uses relational measurement theory. On the basis of qualitative analysis, it combines correlation tables, correlation graphs, and calculation of correlation coefficients with judgment coefficients, and uses formulas in a large number of abstract data sources. Collect and analyze the correlation data within the same logical association range of the basic data of intuitive information. For data modules with unclear overall fluctuation trends, organize the data modules and process the data in combination with parallel algorithms. Its association rule is a discovery model based on large transaction data sets. Let I = {i1, i2, ..., id} be the set of all items in the transaction data set, where an item refers to the attribute corresponding to each column of the transaction. A binary representation method is used. A set consisting of 0 or more items is called an item set. An important property of an item set is its support count, that is, the number of transactions containing a specific item set. Convert it into a linear data set. The parallel algorithm is used to convert the data module into a linear fluctuation model for comparative analysis. The S3 includes: establishing a processable fault association set, dividing the N linear data established in the early stage into each fault association set through the fault association set establishment method; for each fault association set, setting the trigger threshold of the fault for each element therein, and setting the monitoring priority and processing strategy when the fault occurs, and performing a linear fluctuation modeling and comparative analysis on the CPU utilization, the future available time of the disk space, and the packet loss rate data conversion. When the standardized data analysis results of the equipment show abnormal fault association, the subsequent processing strategy is triggered, and the abnormal type is analyzed. When the standardized data analysis results of the equipment are normal, the above process is returned to the starting stage and repeated to ensure the normal system utilization rate.
3. The enterprise information system operation and maintenance intelligent analysis method according to claim 1, characterized in that: The S4 and S5 specifically include: after the abnormal fault association is triggered, according to the processing strategy obtained by analysis, the core network device to which the CPU utilization, the future available time of the disk space, and the packet loss rate are abnormal is shut down or restarted, or the control core network device to which it belongs is self-adjusted; when the abnormal data of the abnormal core network device is restored to normal after self-adjustment or shutdown or restart, all the above steps are repeated to ensure the normal utilization rate of the system; when the abnormal signal does not restore to normal data after self-adjustment, the control device uses an automatic tracking camera to collect appearance images of the core network device to which the abnormal data connected to the network end belongs; The S6 and S7 specifically include: analyzing the predicted operation and maintenance fault type corresponding to the faulty network device from the appearance image of the core network device to which the collected abnormal data belongs, sending the data to the administrator, collecting video of the operation and maintenance process of the operation and maintenance personnel repairing the faulty substation, and extracting operation and maintenance process parameters from the collected operation and maintenance process video, and after the operation and maintenance, collecting appearance images of the faulty network device through an automatic tracking camera to obtain the appearance image of the faulty substation after the operation and maintenance is completed, and automatically generating an operation and maintenance log, and automatically generating an operation and maintenance log by using the analysis server in the operation and maintenance log generation control component to generate an operation and maintenance log based on the abnormal data corresponding to this operation and maintenance, the abnormal data self-adjustment process, the operation and maintenance personnel, the name of the faulty network device, the predicted operation and maintenance fault type, the operation and maintenance process parameters and the appearance image of the faulty network device before and after the operation and maintenance.
4. The method for intelligent analysis of enterprise information system operation and maintenance according to claim 1, characterized in that: The enterprise information system operation and maintenance intelligent analysis body (1) is internally installed with a collection device (11) and a control module (19); a data transmission connection terminal (16) is installed at one end of the right side of the collection device (11) close to the top; a data transmission connection terminal (17) is installed at one end of the right side of the collection device (11) close to the bottom; an analysis engine (12) is installed at the rear end of the control module (19); a network device connection terminal (13) is installed at the rear end of the analysis engine (12); a transmission cable (14) is installed on the side of the network device connection terminal (13); a data mining connection terminal (15) is provided on the right side of the analysis engine (12); and a data mining connection terminal (15) is installed at the rear end of the data mining connection terminal (15). A data operation connection terminal (111) is provided, an algorithm connection terminal (112) is provided below the data operation connection terminal (111), a log storage terminal (113) is provided on the side of the algorithm connection terminal (112), and a model comparison library (114) is provided on the side of the log storage terminal (113); the adjustment component (6) comprises a front drive terminal (65), a second guide rod (62) and a guide groove (63), the output end of the front drive terminal (65) is provided with a second guide rod (62), the top side of the second guide rod (62) is provided with an adjustment seat (61), the end of the second guide rod (62) is provided with a limit platform (64), and the side of the limit platform (64) is provided with a guide groove (63).
Citation Information
Cited By
Information system comprehensive operation and maintenance management platform method and system based on big data
CN120563101A
