CN116074215B - Network quality detection method, device, equipment and storage medium - Google Patents
Network quality detection method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116074215B CN116074215B CN202211721502.4A CN202211721502A CN116074215B CN 116074215 B CN116074215 B CN 116074215B CN 202211721502 A CN202211721502 A CN 202211721502A CN 116074215 B CN116074215 B CN 116074215B
- Authority
- CN
- China
- Prior art keywords
- data information
- target
- information corresponding
- time
- time period
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 79
- 238000003860 storage Methods 0.000 title claims abstract description 27
- 230000002159 abnormal effect Effects 0.000 claims abstract description 98
- 238000000034 method Methods 0.000 claims abstract description 39
- 238000007781 pre-processing Methods 0.000 claims abstract description 25
- 238000012545 processing Methods 0.000 claims description 38
- 238000007621 cluster analysis Methods 0.000 claims description 24
- 238000012423 maintenance Methods 0.000 claims description 19
- 238000004891 communication Methods 0.000 abstract description 12
- 230000005856 abnormality Effects 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 description 24
- 230000006870 function Effects 0.000 description 15
- 238000010586 diagram Methods 0.000 description 14
- 208000018910 keratinopathic ichthyosis Diseases 0.000 description 10
- 230000011664 signaling Effects 0.000 description 8
- 238000013461 design Methods 0.000 description 7
- 238000007418 data mining Methods 0.000 description 6
- 238000005457 optimization Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000011084 recovery Methods 0.000 description 5
- 235000019580 granularity Nutrition 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012795 verification Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 210000001503 joint Anatomy 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000007474 system interaction Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Abstract
The application discloses a network quality detection method, a device, equipment and a storage medium, relates to the technical field of communication, and is used for improving the efficiency of detecting network quality and determining the accuracy of network index abnormality. The method comprises the following steps: basic data information corresponding to a target network in a target historical time period before a target moment is acquired, and the basic data information is subjected to data preprocessing to obtain target data information, wherein the basic data information comprises: equipment operation information, tool operation information and base station operation information, and the data preprocessing comprises the following steps: data detection, data statistics, abnormal data rejection and data format adjustment; based on the target data information and a preset algorithm, determining predicted data information corresponding to a first time period after the target moment; and determining abnormal data information in the real data information corresponding to the first time period based on the predicted data information corresponding to the first time period and the difference value between the real data information corresponding to the first time period.
Description
Technical Field
The present application relates to the field of communications technologies, and in particular, to a method, an apparatus, a device, and a storage medium for detecting network quality.
Background
With the development of communication networks, when network indexes are problematic, how to quickly discover abnormal fluctuation of the network indexes and make full use of data and experience libraries of all parties, and efficiently and accurately locating and timely processing root causes of poor network quality are challenges for network maintenance and optimization personnel. The network index data can be manually analyzed through the network manager at present, so that the root cause of poor network quality can be analyzed, and the root cause of poor network quality can be analyzed by adopting a background signaling tracking mode.
In the method, network index data are obtained through a network manager, so that the efficiency is low when the network index data are manually analyzed, and the analysis result does not have systematicness and predictability. The background signaling tracking mode is generally used for accurately positioning the local network index problem, and the whole network index problem cannot be positioned. Therefore, the efficiency of detecting the network quality is low, and the accuracy of determining the network index abnormality problem is poor.
Disclosure of Invention
The application provides a network quality detection method, a device, equipment and a storage medium, which are used for solving the problems that the efficiency of manually detecting the data information of network indexes is low, and the abnormal data information of the network indexes of the whole network cannot be determined by adopting a background signaling tracking mode, so that the efficiency of detecting the network quality is improved, and the accuracy of determining the abnormal problem of the network indexes is improved.
In order to achieve the above purpose, the application adopts the following technical scheme:
In a first aspect, a network quality detection method is provided, the method including: basic data information corresponding to a target network in a target historical time period before a target moment is acquired, and the basic data information is subjected to data preprocessing to obtain target data information, wherein the basic data information comprises at least one of the following items: device operation information, tool operation information and base station operation information, and the data preprocessing comprises at least one of the following steps: data detection, data statistics, abnormal data rejection and data format adjustment; based on the target data information and a preset algorithm, determining predicted data information corresponding to a first time period after the target moment; and determining abnormal data information in the real data information corresponding to the first time period based on the predicted data information corresponding to the first time period and the difference value between the real data information corresponding to the first time period.
In one possible implementation manner, determining predicted data information corresponding to a first time period after the target time based on the target data information and a preset algorithm includes: determining data information corresponding to each of a plurality of first time points included in a target historical time period from target data information, wherein a preset time is arranged between any two adjacent first time points in the plurality of first time points; inputting the data information corresponding to each first time point in the plurality of first time points into a preset algorithm in sequence according to the time sequence, and obtaining the predicted data information corresponding to each second time point in the plurality of second time points included in the first time period after the target time, wherein the interval between any two adjacent second time points in the plurality of second time points is preset for a long time.
In one possible implementation, the method further includes: acquiring real data information corresponding to each of a plurality of second time points included in the first time period; based on the predicted data information corresponding to the first time period and the difference value between the real data information corresponding to the first time period, determining the abnormal data information in the real data information corresponding to the first time period comprises: determining a size relation between predicted data information and real data information corresponding to any second time point in a plurality of second time points included in the first time period; and when the predicted data information corresponding to any second time point is determined to be larger than the real data information and the difference value between the predicted data information and the real data information is determined to be larger than a preset threshold value, determining the real data information corresponding to any second time point as abnormal data information.
In one possible implementation, each exception data information includes at least one of the following information: location information, network element information, area information, failure code, terminal information; the method further comprises the steps of: performing cluster analysis processing based on the determined plurality of abnormal data information, and determining root causes for generating the plurality of abnormal data information; and generating an alarm work order based on the root cause of the generated multiple abnormal data information, and distributing the alarm work order to corresponding operation and maintenance personnel.
In a second aspect, there is provided a network quality detection apparatus comprising: the device comprises an acquisition unit, a processing unit and a determination unit; the acquisition unit is used for acquiring basic data information corresponding to the target network in a target history time period before the target moment, wherein the basic data information comprises at least one of the following items: equipment operation information, tool operation information and base station operation information; the processing unit is used for carrying out data preprocessing on the basic data information to obtain target data information, wherein the data preprocessing comprises at least one of the following steps: data detection, data statistics, abnormal data rejection and data format adjustment; the determining unit is used for determining prediction data information corresponding to a first time period after the target moment based on the target data information and a preset algorithm; the determining unit is further configured to determine abnormal data information in the real data information corresponding to the first time period based on the predicted data information corresponding to the first time period and a difference value between the real data information corresponding to the first time period.
In a possible implementation manner, the determining unit is further configured to determine, from the target data information, data information corresponding to each of a plurality of first time points included in the target historical time period, where a preset duration is spaced between any two adjacent first time points in the plurality of first time points; the processing unit is further configured to sequentially input data information corresponding to each of the first time points in the plurality of first time points into a preset algorithm according to a time sequence, and obtain predicted data information corresponding to each of the second time points included in the first time period after the target time, where a preset duration is provided between any two adjacent second time points in the plurality of second time points.
In a possible implementation manner, the obtaining unit is further configured to obtain real data information corresponding to each of a plurality of second time points included in the first time period; the determining unit is further used for determining the size relation between the predicted data information and the real data information corresponding to any second time point in the plurality of second time points included in the first time period; and the determining unit is further used for determining that the real data information corresponding to any second time point is abnormal data information when the predicted data information corresponding to any second time point is larger than the real data information and the difference value between the predicted data information and the real data information is larger than a preset threshold value.
In one possible implementation, each exception data information includes at least one of the following information: location information, network element information, area information, failure code, terminal information; the determining unit is also used for carrying out cluster analysis processing based on the determined abnormal data information and determining root causes for generating the abnormal data information; and the processing unit is also used for generating an alarm work order based on the root causes of the abnormal data information and distributing the alarm work order to corresponding operation and maintenance personnel.
In a third aspect, an electronic device, comprising: a processor and a memory; wherein the memory is configured to store one or more programs, the one or more programs comprising computer-executable instructions that, when executed by the electronic device, cause the electronic device to perform a network quality detection method as in the first aspect.
In a fourth aspect, there is provided a computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by a computer, cause the computer to perform a network quality detection method as in the first aspect.
The application provides a network quality detection method, a device, equipment and a storage medium, which are applied to a scene for detecting network quality. When the network quality is required to be detected, basic data information which comprises at least one of equipment operation information, tool operation information and base station operation information and corresponds to a target network in a target historical time period before a target moment can be obtained, and data preprocessing comprising at least one of data detection, data statistics, abnormal data rejection and data format adjustment is carried out on the basic data information to obtain target data information. Further, based on the target data information and a preset algorithm, the predicted data information corresponding to the first time period after the target time is determined. And determining abnormal data information in the real data information corresponding to the first time period based on the predicted data information corresponding to the first time period and the difference value between the real data information corresponding to the first time period. According to the method, when the network quality is required to be detected, the basic data information corresponding to the target network can be obtained, the basic data information is subjected to data preprocessing to obtain the target data information, and then the predicted data information is determined based on the target data information and a preset algorithm so as to determine abnormal data information in the real data information based on the predicted data information and the real data information. Therefore, the problems that the efficiency of manually detecting the data information of the network index is low, and abnormal data information of the network index of the whole network cannot be determined by adopting a background signaling tracking mode are solved. Thereby improving the efficiency of detecting the network quality and the accuracy of determining the network index abnormality problem.
Drawings
Fig. 1 is a schematic diagram of a network quality detection system according to an embodiment of the present application;
fig. 2 is a schematic diagram of a network quality detection system according to a second embodiment of the present application;
fig. 3 is a schematic flow chart of a network quality detection method according to an embodiment of the present application;
fig. 4 is a schematic diagram of data collection and warehousing according to an embodiment of the present application;
fig. 5 is a schematic flow chart II of a network quality detection method according to an embodiment of the present application;
Fig. 6 is a flowchart of a network quality detection method according to an embodiment of the present application;
Fig. 7 is a flowchart of a network quality detection method according to an embodiment of the present application;
FIG. 8 is a schematic diagram of a network index cluster analysis according to an embodiment of the present application;
FIG. 9 is a schematic diagram of design logic of a network quality detection system according to an embodiment of the present application;
Fig. 10 is a schematic structural diagram of a network quality detecting device according to an embodiment of the present application;
fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be described below with reference to the accompanying drawings in the embodiments of the present application.
In the description of the present application, "/" means "or" unless otherwise indicated, for example, A/B may mean A or B. "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. Further, "at least one", "a plurality" means two or more. The terms "first," "second," and the like do not limit the number and order of execution, and the terms "first," "second," and the like do not necessarily differ.
In the communication field, network key performance indicators (Key Performance Indicator, kpis) (i.e., network indicators) directly relate to network quality and user perception, and good communication network quality can bring good use experience to users, and when network indicators have problems, the use experience of users is reduced. Therefore, the method for analyzing the root causes of poor network quality is an urgent problem to be solved and challenges for network maintenance and optimization personnel all the time, and is a necessary path for future development of a mobile network.
At present, two modes are mainly adopted to analyze the root cause of poor network quality, specifically, network index data can be obtained from a network manager to manually analyze the network index data, and a background signaling tracking mode can be adopted to analyze the root cause of poor network quality. The network index data is obtained by the network manager, so that the efficiency is low when the network index data is manually analyzed, and the analysis result is difficult to have systematicness and predictability. The background signaling tracking mode is generally used for accurately positioning the local network index problem, and the whole network index problem cannot be positioned.
The application provides a network quality detection method, when network quality is required to be detected, basic data information which comprises at least one item of equipment operation information, tool operation information and base station operation information and corresponds to a target network in a target historical time period before a target moment can be obtained, and data preprocessing comprising at least one item of data detection, data statistics, abnormal data rejection and data format adjustment is carried out on the basic data information to obtain target data information. Further, based on the target data information and a preset algorithm, the predicted data information corresponding to the first time period after the target time is determined. And determining abnormal data information in the real data information corresponding to the first time period based on the predicted data information corresponding to the first time period and the difference value between the real data information corresponding to the first time period. According to the method, when the network quality is required to be detected, the basic data information corresponding to the target network can be obtained, the basic data information is subjected to data preprocessing to obtain the target data information, and then the predicted data information is determined based on the target data information and a preset algorithm so as to determine abnormal data information in the real data information based on the predicted data information and the real data information. Therefore, the problems that the efficiency of manually detecting the data information of the network index is low, and abnormal data information of the network index of the whole network cannot be determined by adopting a background signaling tracking mode are solved. Thereby improving the efficiency of detecting the network quality and the accuracy of determining the network index abnormality problem.
The network quality detection method provided by the embodiment of the application can be applied to a network quality detection system. Fig. 1 shows a schematic diagram of the structure of a network quality detection system. As shown in fig. 1, the network quality detection system 20 includes: a server 21 and a terminal device 22. The server 21 is configured to obtain basic data information corresponding to a target network through the terminal device 22, perform data preprocessing on the basic data information to obtain target data information, determine predicted data information based on the target data information, determine abnormal data information based on the predicted data information, and send the abnormal data information to the terminal device 22; the terminal device 22 is configured to send basic data information corresponding to the target network to the server 21, and receive abnormal data information from the server 21, so as to detect network quality through the server 21 and the terminal device 22.
Fig. 2 shows a schematic diagram of a network quality detection system. As shown in fig. 2, the network quality detection system 30 includes: a data source module 31, a data mining module 32, a function module 33, and a production system module 34. The data source module 31 includes a device network manager 311, a professional analysis system (Discovery) 312, and an end-to-end analysis system 313; the data mining module 32 includes index statistics 321 and information extraction 322; the functional module 33 includes key performance indicator anomaly detection 331, associated data cluster analysis 332, and experience library matching 333; the production system module 34 includes an electronic operation and maintenance system 341 and a work order processing validation 342.
The data source module 31 is configured to obtain basic data information (including equipment operation information, tool operation information, and base station operation information) corresponding to the target network, and send the basic data information to the data mining module 32; the data mining module 32 is configured to receive the basic data information from the data source module 31, perform data preprocessing (including data detection, data statistics, abnormal data rejection, and data format adjustment) on the basic data information to obtain target data information, and send the target data information to the functional module 33; the function module 33 is configured to receive the target data information from the data mining module 32, determine predicted data information based on the target data information, determine abnormal data information based on the predicted data information, perform cluster analysis processing on the abnormal data information, determine a root cause for generating the abnormal data information, and send the root cause for generating the abnormal data information to the production system module 34; the production system module 34 is configured to receive the root cause of the generation of the abnormal data information from the function module 33, generate an alarm work order based on the root cause of the generation of the abnormal data information, and dispatch the alarm work order to a corresponding operation and maintenance person.
The device network manager 311 is configured to obtain device operation information and send the device operation information to the index statistics 321; professional analysis system 312 is configured to obtain tool operation information and send the tool operation information to information extraction 322; the end-to-end analysis system 313 is configured to obtain base station operation information and send the base station operation information to the information extraction 322; the index statistics 321 is configured to receive the device operation information from the device network manager 311, perform data preprocessing on the device operation information to obtain target data information corresponding to the device operation information, and send the target data information corresponding to the device operation information to the key performance index anomaly detection 331; the information extraction 322 is configured to receive the tool operation information from the professional analysis system 312 and the base station operation information from the end-to-end analysis system 313, perform data preprocessing on the tool operation information and the base station operation information to obtain target data information corresponding to the tool operation information and the base station operation information, and send the target data information corresponding to the tool operation information and the base station operation information to the associated data cluster analysis 332.
The key performance indicator anomaly detection 331 is configured to receive target data information corresponding to the device operation information from the indicator statistics 321, determine predicted data information based on the target data information corresponding to the device operation information and a preset algorithm, and send the predicted data information to the associated data cluster analysis 332; the associated data cluster analysis 332 is configured to receive the tool operation information from the information extraction 322 and the target data information corresponding to the base station operation information, receive the predicted data information from the key performance indicator anomaly detection 331, determine the anomaly data information based on the predicted data information, perform cluster analysis processing on the anomaly data information based on the tool operation information and the target data information corresponding to the base station operation information, and send the result of the cluster analysis processing to the experience base matching 333. The experience library matching 333 is configured to receive the result of the cluster analysis processing from the associated data cluster analysis 332, determine the root cause of generating the abnormal data information based on the result of the cluster analysis processing, and send the root cause of generating the abnormal data information to the electronic operation and maintenance system 341; the electronic operation and maintenance system 341 is configured to receive the root cause of generating the abnormal data information from the associated data cluster analysis 332, generate an alarm work order based on the root cause of generating the abnormal data information, and send the alarm work order to a corresponding operation and maintenance person for work order processing verification; the work order processing verification 342 is used for processing verification of the work order by the operation and maintenance personnel.
The following describes a network quality detection method according to an embodiment of the present application with reference to the accompanying drawings. As shown in fig. 3, the method for detecting network quality provided by the embodiment of the present application is applied to an electronic device, and the method includes S201-S203:
S201, basic data information corresponding to a target network in a target history time period before a target moment is acquired, and data preprocessing is carried out on the basic data information to obtain target data information.
Wherein the underlying data information includes at least one of: device operation information, tool operation information and base station operation information, and the data preprocessing comprises at least one of the following steps: data detection, data statistics, abnormal data rejection and data format adjustment.
It can be understood that the electronic device may acquire basic data information including at least one of device operation information, tool operation information, and base station operation information corresponding to the target network in the target historical period before the target time, and perform data preprocessing including at least one of data detection, data statistics, abnormal data rejection, and adjustment of a data format on the basic data information to obtain the target data information.
Optionally, data integrity checking (i.e., data detection and data statistics) and abnormal data rejection may be performed on the device operational information. Specifically, if the statistical data of the missing network element and index item is found, an alarm is sent out through an alarm interface of the network quality detection system; if a statistical term with a measurement result of 0 is found, the statistical term is deleted by the network quality detection system.
Optionally, the network quality detection system may be in butt joint with the network element operation registration system or the standard worker system to obtain the network element and the operation time period corresponding to the network element, and the performance statistical data corresponding to the network element in the operation time period in the target data information may be removed, so as not to affect the judgment of the network index fluctuation.
It should be noted that, in order to facilitate the subsequent timely and accurate analysis, strict requirements are imposed on the data (i.e., the basic data information) collected and put in storage. Specifically, the original performance data (i.e., the running information of the device) must be complete (for example, the number of attempts, the number of successes, the number of failures of various reasons, etc. related to the network index need to be reported) so as to perform the fluctuation analysis on each statistical term later, thereby finding the problem in a targeted manner. The measurement objects related to the network kpis on the device network management are required to be complete, and follow the minimum rule of the measurement objects (counting the subdivision of the measurement objects to the supported minimum granularity, such as type allocation codes (Type Allocation Code, TAC)), so as to perform accurate positioning. Professional tool data (i.e., tool operating information) and end-to-end system data (i.e., base station operating information) are provided according to the analysis requirements.
In one implementation, as in FIG. 4, a schematic diagram of a data collection warehouse entry is shown. The data sources include a 5G core network (5 gcore,5 gc) equipment network manager, a manufacturer's specialized tool (i.e., a specialized analysis system), and an end-to-end analysis system. Carrying out data acquisition on original performance statistical data (namely equipment operation information) provided by a 5GC equipment network manager through a public object request proxy structure (Common Object Request Broker Architecture, CORBA); data acquisition is carried out on Protocol failure reasons, protocol failure times and user details provided by professional tools of manufacturers through a safe file transfer Protocol (SSH FILE TRANSFER Protocol, SFTP); the opposite end-to-end analysis system collects data through wireless cell and international mobile equipment identification codes (International Mobile Equipment Identity, IMEI) provided by SFTP, then analyzes and stores three collected data (namely, total quantity COUNTER), and finally further performs summarization analysis (namely, summarization analysis from different dimensions and different granularities according to requirements) on the analyzed and stored data.
S202, based on the target data information and a preset algorithm, determining predicted data information corresponding to a first time period after the target time.
It can be appreciated that the electronic device can determine the predicted data information corresponding to the first time period after the target time based on the target data information and the preset algorithm.
Optionally, a detection threshold for network indicator detection may be manually input before the predicted data information corresponding to the first period after the target time is determined based on the target data information and a preset algorithm, and if the detection threshold is not manually input, a default detection threshold of the system may be used. The preset algorithm may be a Prophet algorithm.
For example, the network metrics may be an authentication management function (Authentication Management Function, AMF) initial registration success rate, a fifth generation mobile communication technology (5th Generation Mobile Communication Technology,5G) independent networking (Standalone, SA) session establishment success rate, an EPS FB success rate, and a long term evolution voice-terminal (VoLTE) network connectivity rate. The default detection threshold for the system is shown in table one:
Table-system default detection threshold table
| Network index | System default detection threshold |
| AMF initial registration success rate (reject user reason) | 99％ |
| Success rate of 5G SA session establishment | 99％ |
| EPS FB success rate | 99％ |
| VoLTE network call completing rate (reject user reason) | 99％ |
S203, determining abnormal data information in the real data information corresponding to the first time period based on the predicted data information corresponding to the first time period and the difference value between the real data information corresponding to the first time period.
It is understood that the electronic device may determine the abnormal data information in the real data information corresponding to the first period based on the predicted data information corresponding to the first period and the difference between the real data information corresponding to the first period.
Alternatively, the outlier information may be cluster analyzed (i.e., the outlier information may be further analyzed and located based on more data). Normal data information in the real data information can be added into a normal library in a preset database to be used as an X sample in the follow-up. The entry field of the normal data information into the normal library may include at least one of a province, a network type, a network element, a time point, and a network index. The abnormal data information in the real data information can be added into an abnormal database in the preset database. The entry field of the abnormal data information added into the abnormal library can comprise at least one of province, network type, network element, alarm time, index, fluctuation condition and statistical subitem fluctuation condition. Whether to recover the alarm of the data information newly added into the preset database can be judged, for example, if an abnormal alarm before a corresponding current time point exists in the abnormal database in a network index newly added into the normal database is found, a recovery alarm of the abnormal alarm is generated, and an output field of the recovery alarm can comprise at least one of province, network type, network element, index, alarm time point, index fluctuation condition, recovery time point and index value after recovery.
The application provides a network quality detection method, when network quality is required to be detected, basic data information which comprises at least one item of equipment operation information, tool operation information and base station operation information and corresponds to a target network in a target historical time period before a target moment can be obtained, and data preprocessing comprising at least one item of data detection, data statistics, abnormal data rejection and data format adjustment is carried out on the basic data information to obtain target data information. Further, based on the target data information and a preset algorithm, the predicted data information corresponding to the first time period after the target time is determined. And determining abnormal data information in the real data information corresponding to the first time period based on the predicted data information corresponding to the first time period and the difference value between the real data information corresponding to the first time period. According to the method, when the network quality is required to be detected, the basic data information corresponding to the target network can be obtained, the basic data information is subjected to data preprocessing to obtain the target data information, and then the predicted data information is determined based on the target data information and a preset algorithm so as to determine abnormal data information in the real data information based on the predicted data information and the real data information. Therefore, the problems that the efficiency of manually detecting the data information of the network index is low, and abnormal data information of the network index of the whole network cannot be determined by adopting a background signaling tracking mode are solved. Thereby improving the efficiency of detecting the network quality and the accuracy of determining the network index abnormality problem.
In one design, as shown in fig. 5, a method for detecting network quality in the above step S202 according to an embodiment of the present application specifically includes S301 to S302:
S301, determining data information corresponding to each first time point in a plurality of first time points included in a target historical time period from target data information.
The interval between any two adjacent first time points in the plurality of first time points is preset time length.
It may be appreciated that the data information corresponding to each of the plurality of first time points separated by the preset duration between any two adjacent first time points included in the target history period before the target time may be determined from the target data information.
Alternatively, the index value (i.e., data information) corresponding to each first time point in the target history period before the acquisition target time may be obtained. If the index value corresponding to the first time point in the target history time period is missing, the index value corresponding to the time point before the target history time period is acquired to supplement the index value corresponding to the missing first time point.
For example, the target time may be a current date zero point, the target history time period may be 7 days, and the preset time interval between two adjacent first time points may be 15 minutes, so that an index value corresponding to each of the first time points in 7×24×4 forward steps of the current date zero point may be obtained.
S302, sequentially inputting data information corresponding to each of a plurality of first time points into a preset algorithm according to a time sequence, and obtaining predicted data information corresponding to each of a plurality of second time points included in a first time period after a target time.
The preset duration is arranged between any two adjacent second time points in the plurality of second time points.
It can be understood that the data information corresponding to each first time point in the plurality of first time points may be sequentially input into a preset algorithm according to a time sequence, so as to obtain the predicted data information corresponding to each second time point in the plurality of second time points separated by the preset duration between any two adjacent second time points included in the first time period after the target time.
Alternatively, the data information corresponding to each of the first time points may be sequentially input to a preset algorithm according to a time sequence, and the obtained predicted data information may be an index value, and may further obtain a threshold value of the index (including an upper limit value of the index and a lower limit value of the index) and a true value obtained from the network management device.
For example, the first time period may be 24 hours, the current date zero point is pushed forward by 7×24×4 first time points, and the index value corresponding to each first time point is input into the Prophet algorithm, and the index value corresponding to each second time point, the threshold value of the index corresponding to each second time point, and the actual value corresponding to each second time point obtained from the network management device within 24 hours with 15 minutes granularity after the current date zero point may be output.
In one design, as shown in fig. 6, the method for detecting network quality provided in the embodiment of the present application further includes "obtaining real data information corresponding to each of a plurality of second time points included in the first time period", where the method in step S203 includes steps S401 to S402:
s401, determining a size relation between predicted data information and real data information corresponding to any second time point in a plurality of second time points included in the first time period.
It is understood that the size relationship between the predicted data information and the real data information corresponding to any one of the second time points included in the first time period may be determined for any one of the second time points.
Optionally, the index value corresponding to any second time point in the first time period may be compared with the true value corresponding to any second time point, so as to determine that the magnitude relation between the predicted data information corresponding to any second time point and the real data information, and the difference between the predicted data information corresponding to any second time point and the real data information are greater than a preset threshold.
And S402, when the predicted data information corresponding to any second time point is determined to be larger than the real data information and the difference value between the predicted data information and the real data information is determined to be larger than a preset threshold value, determining the real data information corresponding to any second time point as abnormal data information.
It can be understood that when it is determined that the predicted data information corresponding to any one of the second time points is greater than the real data information and the difference between the predicted data information and the real data information is greater than the preset threshold, the real data information corresponding to any one of the second time points can be determined as the abnormal data information.
Optionally, if the predicted data information (i.e. the index value) corresponding to any one of the second time points is greater than the real data information (i.e. the real value), and the difference between the predicted data information and the real data information is greater than the difference between the predicted data information and the lower limit value of the index, determining that the real data information corresponding to any one of the second time points is abnormal data information.
In one design, as shown in fig. 7, in a network quality detection method provided in an embodiment of the present application, each piece of abnormal data information includes at least one of the following information: location information, network element information, area information, failure code, terminal information, the method further includes S501-S502:
S501, performing cluster analysis processing based on the determined plurality of abnormal data information, and determining root causes of the plurality of abnormal data information.
It is understood that the cluster analysis process may be performed based on the determined plurality of pieces of abnormal data information, and the root cause for generating the plurality of pieces of abnormal data information may be determined.
Alternatively, cluster analysis may be performed based on the determined plurality of abnormal data information, and specifically, failure frequency analysis, proportion fluctuation analysis of failure frequency, and TOP analysis may be performed on the failure code, the network element information, the terminal information (i.e., user or terminal), and the area information of the network index from three dimensions of location information (i.e., province), network element information (i.e., network element), and area information (i.e., tracking area, cell) for the network index corresponding to each of the plurality of abnormal data information. The proportional fluctuation analysis of the failure times may be to compare the failure times item by item with an average value of failure times of the previous n (n is a positive integer) same time periods, and determine that the failure times corresponding to the abnormal data information exceeds a preset fluctuation threshold. The condition that the failure times corresponding to the abnormal data information exceeds the preset fluctuation threshold value can be compared with an experience library, and the root cause of the abnormal data information is determined.
In one implementation, as shown in FIG. 8, a schematic diagram of a network index cluster analysis is shown. Carrying out failure times, proportion fluctuation of the failure times and TOP analysis on failure codes, network elements and users/terminals of the network index based on the provincial dimension of the network index; carrying out failure times, proportion fluctuation of the failure times and TOP analysis on failure codes, tracking areas and users/terminals of the network indexes based on network element dimensions of the network indexes; failure codes, the number of failures of users/terminals and cells, proportion fluctuation of the number of failures and TOP analysis are carried out on the network index based on the tracking area dimension of the network index.
For example, n may be 7, the preset fluctuation threshold may be 50%, and the case that the number of failures corresponding to the abnormal data information exceeds the preset fluctuation threshold may be that the number of failures of a certain tracking area identifier (TRACING AREA IDENTITY, TAI) is greater than the preset fluctuation threshold by an average value of the first 7 days, the number of failures of an individual user is greater than the preset fluctuation threshold by an average value of the first 7 days, and the number of failures of a certain type of protocol is greater than the preset fluctuation threshold by an average value of the first 7 days, where the empirical library format is shown in table two:
Table II experience library format table
S502, generating an alarm work order based on root causes of generating a plurality of abnormal data information, and distributing the alarm work order to corresponding operation and maintenance personnel.
It is understood that an alert work order may be generated based on the root cause that generated the plurality of abnormal data information and distributed to the corresponding operation and maintenance personnel.
Optionally, the network quality detection system may send the alarm worksheet with abnormal network indexes to relevant units or personnel (i.e. operation and maintenance personnel) for processing according to the rule of dispatching orders and the condition of positioning the root cause, where the alarm worksheet carries information mainly including network type, network element name, network index name, time point, abnormal condition, fluctuation subitem information, positioning the root cause and suggesting processing steps. And then the operation and maintenance personnel process the alarm work order until the alarm is recovered. After the alarm is restored, the operation and maintenance personnel can summarize the processing steps and carry out the receipt according to the fixed format.
Optionally, the root cause and the processing method with clear root cause or receipt verification can be summarized to the experience library one by one, and the receipt result is analyzed and processed through an intelligent algorithm to continuously optimize and update the experience library. Specifically, the system can perform machine learning modeling on the receipt content according to the key fields, automatically analyze the receipt content, output key words to obtain specific reasons and processing steps, and update the experience library. The system supports automatic optimization according to the receipt content and word segmentation result evaluation condition of each time. If the network index belongs to normal fluctuation, an algorithm update and alarm threshold parameter setting adjustment suggestion is provided in the receipt. Therefore, the index detection threshold value is adjusted and optimized, and the alarm effectiveness and root cause positioning accuracy of the system are continuously improved.
In one implementation, as shown in fig. 9, a schematic diagram of the design logic of a network quality detection system is shown. The data may be acquired, preprocessed, and then interfaced with an operation registration or standard worker system to perform rule filtering on the preprocessed data. Before performing KPI detection (including index fluctuation detection and index threshold detection) on the rule-filtered data, parameters are manually input or system default parameters are used for performing KPI detection on the rule-filtered data. Judging whether the data after KPI detection accords with a detection rule, if so, carrying out cluster analysis (comprising fluctuation detection of each statistical item in m statistical items, m being a positive integer) on the data after KPI detection to obtain abnormal data; if not, the data after KPI detection is put into storage, and early warning recovery is carried out. And carrying out abnormal warehousing on the abnormal data, matching the abnormal data with an experience library, and determining the root cause. And after the root cause is determined, KPI alarm is carried out, a KPI alarm work order is dispatched, then the KPI alarm work order is processed, the processing result is summarized, and the work order is returned. And updating the experience library and the parameters according to the returned work order.
The embodiment of the application provides a network quality detection method, which comprises the steps of firstly tracking key performance KPIs of 5GC and IP multimedia system (IP Multimedia Subsystem, IMS) domains in real time, then finding out network indexes with poor quality in time through a perfect algorithm, carrying out cluster analysis by combining various associated data, completing root cause positioning by matching an experience library, and finally dispatching first-line maintenance personnel to implement optimization of the network indexes. The whole system for realizing the method can be divided into data mining, KPI anomaly detection, associated data cluster analysis, experience library matching and other system interaction modules. The method not only realizes the root cause positioning of network index fluctuation alarming and poor quality, but also is communicated with the existing network production system, and comprehensively realizes the full-flow closed-loop management of alarming dispatch, experience library optimization and the like. The system can improve the operation efficiency and is an effective way for promoting the digital transformation work of the core network to fall to the ground. Specifically, the system can realize network index fluctuation alarming according to a custom algorithm and support national network index ranking fluctuation alarming. The index can be refined according to the TAI attribution, and network index statistics of the city and the TAI granularity can be realized. The method supports multidimensional analysis of network element, user number, cell and the like to carry out fluctuation statistics on failure times in network indexes, not only can solve the problems of network element, wireless area and even user or terminal level to optimize the indexes by timely positioning and accurately finding local problems in the network, but also can strengthen end network industry matching, improve network operation efficiency and enhance monitoring sensitivity. The root cause positioning of poor network quality can be realized according to the experience library, so that network optimization and improvement can be accurately and efficiently supported.
The foregoing description of the solution provided by the embodiments of the present application has been mainly presented in terms of a method. To achieve the above functions, it includes corresponding hardware structures and/or software modules that perform the respective functions. Those of skill in the art will readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The embodiment of the application can divide the functional modules of a network quality detection method according to the method example, for example, each functional module can be divided corresponding to each function, and two or more functions can be integrated in one processing module. The integrated modules may be implemented in hardware or in software functional modules. Optionally, the division of the modules in the embodiment of the present application is schematic, which is merely a logic function division, and other division manners may be implemented in practice.
Fig. 10 is a schematic structural diagram of a network quality detecting device according to an embodiment of the present application. As shown in fig. 10, a network quality detecting apparatus 40 is used for improving efficiency of detecting network quality, accuracy of determining network index anomaly problems, for example, for performing a network quality detecting method shown in fig. 3. The network quality detection apparatus 40 includes: an acquisition unit 401, a processing unit 402, and a determination unit 403;
An obtaining unit 401, configured to obtain basic data information corresponding to a target network in a target history period before a target time, where the basic data information includes at least one of the following: equipment operation information, tool operation information and base station operation information;
The processing unit 402 is configured to perform data preprocessing on the basic data information to obtain target data information, where the data preprocessing includes at least one of the following: data detection, data statistics, abnormal data rejection and data format adjustment;
a determining unit 403, configured to determine predicted data information corresponding to a first period after the target time based on the target data information and a preset algorithm;
The determining unit 403 is further configured to determine abnormal data information in the real data information corresponding to the first period based on the predicted data information corresponding to the first period and a difference between the real data information corresponding to the first period.
In a possible implementation manner, the determining unit 403 is further configured to determine, from the target data information, data information corresponding to each of a plurality of first time points included in the target historical time period, where a preset duration is spaced between any two adjacent first time points in the plurality of first time points; the processing unit 402 is further configured to sequentially input data information corresponding to each of the first time points in the plurality of first time points into a preset algorithm according to a time sequence, and obtain predicted data information corresponding to each of the second time points included in the first time period after the target time, where a preset duration is provided between any two adjacent second time points in the plurality of second time points.
In a possible implementation manner, the obtaining unit 401 is further configured to obtain real data information corresponding to each of a plurality of second time points included in the first time period; the determining unit 403 is further configured to determine, for any one of a plurality of second time points included in the first time period, a size relationship between predicted data information and real data information corresponding to the any one second time point; the determining unit 403 is further configured to determine that the real data information corresponding to any one of the second time points is abnormal data information when it is determined that the predicted data information corresponding to any one of the second time points is greater than the real data information and a difference between the predicted data information and the real data information is greater than a preset threshold.
In one possible implementation, each exception data information includes at least one of the following information: location information, network element information, area information, failure code, terminal information; a determining unit 403, configured to perform cluster analysis processing based on the determined plurality of abnormal data information, and determine a root cause for generating the plurality of abnormal data information; the processing unit 402 is further configured to generate an alert work order based on root causes of generating the plurality of abnormal data information, and send the alert work order to corresponding operation and maintenance personnel.
In the case of implementing the functions of the integrated modules in the form of hardware, the embodiment of the present application provides a possible structural schematic diagram of the electronic device involved in the above embodiment. As shown in fig. 11, an electronic device 60 is used for improving the efficiency of detecting network quality and determining the accuracy of network index anomaly problems, for example, for performing a network quality detection method shown in fig. 3. The electronic device 60 comprises a processor 601, a memory 602 and a bus 603. The processor 601 and the memory 602 may be connected by a bus 603.
The processor 601 is a control center of the communication device, and may be one processor or a collective term of a plurality of processing elements. For example, the processor 601 may be a general-purpose central processing unit (central processing unit, CPU), or may be another general-purpose processor. Wherein the general purpose processor may be a microprocessor or any conventional processor or the like.
As one example, processor 601 may include one or more CPUs, such as CPU 0 and CPU 1 shown in fig. 11.
The memory 602 may be, but is not limited to, a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (random access memory, RAM) or other type of dynamic storage device that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
As a possible implementation, the memory 602 may exist separately from the processor 601, and the memory 602 may be connected to the processor 601 through the bus 603 for storing instructions or program codes. The processor 601, when calling and executing instructions or program codes stored in the memory 602, can implement a network quality detection method provided by the embodiment of the present application.
In another possible implementation, the memory 602 may also be integrated with the processor 601.
Bus 603 may be an industry standard architecture (industry standard architecture, ISA) bus, a peripheral component interconnect (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus, or an extended industry standard architecture (extended industry standard architecture, EISA) bus, among others. The bus may be classified as an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 11, but not only one bus or one type of bus.
It should be noted that the structure shown in fig. 11 does not constitute a limitation of the electronic device 60. The electronic device 60 may include more or fewer components than shown in fig. 11, or may combine certain components or a different arrangement of components.
As an example, in connection with fig. 10, the acquisition unit 401, the processing unit 402, and the determination unit 403 in the network quality detection apparatus 40 realize the same functions as those of the processor 601 in fig. 11.
Optionally, as shown in fig. 11, the electronic device 60 provided by the embodiment of the present application may further include a communication interface 604.
Communication interface 604 for connecting with other devices via a communication network. The communication network may be an ethernet, a radio access network, a wireless local area network (wireless local area networks, WLAN), etc. The communication interface 604 may include a receiving unit for receiving data and a transmitting unit for transmitting data.
In one design, the electronic device provided in the embodiment of the present application may further include a communication interface integrated in the processor.
From the above description of embodiments, it will be apparent to those skilled in the art that the foregoing functional unit divisions are merely illustrative for convenience and brevity of description. In practical applications, the above-mentioned function allocation may be performed by different functional units, i.e. the internal structure of the device is divided into different functional units, as needed, to perform all or part of the functions described above. The specific working processes of the above-described systems, devices and units may refer to the corresponding processes in the foregoing method embodiments, which are not described herein.
The embodiment of the application also provides a computer readable storage medium, wherein the computer readable storage medium stores instructions, when the computer executes the instructions, the computer executes each step in the method flow shown in the method embodiment.
Embodiments of the present application provide a computer program product comprising instructions which, when run on a computer, cause the computer to perform a network quality detection method as in the method embodiments described above.
The computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: electrical connections having one or more wires, portable computer diskette, hard disk. Random access memory (random access memory, RAM), read-only memory (ROM), erasable programmable read-only memory (erasable programmable read only memory, EPROM), registers, hard disk, optical fiber, portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any other form of computer-readable storage medium known in the art, as appropriate, or any other combination of the foregoing.
An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. In the alternative, the storage medium may be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuit (ASIC).
In embodiments of the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
Since the electronic device, the computer readable storage medium, and the computer program product in the embodiments of the present application can be applied to the above-mentioned method, the technical effects that can be obtained by the method can also refer to the above-mentioned method embodiments, and the embodiments of the present application are not described herein again.
The present application is not limited to the above embodiments, and any changes or substitutions within the technical scope of the present application should be covered by the scope of the present application.
Claims (8)
1. A method for detecting network quality, the method comprising:
basic data information corresponding to a target network in a target historical time period before a target moment is acquired, and the basic data information is subjected to data preprocessing to obtain target data information, wherein the basic data information comprises at least one of the following items: equipment operation information, tool operation information and base station operation information, wherein the data preprocessing comprises at least one of the following steps: data detection, data statistics, abnormal data rejection and data format adjustment;
Based on the target data information and a preset algorithm, determining predicted data information corresponding to a first time period after the target moment;
Determining abnormal data information in the real data information corresponding to the first time period based on the predicted data information corresponding to the first time period and the difference value between the real data information corresponding to the first time period;
The determining, based on the target data information and a preset algorithm, predicted data information corresponding to a first period of time after the target time includes:
Determining data information corresponding to each first time point in a plurality of first time points included in the target historical time period from the target data information, wherein a preset time length is reserved between any two adjacent first time points in the plurality of first time points;
inputting the data information corresponding to each first time point in the plurality of first time points into the preset algorithm in sequence according to the time sequence, and obtaining the predicted data information corresponding to each second time point in the plurality of second time points included in the first time period after the target time, wherein the preset duration is arranged between any two adjacent second time points in the plurality of second time points.
2. The method according to claim 1, wherein the method further comprises:
Acquiring the real data information corresponding to each second time point in the plurality of second time points included in the first time period;
the determining abnormal data information in the real data information corresponding to the first time period based on the predicted data information corresponding to the first time period and the difference value between the real data information corresponding to the first time period includes:
determining a size relationship between the predicted data information and the real data information corresponding to any one of the plurality of second time points included in the first time period;
And when the predicted data information corresponding to any second time point is determined to be larger than the real data information and the difference value between the predicted data information and the real data information is determined to be larger than a preset threshold value, determining that the real data information corresponding to any second time point is abnormal data information.
3. The method according to claim 1 or 2, wherein each exception data information comprises at least one of the following information: location information, network element information, area information, failure code, terminal information; the method further comprises the steps of:
Performing cluster analysis processing based on the determined plurality of abnormal data information, and determining root causes for generating the plurality of abnormal data information;
and generating an alarm work order based on the root cause of the abnormal data information, and distributing the alarm work order to corresponding operation and maintenance personnel.
4. A network quality detection apparatus, characterized in that the network quality detection apparatus comprises: the device comprises an acquisition unit, a processing unit and a determination unit;
The acquiring unit is configured to acquire basic data information corresponding to a target network in a target history period before a target time, where the basic data information includes at least one of the following: equipment operation information, tool operation information and base station operation information;
the processing unit is configured to perform data preprocessing on the basic data information to obtain target data information, where the data preprocessing includes at least one of the following: data detection, data statistics, abnormal data rejection and data format adjustment;
the determining unit is used for determining prediction data information corresponding to a first time period after the target moment based on the target data information and a preset algorithm;
The determining unit is further configured to determine abnormal data information in the real data information corresponding to the first time period based on the predicted data information corresponding to the first time period and a difference value between the real data information corresponding to the first time period;
The determining unit is further configured to determine, from the target data information, data information corresponding to each of a plurality of first time points included in the target historical time period, where a preset duration is spaced between any two adjacent first time points in the plurality of first time points;
the processing unit is further configured to sequentially input data information corresponding to each first time point in the plurality of first time points into the preset algorithm according to a time sequence, and obtain predicted data information corresponding to each second time point in the plurality of second time points included in the first time period after the target time, where the preset duration is spaced between any two adjacent second time points in the plurality of second time points.
5. The network quality detection apparatus according to claim 4, wherein the acquisition unit is further configured to acquire the real data information corresponding to each of the plurality of second time points included in the first period;
The determining unit is further configured to determine, for any one of the plurality of second time points included in the first time period, a size relationship between the predicted data information and the real data information corresponding to the any one second time point;
The determining unit is further configured to determine that the real data information corresponding to the any second time point is abnormal data information when it is determined that the predicted data information corresponding to the any second time point is greater than the real data information and a difference between the predicted data information and the real data information is greater than a preset threshold.
6. The network quality detection apparatus according to claim 4 or 5, wherein each piece of abnormal data information includes at least one of: location information, network element information, area information, failure code, terminal information; the determining unit is further used for performing cluster analysis processing based on the determined plurality of abnormal data information and determining root causes for generating the plurality of abnormal data information;
The processing unit is further used for generating an alarm work order based on root causes of the abnormal data information and distributing the alarm work order to corresponding operation and maintenance personnel.
7. An electronic device, comprising: a processor and a memory; wherein the memory is configured to store one or more programs, the one or more programs comprising computer-executable instructions that, when executed by the electronic device, cause the electronic device to perform a network quality detection method as claimed in any one of claims 1 to 3.
8. A computer readable storage medium storing one or more programs, wherein the one or more programs comprise instructions, which when executed by a computer, cause the computer to perform a network quality detection method as claimed in any of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211721502.4A CN116074215B (en) | 2022-12-30 | Network quality detection method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211721502.4A CN116074215B (en) | 2022-12-30 | Network quality detection method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116074215A CN116074215A (en) | 2023-05-05 |
| CN116074215B true CN116074215B (en) | 2024-04-19 |
Family
ID=
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004072286A (en) * | 2002-08-05 | 2004-03-04 | Nippon Telegr & Teleph Corp <Ntt> | Method and device for detecting structural change and communication network abnormal state and program |
| CN102821002A (en) * | 2011-06-09 | 2012-12-12 | 中国移动通信集团河南有限公司信阳分公司 | Method and system for network flow anomaly detection |
| EP3590042A1 (en) * | 2017-03-01 | 2020-01-08 | Visa International Service Association | Predictive anomaly detection framework |
| CN110809280A (en) * | 2019-10-21 | 2020-02-18 | 北京锦鸿希电信息技术股份有限公司 | Detection and early warning method and device for railway wireless network quality |
| CN111193608A (en) * | 2019-11-19 | 2020-05-22 | 腾讯云计算（北京）有限责任公司 | Network quality detection monitoring method, device and system and computer equipment |
| CN112637132A (en) * | 2020-12-01 | 2021-04-09 | 北京邮电大学 | Network anomaly detection method and device, electronic equipment and storage medium |
| CN112994965A (en) * | 2019-12-13 | 2021-06-18 | 北京金山云网络技术有限公司 | Network anomaly detection method and device and server |
| CN113079143A (en) * | 2021-03-24 | 2021-07-06 | 北京锐驰信安技术有限公司 | Flow data-based anomaly detection method and system |
| CN113099476A (en) * | 2021-05-13 | 2021-07-09 | 中国联合网络通信集团有限公司 | Network quality detection method, device, equipment and storage medium |
| CN113595784A (en) * | 2021-07-26 | 2021-11-02 | 招商银行股份有限公司 | Network flow detection method, device, equipment, storage medium and program product |
| CN114301803A (en) * | 2021-12-24 | 2022-04-08 | 北京百度网讯科技有限公司 | Network quality detection method and device, electronic equipment and storage medium |
| CN114595134A (en) * | 2022-03-10 | 2022-06-07 | 中国农业银行股份有限公司 | Abnormal data detection method and device, electronic equipment and computer storage medium |
| CN115334559A (en) * | 2022-08-19 | 2022-11-11 | 中国联合网络通信集团有限公司 | Network detection method, device, equipment and medium |
| CN115438885A (en) * | 2021-06-02 | 2022-12-06 | 中移动信息技术有限公司 | Method, device, equipment and storage medium for detecting abnormal fluctuation of service |
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004072286A (en) * | 2002-08-05 | 2004-03-04 | Nippon Telegr & Teleph Corp <Ntt> | Method and device for detecting structural change and communication network abnormal state and program |
| CN102821002A (en) * | 2011-06-09 | 2012-12-12 | 中国移动通信集团河南有限公司信阳分公司 | Method and system for network flow anomaly detection |
| EP3590042A1 (en) * | 2017-03-01 | 2020-01-08 | Visa International Service Association | Predictive anomaly detection framework |
| CN110809280A (en) * | 2019-10-21 | 2020-02-18 | 北京锦鸿希电信息技术股份有限公司 | Detection and early warning method and device for railway wireless network quality |
| CN111193608A (en) * | 2019-11-19 | 2020-05-22 | 腾讯云计算（北京）有限责任公司 | Network quality detection monitoring method, device and system and computer equipment |
| CN112994965A (en) * | 2019-12-13 | 2021-06-18 | 北京金山云网络技术有限公司 | Network anomaly detection method and device and server |
| CN112637132A (en) * | 2020-12-01 | 2021-04-09 | 北京邮电大学 | Network anomaly detection method and device, electronic equipment and storage medium |
| CN113079143A (en) * | 2021-03-24 | 2021-07-06 | 北京锐驰信安技术有限公司 | Flow data-based anomaly detection method and system |
| CN113099476A (en) * | 2021-05-13 | 2021-07-09 | 中国联合网络通信集团有限公司 | Network quality detection method, device, equipment and storage medium |
| CN115438885A (en) * | 2021-06-02 | 2022-12-06 | 中移动信息技术有限公司 | Method, device, equipment and storage medium for detecting abnormal fluctuation of service |
| CN113595784A (en) * | 2021-07-26 | 2021-11-02 | 招商银行股份有限公司 | Network flow detection method, device, equipment, storage medium and program product |
| CN114301803A (en) * | 2021-12-24 | 2022-04-08 | 北京百度网讯科技有限公司 | Network quality detection method and device, electronic equipment and storage medium |
| CN114595134A (en) * | 2022-03-10 | 2022-06-07 | 中国农业银行股份有限公司 | Abnormal data detection method and device, electronic equipment and computer storage medium |
| CN115334559A (en) * | 2022-08-19 | 2022-11-11 | 中国联合网络通信集团有限公司 | Network detection method, device, equipment and medium |
Non-Patent Citations (4)
| Title |
|---|
| "Use of Uncertainty with Autoencoder Neural Networks for Anomaly Detection";Adrien Legrand;《2019 IEEE Second International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)》;20190808;全文 * |
| "人工智能及其在网络优化运维中的应用";王西点;《电信工程技术与标准化》;20180711;全文 * |
| 基于层级实时记忆算法的时间序列异常检测算法;曾惟如;吴佳;闫飞;;电子学报;20180215(第02期);全文 * |
| 基于长短期记忆网络的工控网络异常流量检测;田伟宏;李喜旺;司志坚;;计算机系统应用;20200915(第09期);全文 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111126824B (en) | Multi-index correlation model training method and multi-index anomaly analysis method | |
| CN107204894B (en) | Method and device for monitoring network service quality | |
| CN111475370A (en) | Operation and maintenance monitoring method, device and equipment based on data center and storage medium | |
| CN111176953B (en) | Abnormality detection and model training method, computer equipment and storage medium | |
| CN113313280B (en) | Cloud platform inspection method, electronic equipment and nonvolatile storage medium | |
| CN112769605A (en) | Heterogeneous multi-cloud operation and maintenance management method and hybrid cloud platform | |
| CN112817814A (en) | Abnormity monitoring method, system, storage medium and electronic device | |
| CN112612680A (en) | Message warning method, system, computer equipment and storage medium | |
| CN112214577A (en) | Target user determination method, device, equipment and computer storage medium | |
| CN110807050B (en) | Performance analysis method, device, computer equipment and storage medium | |
| CN112637888B (en) | Coverage hole area identification method, device, equipment and readable storage medium | |
| CN116074215B (en) | Network quality detection method, device, equipment and storage medium | |
| CN110609761B (en) | Method and device for determining fault source, storage medium and electronic equipment | |
| CN116074215A (en) | Network quality detection method, device, equipment and storage medium | |
| CN115271407A (en) | Industrial Internet data processing method and system based on artificial intelligence | |
| CN111935279B (en) | Internet of things network maintenance method based on block chain and big data and computing node | |
| CN112398706B (en) | Data evaluation standard determining method and device, storage medium and electronic equipment | |
| CN113452533A (en) | Charging self-inspection and self-healing method and device, computer equipment and storage medium | |
| CN113051307A (en) | Alarm signal analysis method, equipment, storage medium and device | |
| CN111061795B (en) | Data processing method and device, intelligent terminal and storage medium | |
| CN112561262B (en) | Experience feedback data pushing method applied to barrier analysis and computer terminal | |
| CN113923102B (en) | Method and device for analyzing power supply faults of Internet of things equipment | |
| CN113485886B (en) | Alarm log processing method and device, storage medium and electronic device | |
| CN113342861B (en) | Data management method and device in service scene | |
| WO2023118648A1 (en) | System and method for optimizing fault detection in internet of things network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |