NetElement Health Analysis Methods, Devices, Equipment, Storage Media, and Program Products
By monitoring alarm events of service network elements, analyzing alarm information based on monitoring time intervals, obtaining key information sets, and performing network element health analysis, the problem of inaccurate network element health monitoring is solved, and dynamic monitoring and real-time feedback of network element health status are realized.
Patent Information
- Application Number
- CN202410559264.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-05-07
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2044-05-07
AI Technical Summary
Existing technologies cannot effectively monitor the health of network elements dynamically, resulting in a lack of real-time monitoring data and inaccurate network element health monitoring.
By monitoring alarm events of service network elements, alarm information is analyzed based on the monitoring time interval within the monitoring period of the alarm events to obtain a key information set. Then, network element health analysis is performed on the service network elements based on the key information set, and time attributes are introduced to achieve dynamic monitoring.
It enables dynamic monitoring of network element health status, ensures the real-time nature of health analysis data, avoids inaccuracies caused by static analysis, and can reflect the trend of network element health status changes at any time and over continuous time periods.
Smart Images

Figure CN118827452B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of data service technology, and in particular to a method, apparatus, device, storage medium, and program product for network element health analysis. Background Technology
[0002] As operators' businesses develop and their user base expands, the demand for availability of various data services becomes increasingly prominent. A failure in any network element involved in a service could render the entire service unavailable. Therefore, it is necessary to expand the scope of operation and maintenance (O&M) supervision of various network elements and strengthen its oversight. However, current methods cannot effectively monitor network element health dynamically, resulting in a lack of real-time monitoring data and inaccurate O&M health monitoring due to static data analysis. Summary of the Invention
[0003] The main objective of this invention is to provide a method, apparatus, device, storage medium, and program product for network element health analysis, aiming to solve the technical problems of existing technologies being unable to effectively monitor network element health dynamically, resulting in a lack of real-time monitoring data and inaccurate network element health monitoring.
[0004] To achieve the above objectives, the present invention provides a network element health analysis method, the method comprising the following steps:
[0005] Monitor alarm events of network elements;
[0006] Based on the monitoring time interval within the monitoring period of the alarm event, the alarm information of the alarm event is analyzed to obtain a set of key information;
[0007] Based on the key information set, network element health analysis is performed on the service network element to obtain the network element health status of the service network element at each monitoring time interval within the monitoring period.
[0008] Optionally, the step of performing network element health analysis on the service network element based on the key information set to obtain the network element health level of the service network element at each monitoring time interval within the monitoring period includes:
[0009] The weight parameters of the key indicators of the business network element are generated based on the correlation analysis results of the key information set and key indicators. The key indicators include alarm category and alarm level.
[0010] The negative score result for each monitoring time interval is determined based on the key information set;
[0011] Based on the weight parameters and the negative score results, network element health analysis is performed on the service network element to obtain the network element health of the service network element at each monitoring time interval within the monitoring period.
[0012] Optionally, the step of generating weight parameters for the key indicators of the business network element based on the correlation analysis results of the key information set and key indicators includes:
[0013] The number of alarms corresponding to each alarm category within the monitoring period and the total number of alarms within the monitoring period are determined based on the key information set.
[0014] Determine the ratio between the number of alarms corresponding to each alarm category and the total number of alarms;
[0015] Weight parameters for each alarm category are generated based on the correlation analysis results of the quantity ratio and the key indicators.
[0016] Optionally, the step of generating weight parameters for the key indicators of the business network element based on the correlation analysis results of the key information set and key indicators includes:
[0017] The number of alarms corresponding to each alarm level within the monitoring period and the total number of alarms within the monitoring period are determined based on the key information set.
[0018] Determine the ratio between the number of alarms corresponding to each alarm level and the total number of alarms;
[0019] Weight parameters for each alarm level are generated based on the correlation analysis results of the quantity ratio and the key indicators.
[0020] Optionally, determining the negative score result for each monitoring time interval based on the key information set includes:
[0021] Based on the key information set, determine the number of first alarms corresponding to each alarm level under each monitoring time interval, and the number of second alarms corresponding to each alarm category under each monitoring time interval;
[0022] The negative score result for each monitoring time interval is determined based on the number of the first alarm and the number of the second alarm under each monitoring time interval.
[0023] Optionally, the step of analyzing alarm information based on monitoring time intervals within the monitoring period of the alarm event to obtain a key information set includes:
[0024] Based on the monitoring time interval within the monitoring period of the alarm event, the alarm information is analyzed and alarm information is obtained from the monitoring data of the alarm event;
[0025] Feature extraction is performed on the alarm information to obtain alarm feature data;
[0026] Based on the monitoring time interval, key information statistics are performed on the alarm feature data to obtain a key information set.
[0027] Furthermore, to achieve the above objectives, the present invention also proposes a network element health analysis device, the network element health analysis device comprising:
[0028] The alarm monitoring module is used to monitor alarm events of service network elements;
[0029] The information analysis module is used to analyze the alarm information of the alarm event based on the monitoring time interval within the monitoring period of the alarm event, and obtain a key information set;
[0030] The health analysis module is used to perform network element health analysis on the service network element based on the key information set, and to obtain the network element health of the service network element at each monitoring time interval within the monitoring period.
[0031] In addition, to achieve the above objectives, this application also proposes a network element health analysis device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the network element health analysis method as described above.
[0032] In addition, to achieve the above objectives, this application also proposes a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, it implements the steps of the network element health analysis method described above.
[0033] In addition, to achieve the above objectives, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the network element health analysis method described above.
[0034] This invention monitors alarm events of service network elements, analyzes alarm information based on monitoring time intervals within the monitoring period of the alarm events to obtain a key information set, and performs network element health analysis on the service network elements based on the key information set to obtain the network element health level of the service network elements at each monitoring time interval within the monitoring period. Because this application analyzes alarm information based on monitoring time intervals within the monitoring period of alarm events to obtain a key information set, and then performs network element health analysis on the service network elements based on the key information set, it accurately monitors the overall health status of the service network elements. By introducing a time attribute into the network element health analysis, it achieves monitoring of the health status change trend of service network elements over continuous time periods and at any time, realizing dynamic monitoring of network element health status, ensuring the real-time nature of health analysis data, and effectively avoiding the problem of inaccurate network element health analysis caused by static analysis data. Attached Figure Description
[0035] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.
[0036] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0037] Figure 1 This is a schematic diagram of the structure of the network element health analysis device in the hardware operating environment involved in the embodiments of the present invention;
[0038] Figure 2 This is a flowchart illustrating the first embodiment of the network element health analysis method of the present invention;
[0039] Figure 3 This is a flowchart illustrating the second embodiment of the network element health analysis method of the present invention;
[0040] Figure 4 This is a flowchart illustrating the third embodiment of the network element health analysis method of the present invention;
[0041] Figure 5 This is a structural block diagram of the first embodiment of the network element health analysis device of the present invention.
[0042] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation
[0043] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.
[0044] Reference Figure 1 , Figure 1 This is a schematic diagram of the network element health analysis device structure in the hardware operating environment involved in the embodiments of the present invention.
[0045] like Figure 1 As shown, the network element health analysis device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include a display screen and an input unit such as a keyboard; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk storage device. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.
[0046] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the network element health analysis device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.
[0047] like Figure 1 As shown, the memory 1005, which is a computer-readable storage medium, may include an operating system, a network communication module, a user interface module, and a network element health analysis program.
[0048] exist Figure 1 In the network element health analysis device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the network element health analysis device of the present invention can be set in the network element health analysis device, and the network element health analysis device calls the network element health analysis program stored in the memory 1005 through the processor 1001 and executes the network element health analysis method provided in the embodiment of the present invention.
[0049] This invention provides a method for network element health analysis, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the network element health analysis method of the present invention.
[0050] In this embodiment, the network element health analysis method includes the following steps:
[0051] Step S10: Monitor alarm events of service network elements.
[0052] It should be understood that the executing entity of this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an electronic device capable of performing the above functions. The following description uses a network element health analysis device (hereinafter referred to as the analysis device) as an example to illustrate this embodiment and the subsequent embodiments.
[0053] It should be noted that the service network element can be a service network element whose health needs to be monitored. For example, the service network element can be a media plane network element based on the ringback tone service. This embodiment takes the media plane network element of the above-mentioned ringback tone service as an example for explanation.
[0054] It is understood that this embodiment can monitor alarm events of service network elements based on the monitoring period, obtain alarm data of alarm events, and then preprocess the alarm data for subsequent alarm information analysis.
[0055] It should be noted that the analysis equipment aggregates and organizes the alarm data as a data preprocessing stage for in-depth analysis of network element health status.
[0056] It should be noted that the above-mentioned preprocessing of alarm data can be a process of standardizing network element indicator data. The media plane network element indicator information of the above-mentioned ringback tone service includes the number / average of audio channels, the number / average of video channels, CAPS, resource concurrency / maximum concurrency, single-unit media resource utilization rate, total number of playbacks / total number of failures, single-unit MRF playback success rate, etc. It also includes the performance indicator set of the cluster / host involved in the media plane network element.
[0057] Step S20: Analyze the alarm information of the alarm event based on the monitoring time interval within the monitoring period of the alarm event to obtain a key information set.
[0058] It should be noted that the monitoring period can be the time period for monitoring alarm events. The aforementioned monitoring time interval can be the statistical time interval for key monitoring information in the key information set. For example, the monitoring time interval can be a second as the data update cycle to statistically obtain the key information set.
[0059] It should be understood that the aforementioned monitoring time interval can be the time interval for generating network element health status subsequently. That is, network element health status is generated based on the monitoring time interval, thereby obtaining continuous health status data within the monitoring period, i.e., dynamic health status trend, so as to realize dynamic monitoring of network element health status.
[0060] Step S30: Perform network element health analysis on the service network element based on the key information set to obtain the network element health of the service network element for each monitoring time interval within the monitoring period.
[0061] It should be noted that the network element health score can be the network element health score of the business network element, which reflects the health level of the business network element.
[0062] It should be noted that this embodiment can analyze network element health by combining monitoring time intervals and key information sets, calculate the network element health level corresponding to each moment and / or monitoring time interval within the monitoring period (e.g., the monitoring time interval is per second), obtain the network element health level score per second, that is, obtain dynamic network element health data, and thus combine continuous network element health levels to realize dynamic health trend analysis of business network elements.
[0063] It is understood that this embodiment introduces a time element into the health monitoring of service network elements, thereby introducing time characteristics. Combining these time characteristics with the network element health analysis results in dynamic health analysis data, which can reflect the trend changes in the health status of the monitored object at any time and over continuous time periods.
[0064] This embodiment monitors alarm events of service network elements, analyzes alarm information based on monitoring time intervals within the monitoring period of the alarm events to obtain a key information set, and performs network element health analysis on the service network elements based on the key information set to obtain the network element health level of the service network elements at each monitoring time interval within the monitoring period. Because this embodiment analyzes alarm information based on monitoring time intervals within the monitoring period of alarm events to obtain a key information set, and then performs network element health analysis on the service network elements based on the key information set, it accurately monitors the overall health status of the service network elements. By introducing a time attribute into the network element health analysis, it achieves monitoring of the health status change trend of service network elements over continuous time periods and at any time, realizing dynamic monitoring of network element health status, ensuring the real-time nature of health analysis data, and effectively avoiding the problem of inaccurate network element health analysis caused by static analysis data.
[0065] refer to Figure 3 , Figure 3 This is a flowchart illustrating the second embodiment of the network element health analysis method of the present invention.
[0066] Based on the first embodiment described above, in this embodiment, step S30 further includes:
[0067] Step S31: Generate the weight parameters of the key indicators of the business network element based on the correlation analysis results of the key information set and key indicators.
[0068] It should be noted that key indicators can be data that reflects the health status of network elements. For example, key indicators may include, but are not limited to, alarm generation time, alarm type, alarm level, and alarm frequency, all of which can reflect the health status of network elements to varying degrees. For instance, if a monitored business network element suddenly experiences a severe alarm at several consecutive times, it indicates that the health status of that network element may be declining significantly, requiring attention from operations and maintenance personnel.
[0069] In some embodiments, in addition to alarm level, the same key indicators include alarm category, specific alarm event, alarm time, and frequency of occurrence. The priority of alarm events in the network element health status feedback varies for different network elements.
[0070] It is understandable that the correlation analysis results of the above key indicators can be the results of the analysis device's prior analysis of the correlation between changes in key indicators of alarm information.
[0071] It should be noted that the correlation analysis results may include: the fewer times an alarm category appears, the more important the alarm of that category is; the fewer times an alarm level appears, the more important the alarm of that level is; the more different alarm events appear within the same category and level, the more problems there are; in a continuous time series, an increase in the number of alarm events within the same category and level indicates an increase in problems, and the corresponding health status may be affected.
[0072] Furthermore, in order to accurately calculate the weight parameters of the alarm category, step S31 above may include:
[0073] Step S3111: Determine the number of alarms corresponding to each alarm category within the monitoring period, and the total number of alarms within the monitoring period, based on the key information set;
[0074] Step S3112: Determine the ratio between the number of alarms corresponding to each alarm category and the total number of alarms;
[0075] Step S3113: Generate weight parameters for each alarm category based on the correlation analysis results of the quantity ratio and the key indicators.
[0076] Understandably, the weight parameters for alarm categories are calculated using the following formula, where freqLabel... iThis represents the proportion of alarms corresponding to the i-th alarm category out of the total number of alarms. The smaller the proportion, the more important the alarm, so it should be assigned a higher weight.
[0077] The total number of alarm categories is LABLEN, alarmIDNumByLable i F(freqLabel) represents the number of alarms corresponding to the i-th alarm category. i ; α, β) represent the cumulative distribution function of the B distribution. To prevent the result from being 0, a parameter σ is added, with σ taking the value (0, 1). arg_label i This represents the weight parameter for the i-th alarm category, where the sum of the weights of the LEVELN alarm levels is 1.
[0078]
[0079]
[0080] Furthermore, in order to accurately calculate the weight parameters of the alarm level, step S31 above may include:
[0081] Step S3121: Determine the number of alarms corresponding to each alarm level within the monitoring period, and the total number of alarms within the monitoring period, based on the key information set;
[0082] Step S3122: Determine the ratio between the number of alarms corresponding to each alarm level and the total number of alarms;
[0083] Step S3123: Generate weight parameters for each alarm level based on the correlation analysis results of the quantity ratio and the key indicators.
[0084] Understandably, the weighting parameter for alarm levels is calculated using the following formula, where freqLevel i This represents the proportion of alarms corresponding to the i-th alarm level to the total number of alarms. The smaller the proportion, the more important the alarm, so it should be assigned a higher weight.
[0085] The total number of alarm levels is LEVELN, alarmIDNumByLabel i F(freqLabel) represents the number of alarms corresponding to the i-th alarm level. i ; α, β) denote the cumulative distribution function of the B distribution, arg_label i This represents the weight parameter for the i-th alarm level, where the sum of the weights of the LEVELN alarm levels is 1.
[0086]
[0087]
[0088] Step S32: Determine the negative score result for each monitoring time interval based on the key information set.
[0089] It should be noted that negative scores can be indicators that reflect the performance of service network elements. Negative scores reflect poor performance of service network elements within a specific evaluation period. For example, negative scores are related to the number of alarms that occur at each time point within the monitoring period.
[0090] Furthermore, in order to accurately calculate the negative score result, step S32 above may include:
[0091] Step S321: Based on the key information set, determine the number of first alarms corresponding to each alarm level under each monitoring time interval, and the number of second alarms corresponding to each alarm category under each monitoring time interval;
[0092] Step S322: Determine the negative score result for each monitoring time interval based on the number of first alarms and the number of second alarms under each monitoring time interval.
[0093] It is understood that this embodiment can calculate the negative score result based on the NS negative score generation algorithm. The NS negative score generation algorithm refers to the following formula, where NS is the final negative score result, and NegativeScore is the negative score actually calculated.
[0094] NegativeScore t Represents the negative score result at time t, alarmIDNumByLL t This represents the number of alarms of the same alarm category and alarm level at time t. Specifically, if the number of alarms at time t-1 is alarmIDNumByLL... t-1 If it is None, then the current time-to-date negative score is NegativeScore. t The current number of alarms is alarmIDNumByLL t .
[0095]
[0096]
[0097] Step S33: Perform network element health analysis on the service network element according to the weight parameters and the negative score results to obtain the network element health of the service network element in each monitoring time interval within the monitoring period.
[0098] It is understood that this embodiment calculates the network element health based on the weight parameters and negative score results. Referring to the following formula, the network element health score for each moment or monitoring time interval within the monitoring period is finally obtained, such as obtaining the network element health score per second, which facilitates timely and effective operation and maintenance operations in the future.
[0099]
[0100] Where HS (Health Score) is the health score, arg_label i arg_level represents the weight parameter for the i-th alarm category. j NS represents the weight parameter for the j-th alarm level. ij This represents the negative scoring parameter for the i-th alarm category and j-th alarm level. Where NS ij The calculation is performed using a negative score generation algorithm.
[0101] This embodiment generates weight parameters for key indicators of the business network element based on the correlation analysis results of the key information set and key indicators. It determines the negative score results for each monitoring time interval based on the key information set, and performs network element health analysis on the business network element according to the weight parameters and the negative score results to obtain the network element health level of the business network element for each monitoring time interval within the monitoring period. Because this embodiment dynamically generates the weight parameters for network element business indicators, it is more flexible than using fixed values from historical periods or manual experience values, and can provide real-time feedback on the operating status of the monitored object. The weight parameters can be adjusted dynamically based on the operating data of the monitored object's indicators, enabling more accurate monitoring of the overall health status of the network element. Introducing time characteristics into the negative score calculation allows for feedback on the trend changes of the monitored object's health status at any given time or over consecutive time periods.
[0102] refer to Figure 4 , Figure 4 This is a flowchart illustrating the third embodiment of the network element health analysis method of the present invention.
[0103] Based on the above embodiments, in this embodiment, step S10, the method further includes:
[0104] Step S101: Analyze the alarm information of the alarm event based on the monitoring time interval within the monitoring period of the alarm event, and obtain alarm information from the monitoring data of the alarm event.
[0105] Understandably, the analysis equipment monitors alarm events of service network elements, obtains alarm data, and then extracts key alarm information from the alarm data that can reflect the health status of the network elements to varying degrees.
[0106] For example, if a monitored network element suddenly experiences a severe alarm at certain consecutive moments, it indicates that the health status of that network element may be declining significantly, requiring attention from operations and maintenance personnel.
[0107] It should be noted that key alarm information, including alarm occurrence time, alarm type, alarm level, and alarm frequency, can all reflect the health status of network elements to varying degrees. Similarly, in addition to alarm level, other key indicators include alarm type, specific alarm event, alarm time, and frequency. The priority of alarm events in the health status feedback varies for different network elements.
[0108] Step S102: Extract features from the alarm information to obtain alarm feature data.
[0109] It is understood that this embodiment analyzes alarm information and extracts alarm features from alarm data. The alarm features may include at least one of the following: alarm generation time, alarm event ID, alarm category, alarm level, and alarm generation count (the number of times a certain alarm event occurs at a certain time). Based on the extracted alarm features, an alarm feature data set is generated.
[0110] Step S103: Perform key information statistics on the alarm feature data based on the monitoring time interval to obtain a key information set.
[0111] It should be understood that the analysis equipment performs key information statistics based on alarm feature data groups, with the monitoring time interval as the data update cycle, to obtain a key information set. The time interval of this key information set is the time interval for subsequently generating network element health scores.
[0112] It should be noted that the above-mentioned key information statistics can include key information such as alarm category, alarm level, and number of alarms. The calculation process for the number of alarms is: the number of alarm event IDs that occur under the same alarm category and alarm level.
[0113] This embodiment analyzes alarm information based on the monitoring time interval within the monitoring period of the alarm event, obtains alarm information from the monitoring data of the alarm event, extracts features from the alarm information to obtain alarm feature data, and performs key information statistics on the alarm feature data based on the monitoring time interval to obtain a key information set, thereby realizing dynamic statistics of monitoring data and effectively improving the efficiency and accuracy of network element health analysis.
[0114] Furthermore, embodiments of the present invention also propose a computer-readable storage medium storing a network element health analysis program, wherein when the network element health analysis program is executed by a processor, it implements the steps of the network element health analysis method described above.
[0115] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.
[0116] The aforementioned computer-readable storage medium may be included in the network element health analysis device; or it may exist independently and not be assembled into the network element health analysis device.
[0117] Furthermore, this invention also proposes a computer program product, including a network element health analysis program, which, when executed by a processor, implements the steps of the network element health analysis method as described above.
[0118] The specific implementation of the computer program product of the present invention is basically the same as the embodiments of the above-described network element health analysis method, and will not be repeated here.
[0119] Reference Figure 5 , Figure 5 This is a structural block diagram of the first embodiment of the network element health analysis device of the present invention.
[0120] like Figure 5 As shown, the network element health analysis device proposed in this embodiment of the invention includes:
[0121] The alarm monitoring module 10 is used to monitor alarm events of service network elements;
[0122] The information analysis module 20 is used to analyze the alarm information of the alarm event based on the monitoring time interval within the monitoring period of the alarm event, and obtain a key information set;
[0123] The health analysis module 30 is used to perform network element health analysis on the service network element based on the key information set, and obtain the network element health of the service network element at each monitoring time interval within the monitoring period.
[0124] Furthermore, the health analysis module 30 is also used to generate weight parameters of key indicators of the service network element based on the correlation analysis results of the key information set and key indicators, wherein the key indicators include alarm category and alarm level; determine the negative score result of each monitoring time interval based on the key information set; and perform network element health analysis on the service network element based on the weight parameters and the negative score result to obtain the network element health of the service network element in each monitoring time interval within the monitoring period.
[0125] Furthermore, the network element health analysis device also includes:
[0126] The dynamic weight calculation module 40 is used to determine the number of alarms corresponding to each alarm category within the monitoring period and the total number of alarms within the monitoring period based on the key information set; determine the ratio between the number of alarms corresponding to each alarm category and the total number of alarms; and generate weight parameters for each alarm category based on the ratio and the correlation analysis results of the key indicators.
[0127] Furthermore, the dynamic weight calculation module 40 is also used to determine the number of alarms corresponding to each alarm level within the monitoring period and the total number of alarms within the monitoring period based on the key information set; determine the ratio between the number of alarms corresponding to each alarm level and the total number of alarms; and generate weight parameters for each alarm level based on the ratio and the correlation analysis results of the key indicators.
[0128] Furthermore, the network element health analysis device also includes:
[0129] The negative score calculation module 50 is used to determine the number of first alarms corresponding to each alarm level under each monitoring time interval and the number of second alarms corresponding to each alarm category under each monitoring time interval based on the key information set; and to determine the negative score result of each monitoring time interval based on the number of first alarms and the number of second alarms under each monitoring time interval.
[0130] Furthermore, the information analysis module 20 is also used to perform alarm information analysis on the alarm event based on the monitoring time interval within the monitoring period of the alarm event, obtain alarm information from the monitoring data of the alarm event; extract features from the alarm information to obtain alarm feature data; and perform key information statistics on the alarm feature data based on the monitoring time interval to obtain a key information set.
[0131] This embodiment monitors alarm events of service network elements, analyzes alarm information based on monitoring time intervals within the monitoring period of the alarm events to obtain a key information set, and performs network element health analysis on the service network elements based on the key information set to obtain the network element health level of the service network elements at each monitoring time interval within the monitoring period. Because this embodiment analyzes alarm information based on monitoring time intervals within the monitoring period of alarm events to obtain a key information set, and then performs network element health analysis on the service network elements based on the key information set, it accurately monitors the overall health status of the service network elements. By introducing a time attribute into the network element health analysis, it achieves monitoring of the health status change trend of service network elements over continuous time periods and at any time, realizing dynamic monitoring of network element health status, ensuring the real-time nature of health analysis data, and effectively avoiding the problem of inaccurate network element health analysis caused by static analysis data.
[0132] The network element health analysis device provided in this application, employing the network element health analysis method in the above embodiments, can solve the technical problems of network element health analysis. Compared with the prior art, the beneficial effects of the network element health analysis device provided in this application are the same as those of the network element health analysis method provided in the above embodiments, and other technical features in the network element health analysis device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.
[0133] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.
[0134] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0135] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of the present invention.
[0136] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.
Claims
1. A method of network element health analysis, the method comprising: The network element health analysis method includes: Monitor alarm events of network elements; Based on the monitoring time interval within the monitoring period of the alarm event, alarm information analysis is performed on the alarm event to obtain a key information set; the monitoring time interval is the statistical time interval of the key monitoring information in the key information set; Based on the key information set, determine the number of alarms corresponding to each alarm category within the monitoring period, and the total number of alarms within the monitoring period; determine the ratio between the number of alarms corresponding to each alarm category and the total number of alarms; generate weight parameters for each alarm category based on the correlation analysis results of the ratio and key indicators; or, based on the key information set, determine the number of alarms corresponding to each alarm level within the monitoring period, and the total number of alarms within the monitoring period; determine the ratio between the number of alarms corresponding to each alarm level and the total number of alarms; generate weight parameters for each alarm level based on the correlation analysis results of the ratio and key indicators; the key indicators include alarm category and alarm level; Based on the key information set, determine the number of first alarms corresponding to each alarm level under each monitoring time interval, and the number of second alarms corresponding to each alarm category under each monitoring time interval; determine the negative score result for each monitoring time interval based on the number of first alarms and the number of second alarms under each monitoring time interval; Based on the weight parameters and the negative score results, network element health analysis is performed on the service network element to obtain the network element health of the service network element at each monitoring time interval within the monitoring period.
2. The network element health analysis method as described in claim 1, characterized in that, The alarm information analysis is performed on the alarm event based on the monitoring time interval within the monitoring period of the alarm event to obtain a key information set, including: Based on the monitoring time interval within the monitoring period of the alarm event, the alarm information is analyzed and alarm information is obtained from the monitoring data of the alarm event; Feature extraction is performed on the alarm information to obtain alarm feature data; Based on the monitoring time interval, key information statistics are performed on the alarm feature data to obtain a key information set.
3. A network element health analysis device, characterized in that, The network element health analysis device includes: The alarm monitoring module is used to monitor alarm events of service network elements; The information analysis module is used to analyze the alarm information of the alarm event based on the monitoring time interval within the monitoring period of the alarm event, and obtain a key information set; the monitoring time interval is the statistical time interval of the key monitoring information in the key information set; A dynamic weight calculation module is used to determine the number of alarms corresponding to each alarm category within the monitoring period, and the total number of alarms within the monitoring period, based on the key information set; determine the ratio between the number of alarms corresponding to each alarm category and the total number of alarms; and generate weight parameters for each alarm category based on the ratio and the correlation analysis results of key indicators; or, based on the key information set, determine the number of alarms corresponding to each alarm level within the monitoring period, and the total number of alarms within the monitoring period; determine the ratio between the number of alarms corresponding to each alarm level and the total number of alarms; and generate weight parameters for each alarm level based on the ratio and the correlation analysis results of key indicators; wherein the key indicators include alarm category and alarm level; The health analysis module is used to determine, based on the key information set, the number of first alarms corresponding to each alarm level and the number of second alarms corresponding to each alarm category under each monitoring time interval; determine the negative score result for each monitoring time interval based on the number of first alarms and the number of second alarms under each monitoring time interval; and perform network element health analysis on the service network element based on the weight parameters and the negative score result to obtain the network element health of the service network element in each monitoring time interval within the monitoring period.
4. A network element health analysis device, characterized in that, The network element health analysis device includes: a memory, a processor, and a network element health analysis program stored in the memory and executable on the processor, wherein the network element health analysis program is configured to implement the network element health analysis method as described in any one of claims 1 to 2.
5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a network element health analysis program, which, when executed by a processor, implements the network element health analysis method as described in any one of claims 1 to 2.
6. A computer program product, characterized in that, The computer program product includes a network element health analysis program, which, when executed by a processor, implements the steps of the network element health analysis method as described in any one of claims 1 to 2.
Citation Information
Patent Citations
Monitoring device and method based on health degree analysis
CN102447570A
Alarm data analysis based device health degree estimation method and apparatus
CN107451402A
Command risk assessment method and related equipment
CN114548617A
Memory fault prediction method and device, storage medium and electronic device
CN115686909A
