CN111934895B - Intelligent early warning method and device for network management system and computing equipment - Google Patents
Intelligent early warning method and device for network management system and computing equipment Download PDFInfo
- Publication number
- CN111934895B CN111934895B CN201910395539.4A CN201910395539A CN111934895B CN 111934895 B CN111934895 B CN 111934895B CN 201910395539 A CN201910395539 A CN 201910395539A CN 111934895 B CN111934895 B CN 111934895B
- Authority
- CN
- China
- Prior art keywords
- early warning
- index
- index data
- data
- warning information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/04—Processing captured monitoring data, e.g. for logfile generation
- H04L43/045—Processing captured monitoring data, e.g. for logfile generation for graphical visualisation of monitoring data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0805—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability
- H04L43/0817—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters by checking availability by checking functioning
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Mining & Analysis (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The embodiment of the invention relates to the technical field of a business support network operation management system, and discloses an intelligent early warning method, an intelligent early warning device and computing equipment of a network management system, wherein the method comprises the following steps: acquiring index data of at least one index; performing early warning analysis on the index data of the at least one index to obtain early warning information; and outputting the early warning information to a monitoring center for early warning and monitoring. The early warning information is obtained by performing early warning analysis such as preprocessing, abnormal motion judgment, artificial intelligence early warning and the like on the index data. Through the mode, the embodiment of the invention can visually see the early warning information, can show the life cycle process of early warning information processing and the trend of the abnormal change index of the latest period of the fault risk time point, and further can provide an effective loss stopping decision.
Description
Technical Field
The embodiment of the invention relates to the technical field of business support network operation management systems, in particular to an intelligent early warning method, an intelligent early warning device and computing equipment of a network management system.
Background
At present, a Business Operation Management Center (BOMC) is based on an alarm, and alarm Management is after the fact, that is, a fault and an alarm have occurred, which have a factual impact on a Business, but the impact on the Business scope, the user group, the impact degree, etc. cannot be quantitatively and accurately judged, and an effective loss-stopping decision cannot be made in advance.
In the process of implementing the embodiment of the present invention, the inventors found that: because the current service support network operation management system is based on alarm, and when the system sends out alarm, the current service is influenced, and maintenance personnel can process according to the alarm content, but because the scheme can not carry out early warning analysis according to operation index data in advance, an effective loss stopping decision can not be provided.
Disclosure of Invention
In view of the foregoing problems, embodiments of the present invention provide an intelligent early warning method, apparatus, and computing device for a network management system, which overcome the foregoing problems or at least partially solve the foregoing problems.
According to an aspect of an embodiment of the present invention, an intelligent early warning method for a network management system is provided, where the method includes: acquiring index data of at least one index; performing early warning analysis on the index data of the at least one index to obtain early warning information; and outputting the early warning information to a monitoring center for early warning and monitoring.
In an optional manner, the index includes a user index, a service index, an application index, and a platform index.
In an optional manner, the performing the early warning analysis on the index data of the at least one index to obtain the early warning information includes: acquiring index data of at least one index for judging faults and early warning; preprocessing and caching the index data of the at least one index; carrying out transaction judgment on the index data of the at least one index according to a preset transaction algorithm to output the index data of the transaction; and carrying out artificial intelligence early warning judgment on the abnormal index data by using a preset artificial intelligence model to obtain early warning information.
In an optional manner, the acquiring indicator data of at least one indicator used for determining a fault and performing early warning further includes: and adjusting the index data of the at least one index for judging the fault and early warning according to the running condition of the network management system.
In an optional manner, the obtaining of the index data of the at least one index used for determining the fault and performing the early warning includes: selecting an index model and a classification mode of at least one index; and acquiring index data of the at least one index of at least one network level according to the index model and the classification mode.
In an optional manner, the pre-processing and caching the metric data of the at least one metric includes: aligning the index data of the at least one index by time; cleaning unnecessary index data in the index data of the at least one index; and caching the cleaned index data of the at least one index.
In an alternative mode, the cleaning of the index data of the at least one index from the unnecessary index data includes: filtering the index data of the at least one index within a preset filtering time period range; and filtering the index data of the at least one index, wherein the index data is not within a preset effective caching time.
In an optional manner, the performing a transaction determination on the index data of the at least one index according to a preset transaction algorithm to output the index data of the transaction includes: verifying the index data of the at least one index with the reference range of the index; if the verification fails, the index data is output to a transaction analysis report; if the check is passed, carrying out transaction judgment according to a transaction algorithm corresponding to the index; and outputting the index data of the transaction to the transaction analysis report.
In an optional manner, the applying a preset artificial intelligence model to perform artificial intelligence early warning judgment on the abnormal index data to obtain early warning information further includes: calculating an early warning index according to the abnormal index data; determining whether early warning is needed or not according to the early warning index; and if the early warning is required, generating the early warning information.
In an optional manner, the calculating an early warning index according to the abnormal index data further includes: calculating a difference movement deviation rate according to the difference movement index data and a preset threshold value corresponding to the index; calculating the early warning probability of the index in the same year; and calculating an early warning index according to the abnormal change deviation rate, the early warning probability of the same year in the last year and a reference early warning probability.
In an alternative way, the early warning index r satisfies the following relation: r = k σ + w (epsilon-epsilon i), wherein k and w are adjustment coefficients, σ is the difference deviation rate, epsilon is the early warning probability of the same period of the last year, and epsilon i is the reference early warning probability.
In an optional manner, before outputting the warning information to a monitoring center for warning and monitoring, the method further includes: carrying out continuity judgment on the early warning information; and caching a plurality of pieces of early warning information with continuity.
In an optional manner, the outputting the warning information to a monitoring center for warning and monitoring further includes: setting output parameters of the early warning information; and outputting the early warning information to a monitoring center according to the output parameter setting.
In an alternative form, the output parameters include: at least one of a real-time refresh time, a color setting, a grade setting, or a monitoring setting.
According to another aspect of the embodiments of the present invention, there is provided an intelligent warning apparatus for a network management system, the apparatus including: the data acquisition module is used for acquiring index data of at least one index; the early warning analysis module is used for carrying out early warning analysis on the index data of the at least one index to obtain early warning information; and the early warning output module is used for outputting the early warning information to a monitoring center for early warning and monitoring.
According to another aspect of embodiments of the present invention, there is provided a computing device including: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete mutual communication through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the steps of the intelligent early warning method of the network management system.
According to another aspect of the embodiments of the present invention, there is provided a computer storage medium, in which at least one executable instruction is stored, and the executable instruction causes the processor to execute the steps of the intelligent early warning method of the network management system.
The embodiment of the invention collects the index data of at least one index; performing early warning analysis on the index data of the at least one index to obtain early warning information; and outputting the early warning information to a monitoring center for early warning and monitoring. The early warning information is obtained through early warning analysis such as preprocessing, abnormal motion judgment, artificial intelligence early warning and the like on the index data, the early warning information can be visually seen, the life cycle process of early warning information processing and the trend of the abnormal motion index of a latest period of time of a fault risk time point can be displayed, and then an effective loss stopping decision can be provided.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and in order that the technical solutions of the embodiments of the present invention can be clearly understood, the embodiments of the present invention can be implemented according to the content of the description, and the above and other objects, features, and advantages of the embodiments of the present invention can be more clearly understood, the detailed description of the present invention is provided below.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a schematic flowchart illustrating an intelligent warning method for a network management system according to an embodiment of the present invention;
fig. 2 shows an early warning analysis flowchart of an intelligent early warning method of a network management system according to an embodiment of the present invention;
fig. 3 is a schematic diagram of a radar model of an intelligent early warning method of a network management system according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram illustrating an intelligent early warning apparatus of a network management system according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a computing device provided by an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the invention are shown in the drawings, it should be understood that the invention can be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Fig. 1 shows a flowchart of an intelligent early warning method of a network management system according to an embodiment of the present invention. As shown in fig. 1, the intelligent early warning method of the network management system includes:
step S11: index data for at least one index is collected.
Some key preparation people indexes monitored in daily operation are extracted, the index sources are five layers, and the index sources are a user layer, a business layer, a service layer, an application layer and a platform layer from top to bottom in sequence. According to the source, the indexes comprise user indexes, business indexes, service indexes, application indexes and platform indexes. In step S11, the five types of index data are subjected to data acquisition and output to a distributed publish-subscribe message system (Kafka) stream processing platform.
Step S12: and carrying out early warning analysis on the index data of the at least one index to obtain early warning information.
Specifically, index data is extracted from the Kafka stream processing platform through the data center platform, and early warning information is obtained through early warning analysis such as abnormal judgment, artificial Intelligence (AI) early warning, continuity judgment and the like of the early warning data stream through an early warning data stream processing engine of the data center platform.
In the embodiment of the present invention, as shown in fig. 2, step S12 further includes:
step S121: index data of at least one index used for judging faults and early warning is obtained.
The index source comprises a user layer, a business layer, a service layer, an application layer and a platform layer from top to bottom in sequence. The indexes of each layer are very many, but the key indexes for judging faults and early warning are not many, and the index models and classification modes of the following table are selected according to experience to provide input early warning index data.
In step S121, an index model and a classification manner of at least one index are selected; and acquiring index data of the at least one index of at least one network level according to the index model and the classification mode. The empirically selected index model and classification method are shown in table 1 below.
TABLE 1 selection of index models and classification schemes
As can be seen from table 1, in the key indexes for determining a fault and performing early warning, the user indexes include a login amount, an active user number, and a hot spot consultation, the service indexes include a total province service amount, a channel service amount, a business hall service amount, a service detection success rate, and a service detection time, the service indexes include an interface calling system success rate and an interface calling system duration, the application indexes include a log error reporting amount, and the platform indexes include a host ping, a database health degree, and a system health degree.
In step S121, the method further includes: and adjusting the index data of the at least one index for judging the fault and early warning according to the running condition of the network management system, and further acquiring the adjusted index data.
Step S122: and preprocessing and caching the index data of the at least one index.
Specifically, the index data of the at least one index is aligned in time; cleaning unnecessary index data in the index data of the at least one index; and caching the cleaned index data of the at least one index. The index data is obtained from a user layer, a business layer, a service layer, an application layer and a platform layer, and the sequence is disordered and inconsistent, so that the index data is aligned according to time, and the further processing is convenient for the follow-up.
In the embodiment of the invention, a filtering time and a buffering effective time are set, and original index data are filtered according to the filtering time and the buffering effective time. Specifically, the index data in a preset filtering time period range in the index data of at least one index is filtered; and filtering the index data of the at least one index except for a preset effective caching time. For example: filter time is set to 23: 00-8:01, filtering out the index data of the time period of 23. And 8, reserving: 00-8: and (5) the data cached in the time period of 01 is cleaned, and the data exceeding the effective time of the cache is cleaned.
Step S123: and carrying out transaction judgment on the index data of the at least one index according to a preset transaction algorithm to output the index data of the transaction.
In the embodiment of the invention, an index transaction algorithm list is preset, and different types of indexes are assembled with different transaction analysis algorithms. In step S123, checking the index data of the at least one index with the reference range of the index; if the verification is not passed, the index data is output to a transaction analysis report; if the check is passed, carrying out transaction judgment according to a transaction algorithm corresponding to the index; and outputting the index data of the transaction to the transaction analysis report.
The transaction analysis algorithm corresponding to different types of indexes is as follows:
1. the business indexes comprise a transaction analysis algorithm of provincial business volume, channel business volume, business hall business volume, business detection success rate and business detection time consumption: and regarding the index data of the provincial business volume, the channel business volume and the business hall business volume, taking the absolute value of the difference value of the index data and the previous index data of the same type, if the difference value is less than 0.75 time of the expected value of the business change, determining that the index is a normal index, and otherwise, determining that the index is a transaction index. For example, if the current index data of the business hall traffic index is X1, the index data of the business hall traffic index at the previous moment is X0, and the expected change amount of the business hall traffic is M, if (X1-X0)/M is greater than or equal to 0.75, the current business hall traffic index is considered to be abnormal. For the service detection success rate, if the index data of the three continuous service detection success rates is less than 0.2, the index data is determined to be transaction index data. Regarding the time consumed by the traffic detection, if the time consumed by the traffic detection exceeds a preset time threshold, for example, 15 seconds, the time consumed by the traffic detection may be regarded as transaction indicator data.
2. User indexes comprise login amount, active user number and a transaction analysis algorithm of hot spot consultation: and for the login amount, different provinces have different login amount expectations, statistics is carried out according to the city as a unit, and if the login amount displayed by the current index data is smaller than the lowest login amount requirement of the index data on the city, the current index data is determined to be the abnormal action index data. For the number of active users, if the number of active users decreases too fast, i.e. decreases more than the expected number of users, the active user index transaction is determined. For hot spot consultation, if the consultation index of a certain type of hot spot problem is increased suddenly in a short time and exceeds the expected growth rate, the hot spot consultation index is determined to be abnormal.
3. The service index comprises a transaction analysis algorithm of the success rate of the interface calling system and the duration of the interface calling system: and for the success rate of the interface calling system, if the success rate of the interface calling system is less than 90%, determining that the success rate of the interface calling system varies. And regarding the interface calling system time, if the interface calling system time is more than 20 seconds, determining that the interface calling system time index changes.
4. And (3) applying indexes including a transaction analysis algorithm of log error reporting quantity: and if the log error reporting amount is larger than the expected error reporting value, determining that the log error reporting amount index changes.
5. Platform indexes comprise a host Internet Groper (ping) time, database health degree and system health degree transaction analysis algorithm: for the host ping time, the index is an index for evaluating the network connectivity of the system host, and if the host ping time is greater than a threshold value, the current host ping index varies. For the database health degree and the system health degree, the health degree is a scoring strategy of the system for judging whether the database and the whole system are healthy, and if the score is smaller than an expected value, the health degree index is judged to be abnormal.
Step S124: and carrying out artificial intelligence early warning judgment on the abnormal index data by using a preset artificial intelligence model to obtain early warning information.
In the embodiment of the invention, after the abnormal operation indexes are screened out, the abnormal operation indexes need to be further and accurately judged to judge whether the current indexes need to be early warned or not. In step S124, calculating an early warning index according to the abnormal index data; determining whether early warning is needed or not according to the early warning index; and if the early warning is needed, generating the early warning information. Specifically, when an early warning index is calculated according to the index data of the abnormal motion, the abnormal motion deviation rate is calculated according to the index data of the abnormal motion and a preset threshold corresponding to the index; calculating the early warning probability of the index in the same period of the last year; and calculating an early warning index according to the transaction deviation rate, the early warning probability of the same year in the last year and a reference early warning probability.
For each type of transaction index, there is a preset threshold Xi, for example, the preset threshold of the total province traffic, the social channel traffic, and the business hall traffic is 0.75, the preset threshold of the business detection success rate is 0.2, and so on. Assuming that the numerical value of the current abnormal motion index is X, calculating the abnormal motion deviation ratio sigma, and satisfying the following relational expression:
the early warning index r satisfies the following relational expression:
r＝k*σ+w*(ε-εi)
wherein, σ is the variation deviation ratio, epsilon is the early warning probability of the same period of the last year, epsilon i is the reference early warning probability, and k and w are adjustment coefficients. Different types of indexes have corresponding adjusting coefficient values.
And when r is greater than r0, judging that the current abnormal index needs early warning, otherwise, judging that the current abnormal index does not need early warning, wherein r0 is a preset index base number, and different types of indexes have different index base numbers.
Step S13: and outputting the early warning information to a monitoring center for early warning and monitoring.
Specifically, the early warning time, the risk level, the early warning state, the early warning content, the associated fault list, whether the information is checked or not and the like are set for the early warning information. And displaying all early warnings of the current day by default, and refreshing the list periodically. Therefore, the life cycle process of early warning information processing and the trend of the abnormal index of the latest period of the fault risk time point can be displayed, and effective loss stopping decision can be provided by performing early warning analysis on the index data in advance.
In the embodiment of the present invention, before step S13, continuity judgment is performed on the early warning information; and caching a plurality of pieces of early warning information with continuity. And if the time interval of the two pieces of early warning information is smaller than the preset time interval T, the two pieces of early warning information are continuous. Specifically, after AI early warning judgment, early warning information is sent when the current index needs early warning. After receiving the early warning information, caching the early warning information, starting countdown, wherein the moment is the starting time, if a piece of early warning information is received within a preset time interval T, caching the early warning information, counting down again, until the next piece of early warning information is not received after the countdown time T, wherein the moment is the ending time, outputting all the early warning information cached within the starting time period and the ending time period, and finally emptying the cache.
In step S13, setting output parameters for the warning information; and outputting the early warning information to a monitoring center according to the output parameter setting. The output parameters include: at least one of a real-time refresh time, a color setting, an upgrade setting, or a monitor setting.
In the embodiment of the present invention, each output parameter is specifically set as follows:
and setting the real-time refreshing time of the early warning information list, wherein the default time is 15 seconds.
Early warning level color setting: and expressing the risk level of the fault early warning event by color, wherein the lowest level is 5-level gray early warning, and the highest level is 1-level red early warning.
Early warning upgrade setting: the early warning is not cancelled, and can be upgraded step by step until the highest level. The upgrade time can be configured, and the time for early warning upgrade at different levels can be configured. If the early warning starts from 5-level gray color, the blue color is upgraded within 30 minutes, the yellow color is upgraded within 30 minutes, the orange color is upgraded within 60 minutes, and the red color is upgraded within 120 minutes.
In the monitoring center, staff can visually see the early warning level of each early warning information, and all early warnings in the day are displayed in a list mode, so that the monitoring center is very visual.
In the embodiment of the invention, the early warning information can be monitored, all early warnings can be displayed, the list can be refreshed periodically, and the early warning information can be selected to be displayed and processed correspondingly. And displaying all early warnings of the current day by default, and refreshing the list periodically. After the early warning information is selected, the life cycle process of early warning information processing and the trend of the abnormal index of the latest period of time of the fault risk time point can be displayed.
Displaying all the early warnings on the day in a list mode, wherein the displayed early warning information comprises: early warning time, risk level, early warning state, early warning content, associated fault list, whether the fault list is checked and the like.
For the same continuous early warning event, only one piece of early warning information is displayed on the foreground, but the content of the early warning needs to be updated.
After the early warning is cancelled: the early warning of the fault risk can be cancelled, the risk state is cancelled, and a recovery judgment basis is provided, such as the original abnormal index trend is recovered to be normal.
The early warning information processing can be carried out, and the operations of notification, confirmation, knowledge checking processing and the like can be carried out. Specifically, the early warning is announced by WeChat/short message/multimedia message; confirming whether the early warning is correct or not, and confirming the associated fault, wherein the single function is repeated with the associated fault; the processing experience is viewed in association with the knowledge base.
And (4) displaying the process of the early warning life cycle, and taking the process from fault management or informing the process of taking the process.
The matrix diagram of the abnormal indexes related to the early warning model can be displayed, and the indexes with abnormal actions in the early warning period need to be displayed.
The replay trend graph of the abnormal index related to the early warning model can be displayed, and the time is the index from 10 periods before the early warning starting time point to the current time point. If the number of points behind the early warning time point is not enough, the number of points is supplemented forwards. And displaying the related indexes of the first early warning by default.
Finally, the health condition of the service system 5-layer architecture can be represented by a radar model, and fig. 3 is a normalized radar model schematic diagram. And (4) selecting n key indexes (consistent with the early warning input indexes) with the largest influence on the state of each layer, and grouping the n key indexes into health indexes of each layer through a model algorithm. The five-layer architecture comprises: user layer, service layer, application layer and platform layer.
The layer normalization model algorithm is as follows:
if there is no warning in each layer, the score of 60 is evaluated, and the health score of a certain layer is =60+40 (1-number of examples of abnormal index/total number of examples of input index).
If the warning is given, the score 0 is evaluated, and the state of health of a certain layer is =100 (1-number of abnormal index instances/total number of input index instances).
The embodiment of the invention collects the index data of at least one index; performing early warning analysis on the index data of the at least one index to obtain early warning information; and outputting the early warning information to a monitoring center for early warning and monitoring. The early warning information is obtained through early warning analysis such as preprocessing, abnormal motion judgment, artificial intelligence early warning and the like on the index data, the early warning information can be visually seen, the life cycle process of early warning information processing and the trend of the abnormal motion index of a latest period of time of a fault risk time point can be displayed, and then an effective loss stopping decision can be provided.
Fig. 4 shows a schematic structural diagram of an intelligent early warning apparatus of a network management system according to an embodiment of the present invention. As shown in fig. 4, the intelligent early warning apparatus of the network management system includes: a data acquisition module 401, an early warning analysis module 402 and an early warning output module 403. Wherein:
the data acquisition module 401 is configured to acquire index data of at least one index; the early warning analysis module 402 is configured to perform early warning analysis on the index data of the at least one index to obtain early warning information; the early warning output module 403 is configured to output the early warning information to a monitoring center for early warning and monitoring.
In an optional manner, the index includes a user index, a service index, an application index, and a platform index.
In an alternative approach, the early warning analysis module 402 is configured to: acquiring index data of at least one index for judging faults and early warning; preprocessing and caching the index data of the at least one index; carrying out transaction judgment on the index data of the at least one index according to a preset transaction algorithm to output the index data of the transaction; and carrying out artificial intelligence early warning judgment on the abnormal index data by using a preset artificial intelligence model to obtain early warning information.
In an optional manner, the early warning analysis module 402 is further configured to: and adjusting the index data of the at least one index for judging the fault and early warning according to the running condition of the network management system.
In an optional manner, the early warning analysis module 402 is further configured to: selecting an index model and a classification mode of at least one index; and acquiring index data of the at least one index of at least one network level according to the index model and the classification mode.
In an optional manner, the early warning analysis module 402 is further configured to: aligning the index data of the at least one index by time; cleaning the index data of the at least one index from the unneeded index data; and caching the cleaned index data of the at least one index.
In an optional manner, the early warning analysis module 402 is further configured to: filtering the index data of the at least one index within a preset filtering time period range; and filtering the index data of the at least one index, wherein the index data is not within a preset effective caching time.
In an optional manner, the early warning analysis module 402 is further configured to: verifying the index data of the at least one index with the reference range of the index; if the verification is not passed, the index data is output to a transaction analysis report; if the check is passed, carrying out transaction judgment according to a transaction algorithm corresponding to the index; and outputting the index data of the transaction to the transaction analysis report.
In an optional manner, the early warning analysis module 402 is further configured to: calculating an early warning index according to the abnormal index data; determining whether early warning is needed or not according to the early warning index; and if the early warning is required, generating the early warning information.
In an optional manner, the early warning analysis module 402 is further configured to: calculating a difference movement deviation rate according to the difference movement index data and a preset threshold value corresponding to the index; calculating the early warning probability of the index in the same year; and calculating an early warning index according to the transaction deviation rate, the early warning probability of the same year in the last year and a reference early warning probability.
In an alternative way, the early warning index r satisfies the following relation: r = k σ + w (epsilon-epsilon i), wherein k and w are adjustment coefficients, sigma is the heterokinetic deviation rate, epsilon is the early warning probability of the same period of the last year, and epsilon i is the reference early warning probability.
In an optional manner, the warning output module 403 is further configured to: carrying out continuity judgment on the early warning information; and caching a plurality of pieces of early warning information with continuity.
In an alternative manner, the warning output module 403 is configured to: setting output parameters of the early warning information; and outputting the early warning information to a monitoring center according to the output parameter setting.
In an alternative form, the output parameters include: at least one of a real-time refresh time, a color setting, an upgrade setting, or a monitor setting.
The embodiment of the invention collects the index data of at least one index; performing early warning analysis on the index data of the at least one index to obtain early warning information; and outputting the early warning information to a monitoring center for early warning and monitoring. The early warning information is obtained by performing pre-processing, abnormal motion judgment, artificial intelligence early warning and other early warning analysis on the index data, the early warning information can be seen visually, the life cycle process of early warning information processing and the trend of the abnormal motion index at the latest period of time of the fault risk time point can be displayed, and then an effective loss stopping decision can be provided.
The embodiment of the invention provides a nonvolatile computer storage medium, wherein at least one executable instruction is stored in the computer storage medium, and the computer executable instruction can execute the intelligent early warning method of the network management system in any method embodiment.
The executable instructions may be specifically configured to cause the processor to perform the following operations:
acquiring index data of at least one index;
performing early warning analysis on the index data of the at least one index to obtain early warning information;
and outputting the early warning information to a monitoring center for early warning and monitoring.
In an optional manner, the index includes a user index, a business index, a service index, an application index, and a platform index.
In an alternative form, the executable instructions cause the processor to:
acquiring index data of at least one index for judging faults and early warning;
preprocessing and caching the index data of the at least one index;
carrying out transaction judgment on the index data of the at least one index according to a preset transaction algorithm to output the index data of the transaction;
and carrying out artificial intelligence early warning judgment on the abnormal index data by using a preset artificial intelligence model to obtain early warning information.
In an alternative, the executable instructions cause the processor to:
and adjusting the index data of the at least one index for judging the fault and early warning according to the running condition of the network management system.
In an alternative form, the executable instructions cause the processor to:
selecting an index model and a classification mode of at least one index;
and acquiring index data of the at least one index of at least one network level according to the index model and the classification mode.
In an alternative, the executable instructions cause the processor to:
aligning the index data of the at least one index by time;
cleaning the index data of the at least one index from the unneeded index data;
and caching the cleaned index data of the at least one index.
In an alternative, the executable instructions cause the processor to:
filtering the index data of the at least one index within a preset filtering time period range;
and filtering the index data of the at least one index, wherein the index data is not within a preset effective caching time.
In an alternative form, the executable instructions cause the processor to:
verifying the index data of the at least one index with the reference range of the index;
if the verification is not passed, the index data is output to a transaction analysis report;
if the check is passed, carrying out transaction judgment according to a transaction algorithm corresponding to the index;
and outputting the index data of the transaction to the transaction analysis report.
In an alternative, the executable instructions cause the processor to:
calculating an early warning index according to the abnormal index data;
determining whether early warning is needed or not according to the early warning index;
and if the early warning is needed, generating the early warning information.
In an alternative, the executable instructions cause the processor to:
calculating the abnormal movement deviation rate according to the abnormal movement index data and a preset threshold corresponding to the index;
calculating the early warning probability of the index in the same year;
and calculating an early warning index according to the abnormal change deviation rate, the early warning probability of the same year in the last year and a reference early warning probability.
In an alternative way, the early warning index r satisfies the following relation:
r＝k*σ+w*(ε-εi)
and k and w are adjustment coefficients, sigma is the difference deviation rate, epsilon is the early warning probability of the same period of the last year, and epsilon i is the reference early warning probability.
In an alternative, the executable instructions cause the processor to:
carrying out continuity judgment on the early warning information;
and caching a plurality of pieces of early warning information with continuity.
In an alternative, the executable instructions cause the processor to:
setting output parameters of the early warning information;
and outputting the early warning information to a monitoring center according to the output parameter setting.
The embodiment of the invention collects the index data of at least one index; performing early warning analysis on the index data of the at least one index to obtain early warning information; and outputting the early warning information to a monitoring center for early warning and monitoring. The early warning information is obtained through early warning analysis such as preprocessing, abnormal motion judgment, artificial intelligence early warning and the like on the index data, the early warning information can be visually seen, the life cycle process of early warning information processing and the trend of the abnormal motion index of a latest period of time of a fault risk time point can be displayed, and then an effective loss stopping decision can be provided.
An embodiment of the present invention provides a computer program product, which includes a computer program stored on a computer storage medium, where the computer program includes program instructions, and when the program instructions are executed by a computer, the computer is caused to execute the intelligent early warning method of a network management system in any of the above method embodiments.
The executable instructions may be specifically configured to cause the processor to:
acquiring index data of at least one index;
performing early warning analysis on the index data of the at least one index to obtain early warning information;
and outputting the early warning information to a monitoring center for early warning and monitoring.
In an optional manner, the index includes a user index, a service index, an application index, and a platform index.
In an alternative, the executable instructions cause the processor to:
acquiring index data of at least one index for judging faults and early warning;
preprocessing and caching the index data of the at least one index;
carrying out transaction judgment on the index data of the at least one index according to a preset transaction algorithm to output the index data of the transaction;
and carrying out artificial intelligence early warning judgment on the abnormal index data by using a preset artificial intelligence model to obtain early warning information.
In an alternative, the executable instructions cause the processor to:
and adjusting the index data of the at least one index for judging the fault and early warning according to the running condition of the network management system.
In an alternative, the executable instructions cause the processor to:
selecting an index model and a classification mode of at least one index;
and acquiring index data of the at least one index of at least one network level according to the index model and the classification mode.
In an alternative, the executable instructions cause the processor to:
aligning the index data of the at least one index by time;
cleaning the index data of the at least one index from the unneeded index data;
and caching the cleaned index data of the at least one index.
In an alternative, the executable instructions cause the processor to:
filtering the index data of the at least one index within a preset filtering time period range;
and filtering the index data of the at least one index, wherein the index data is not within a preset effective caching time.
In an alternative form, the executable instructions cause the processor to:
verifying the index data of the at least one index with the reference range of the index;
if the verification fails, the index data is output to a transaction analysis report;
if the check is passed, carrying out transaction judgment according to a transaction algorithm corresponding to the index;
and outputting the index data of the transaction to the transaction analysis report.
In an alternative form, the executable instructions cause the processor to:
calculating an early warning index according to the abnormal index data;
determining whether early warning is needed or not according to the early warning index;
and if the early warning is needed, generating the early warning information.
In an alternative, the executable instructions cause the processor to:
calculating a difference movement deviation rate according to the difference movement index data and a preset threshold value corresponding to the index;
calculating the early warning probability of the index in the same year;
and calculating an early warning index according to the transaction deviation rate, the early warning probability of the same year in the last year and a reference early warning probability.
In an alternative mode, the warning index r satisfies the following relation:
r＝k*σ+w*(ε-εi)
and k and w are adjustment coefficients, sigma is the difference deviation rate, epsilon is the early warning probability of the same period of the last year, and epsilon i is the reference early warning probability.
In an alternative, the executable instructions cause the processor to:
carrying out continuity judgment on the early warning information;
and caching a plurality of pieces of early warning information with continuity.
In an alternative form, the executable instructions cause the processor to:
setting output parameters of the early warning information;
and outputting the early warning information to a monitoring center according to the output parameter setting.
The embodiment of the invention collects the index data of at least one index; performing early warning analysis on the index data of the at least one index to obtain early warning information; and outputting the early warning information to a monitoring center for early warning and monitoring. The early warning information is obtained by performing pre-processing, abnormal motion judgment, artificial intelligence early warning and other early warning analysis on the index data, the early warning information can be seen visually, the life cycle process of early warning information processing and the trend of the abnormal motion index at the latest period of time of the fault risk time point can be displayed, and then an effective loss stopping decision can be provided.
Fig. 5 is a schematic structural diagram of an embodiment of the apparatus according to the present invention, and the specific embodiment of the present invention does not limit the specific implementation of the apparatus.
As shown in fig. 5, the apparatus may include: a processor (processor) 502, a Communications Interface 504, a memory 506, and a communication bus 508.
Wherein: the processor 502, communication interface 504, and memory 506 communicate with one another via a communication bus 508. A communication interface 504 for communicating with network elements of other devices, such as clients or other servers. The processor 502 is configured to execute the program 510, and may specifically execute relevant steps in the above-described intelligent warning method embodiment of the network management system.
In particular, program 510 may include program code that includes computer operating instructions.
The processor 502 may be a central processing unit CPU, or an Application Specific Integrated Circuit ASIC (Application Specific Integrated Circuit), or one or more Integrated circuits configured to implement an embodiment of the present invention. The device includes one or more processors, which may be the same type of processor, such as one or more CPUs; or may be different types of processors such as one or more CPUs and one or more ASICs.
A memory 506 for storing a program 510. The memory 506 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
The program 510 may specifically be used to cause the processor 502 to perform the following operations:
acquiring index data of at least one index;
performing early warning analysis on the index data of the at least one index to obtain early warning information;
and outputting the early warning information to a monitoring center for early warning and monitoring.
In an alternative manner, the preset conditions include: calling number, called number, terminal type, calling duration, and calling frequency.
In an alternative, the program 510 causes the processor to:
acquiring index data of at least one index for judging faults and early warning;
preprocessing and caching the index data of the at least one index;
carrying out transaction judgment on the index data of the at least one index according to a preset transaction algorithm to output the index data of the transaction;
and carrying out artificial intelligence early warning judgment on the abnormal index data by using a preset artificial intelligence model to obtain early warning information.
In an alternative, the program 510 causes the processor to:
and adjusting the index data of the at least one index for judging the fault and early warning according to the running condition of the network management system.
In an alternative, the program 510 causes the processor to:
selecting an index model and a classification mode of at least one index;
and acquiring index data of the at least one index of at least one network level according to the index model and the classification mode.
In an alternative, the program 510 causes the processor to:
aligning the index data of the at least one index by time;
cleaning the index data of the at least one index from the unneeded index data;
and caching the cleaned index data of the at least one index.
In an alternative, the program 510 causes the processor to:
filtering the index data of the at least one index within a preset filtering time period range;
and filtering the index data of the at least one index, wherein the index data is not within a preset effective caching time.
In an alternative, the program 510 causes the processor to:
verifying the index data of the at least one index with the reference range of the index;
if the verification is not passed, the index data is output to a transaction analysis report;
if the check is passed, carrying out transaction judgment according to a transaction algorithm corresponding to the index;
and outputting the index data of the transaction to the transaction analysis report.
In an alternative, the program 510 causes the processor to:
calculating an early warning index according to the abnormal index data;
determining whether early warning is needed or not according to the early warning index;
and if the early warning is required, generating the early warning information.
In an alternative, the program 510 causes the processor to:
calculating the abnormal movement deviation rate according to the abnormal movement index data and a preset threshold corresponding to the index;
calculating the early warning probability of the index in the same period of the last year;
and calculating an early warning index according to the abnormal change deviation rate, the early warning probability of the same year in the last year and a reference early warning probability.
In an alternative way, the early warning index r satisfies the following relation:
r＝k*σ+w*(ε-εi)
and k and w are adjustment coefficients, sigma is the variation deviation rate, epsilon is the early warning probability of the same period of the last year, and epsilon i is the reference early warning probability.
In an alternative, the program 510 causes the processor to:
carrying out continuity judgment on the early warning information;
and caching a plurality of pieces of early warning information with continuity.
In an alternative, the program 510 causes the processor to:
setting output parameters of the early warning information;
and outputting the early warning information to a monitoring center according to the output parameter setting.
The embodiment of the invention collects the index data of at least one index; performing early warning analysis on the index data of the at least one index to obtain early warning information; and outputting the early warning information to a monitoring center for early warning and monitoring. The early warning information is obtained by performing pre-processing, abnormal motion judgment, artificial intelligence early warning and other early warning analysis on the index data, the early warning information can be seen visually, the life cycle process of early warning information processing and the trend of the abnormal motion index at the latest period of time of the fault risk time point can be displayed, and then an effective loss stopping decision can be provided.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general purpose systems may also be used with the teachings herein. The required structure for constructing such a system will be apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It is appreciated that a variety of programming languages may be used to implement the teachings of the present invention as described herein, and any descriptions of specific languages are provided above to disclose the best mode of the invention.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: rather, the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the devices in an embodiment may be adaptively changed and arranged in one or more devices different from the embodiment. The modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore, may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means can be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specified otherwise.
Claims (13)
1. An intelligent early warning method for a network management system, the method comprising:
acquiring index data of at least one index;
acquiring index data of at least one index for judging faults and early warning;
preprocessing and caching the index data of the at least one index;
performing transaction judgment on the index data of the at least one index according to a preset transaction algorithm, and outputting the index data of the transaction, including: checking the index data of the at least one index with the reference range of the index; if the verification fails, the index data is output to a transaction analysis report; if the check is passed, carrying out transaction judgment according to a transaction algorithm corresponding to the index; outputting the index data of the transaction to the transaction analysis report;
applying a preset artificial intelligence model to carry out artificial intelligence early warning judgment on the abnormal index data, and acquiring early warning information, wherein the method comprises the following steps: calculating the abnormal movement deviation rate according to the abnormal movement index data and a preset threshold corresponding to the index; calculating the early warning probability of the index in the same year; calculating an early warning index according to the transaction deviation rate, the early warning probability of the same year in the last year and a reference early warning probability; determining whether early warning is needed or not according to the early warning index; if the early warning is needed, generating the early warning information;
and outputting the early warning information to a monitoring center for early warning and monitoring.
2. The method of claim 1, wherein the metrics comprise user metrics, business metrics, service metrics, application metrics, platform metrics.
3. The method of claim 1, wherein obtaining indicator data of at least one indicator used for fault diagnosis and early warning comprises:
and adjusting the index data of the at least one index for judging the fault and early warning according to the running condition of the network management system.
4. The method of claim 1, wherein the obtaining of the index data of the at least one index for determining the fault and the early warning comprises:
selecting an index model and a classification mode of at least one index;
and acquiring index data of the at least one index of at least one network level according to the index model and the classification mode.
5. The method of claim 1, wherein pre-processing the metric data of the at least one metric for caching comprises:
aligning the index data of the at least one index by time;
cleaning the index data of the at least one index from the unneeded index data;
and caching the cleaned index data of the at least one index.
6. The method of claim 5, wherein the purging of unwanted metric data in the metric data of the at least one metric comprises:
filtering the index data of the at least one index within a preset filtering time period range;
and filtering the index data of the at least one index except for a preset effective caching time.
7. The method of claim 1, wherein the pre-warning index r satisfies the following relationship:
r＝k*σ+w*(ε-εi)
and k and w are adjustment coefficients, sigma is the variation deviation rate, epsilon is the early warning probability of the same period of the last year, and epsilon i is the reference early warning probability.
8. The method of claim 1, wherein before outputting the warning information to a monitoring center for warning and monitoring, the method further comprises:
carrying out continuity judgment on the early warning information;
and caching a plurality of pieces of early warning information with continuity.
9. The method of claim 1, wherein outputting the warning information to a monitoring center for warning and monitoring further comprises:
setting output parameters of the early warning information;
and outputting the early warning information to a monitoring center according to the output parameter setting.
10. The method of claim 9, wherein the output parameters comprise: at least one of a real-time refresh time, a color setting, an upgrade setting, or a monitor setting.
11. An intelligent early warning device of a network management system, the device comprising:
the data acquisition module is used for acquiring index data of at least one index;
the early warning analysis module is used for acquiring index data of at least one index for judging faults and early warning; preprocessing and caching the index data of the at least one index; performing abnormal change judgment on the index data of the at least one index according to a preset abnormal change algorithm, and outputting the abnormal index data; applying a preset artificial intelligence model to carry out artificial intelligence early warning judgment on the abnormal index data, and acquiring early warning information, wherein the method comprises the following steps: calculating a difference movement deviation rate according to the difference movement index data and a preset threshold value corresponding to the index; calculating the early warning probability of the index in the same year; calculating an early warning index according to the abnormal change deviation rate, the early warning probability of the same year in the last year and a reference early warning probability; determining whether early warning is needed or not according to the early warning index; if the early warning is needed, generating the early warning information;
and the early warning output module is used for outputting the early warning information to a monitoring center for early warning and monitoring.
12. A computing device, comprising: the system comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface are communicated with each other through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform the steps of the intelligent warning method of the network management system according to any of claims 1-10.
13. A computer storage medium having stored therein at least one executable instruction for causing a processor to perform the steps of the intelligent warning method of a network management system according to any one of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910395539.4A CN111934895B (en) | 2019-05-13 | 2019-05-13 | Intelligent early warning method and device for network management system and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910395539.4A CN111934895B (en) | 2019-05-13 | 2019-05-13 | Intelligent early warning method and device for network management system and computing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111934895A CN111934895A (en) | 2020-11-13 |
| CN111934895B true CN111934895B (en) | 2022-11-15 |
Family
ID=73282869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910395539.4A Active CN111934895B (en) | 2019-05-13 | 2019-05-13 | Intelligent early warning method and device for network management system and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111934895B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113095676B (en) * | 2021-04-12 | 2024-06-11 | 中国工商银行股份有限公司 | Method, device, equipment and medium for acquiring risk level of production event |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101155087A (en) * | 2007-07-10 | 2008-04-02 | 中国移动通信集团江苏有限公司 | System and method for receiving network early warning information by multimedia message |
| WO2010069190A1 (en) * | 2008-12-18 | 2010-06-24 | 中兴通讯股份有限公司 | Early warning system and method for wireless communication |
| CN103178990A (en) * | 2011-12-20 | 2013-06-26 | 中国移动通信集团青海有限公司 | Network device performance monitoring method and network management system |
| CN106161085A (en) * | 2016-06-20 | 2016-11-23 | 深圳前海微众银行股份有限公司 | The monitoring system and method for messaging bus |
| WO2017219357A1 (en) * | 2016-06-24 | 2017-12-28 | 深圳市赛亿科技开发有限公司 | Method and system for monitoring power supply and distribution safety |
| CN108063676A (en) * | 2016-11-08 | 2018-05-22 | 中国移动通信集团山西有限公司 | Communication network failure method for early warning and device |
| CN108206747A (en) * | 2016-12-16 | 2018-06-26 | 中国移动通信集团山西有限公司 | Method for generating alarm and system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104156822A (en) * | 2014-08-11 | 2014-11-19 | 国家电网公司 | SOA-based comprehensive enterprise level information system operation and maintenance management method |
| CN105868256A (en) * | 2015-12-28 | 2016-08-17 | 乐视网信息技术（北京）股份有限公司 | Method and system for processing user behavior data |
| CN205510066U (en) * | 2016-04-08 | 2016-08-24 | 国家新闻出版广电总局无线电台管理局 | Well short wave transmitting machine fault early -warning device |
| US10127125B2 (en) * | 2016-10-21 | 2018-11-13 | Accenture Global Solutions Limited | Application monitoring and failure prediction |
| CN109582545A (en) * | 2018-12-06 | 2019-04-05 | 合肥海诺恒信息科技有限公司 | A kind of IT operation management system and method based on intelligent mobile terminal |
-
2019
- 2019-05-13 CN CN201910395539.4A patent/CN111934895B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101155087A (en) * | 2007-07-10 | 2008-04-02 | 中国移动通信集团江苏有限公司 | System and method for receiving network early warning information by multimedia message |
| WO2010069190A1 (en) * | 2008-12-18 | 2010-06-24 | 中兴通讯股份有限公司 | Early warning system and method for wireless communication |
| CN103178990A (en) * | 2011-12-20 | 2013-06-26 | 中国移动通信集团青海有限公司 | Network device performance monitoring method and network management system |
| CN106161085A (en) * | 2016-06-20 | 2016-11-23 | 深圳前海微众银行股份有限公司 | The monitoring system and method for messaging bus |
| WO2017219357A1 (en) * | 2016-06-24 | 2017-12-28 | 深圳市赛亿科技开发有限公司 | Method and system for monitoring power supply and distribution safety |
| CN108063676A (en) * | 2016-11-08 | 2018-05-22 | 中国移动通信集团山西有限公司 | Communication network failure method for early warning and device |
| CN108206747A (en) * | 2016-12-16 | 2018-06-26 | 中国移动通信集团山西有限公司 | Method for generating alarm and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111934895A (en) | 2020-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102011453B1 (en) | Predictability of Conditionality Using Recurrent Neural Networks | |
| CN108052528A (en) | A kind of storage device sequential classification method for early warning | |
| CN107992410B (en) | Software quality monitoring method and device, computer equipment and storage medium | |
| WO2019051042A1 (en) | Apparatus and method for real time analysis, predicting and reporting of anomalous database transaction log activity | |
| CN108109066A (en) | A kind of credit scoring model update method and system | |
| CN108880845A (en) | A kind of method and relevant apparatus of information alert | |
| CN112346936A (en) | Application fault root cause positioning method and system | |
| CN111539493A (en) | Alarm prediction method and device, electronic equipment and storage medium | |
| CN112650608B (en) | Abnormal root cause positioning method, related device and equipment | |
| CN116449762B (en) | Safety early warning method and device for realizing intelligent equipment based on Internet of things | |
| CN112085869A (en) | Civil aircraft flight safety analysis method based on flight parameter data | |
| CN110275992A (en) | Emergency processing method, device, server and computer readable storage medium | |
| CN111934895B (en) | Intelligent early warning method and device for network management system and computing equipment | |
| US20190087904A1 (en) | Remote processing of anomalous vehicle sensor data | |
| CN111949502A (en) | Database early warning method and device, computing equipment and medium | |
| CN109074413A (en) | For determining whether assets are possible to the computerization fluid analysis with flow problem | |
| CN115860465A (en) | Enterprise associated data processing early warning method, system and device | |
| CN115509784A (en) | Fault detection method and device for database instance | |
| CN110059906B (en) | Policy effectiveness analysis method, device, server and storage medium | |
| CN115187026A (en) | Industrial risk monitoring method and system and readable storage medium | |
| CN110457367B (en) | Method and system for discovering data transaction | |
| CN112395167A (en) | Operation fault prediction method and device and electronic equipment | |
| CN113763181A (en) | Risk pressure test system | |
| CN109427177A (en) | A kind of monitoring alarm method and device | |
| CN114327962A (en) | Hard disk fault grading early warning method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |