CN111327438A - Alarm data processing method and device and readable medium - Google Patents
Alarm data processing method and device and readable medium Download PDFInfo
- Publication number
- CN111327438A CN111327438A CN201811531988.9A CN201811531988A CN111327438A CN 111327438 A CN111327438 A CN 111327438A CN 201811531988 A CN201811531988 A CN 201811531988A CN 111327438 A CN111327438 A CN 111327438A
- Authority
- CN
- China
- Prior art keywords
- base station
- alarm
- base stations
- determining
- alarm data
- 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.)
- Granted
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
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses an alarm data processing method, an alarm data processing device and a readable medium, wherein the method comprises the following steps: acquiring base station alarm data of a plurality of base stations and dynamic ring alarm data of a plurality of dynamic ring alarm devices; and determining the incidence relation between a plurality of base stations and a plurality of dynamic ring alarm devices according to the base station alarm data, the dynamic ring alarm data and the trained incidence relation model between the base stations and the dynamic ring alarm devices. Therefore, the incidence relation between the base station and the moving ring alarm device is accurately determined, in addition, the incidence relation model is obtained by training the base station alarm data of the base station and the moving ring alarm data of the moving ring alarm device according to the known incidence relation, so the accuracy of the determined incidence relation is further improved, and in addition, the coverage rate of the moving ring alarm device is effectively improved based on the incidence relation.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a method and an apparatus for processing alarm data, and a readable medium.
Background
The dynamic loop monitoring refers to centralized monitoring aiming at power equipment and environment variables in various machine rooms. And the monitoring of the dynamic loop of the base station is a necessary technology for ensuring the normal communication of the network. However, the coverage of the current moving loop is not high enough, so that some base stations do not have moving loop monitoring equipment, and the approximate position of the fault cannot be timely positioned. In order to improve the coverage rate of the moving-ring monitoring equipment, an effective method is to add moving-ring alarm equipment, but the cost is limited.
In the prior art, a base station capable of sharing a moving ring is determined based on base station alarm data and moving ring alarm data, but most of the adopted methods are based on technologies such as a knowledge base of association rules, a data dictionary, statistical analysis and the like, the mining degree is shallow, and the real association between the moving ring alarm and a base station alarm phenomenon cannot be realized, so that the determined association relationship between the base station and moving ring monitoring equipment is not accurate enough, and the coverage rate of the moving ring monitoring equipment is influenced.
Therefore, how to accurately determine the association relationship between the dynamic loop monitoring device and the base station, and further improve the coverage rate of the dynamic loop monitoring device is one of the primary considerations.
Disclosure of Invention
The embodiment of the invention provides an alarm data processing method, an alarm data processing device and a readable medium, which are used for accurately determining the incidence relation between a dynamic loop monitoring device and a base station so as to improve the coverage rate of the dynamic loop monitoring device.
In a first aspect, an embodiment of the present invention provides an alarm data processing method, including:
acquiring base station alarm data of a plurality of base stations and dynamic ring alarm data of a plurality of dynamic ring alarm devices;
determining the incidence relation between a plurality of base stations and a plurality of dynamic ring alarm devices according to the base station alarm data, the dynamic ring alarm data and the trained incidence relation model between the base stations and the dynamic ring alarm devices;
and the incidence relation model is obtained by training base station alarm data of a base station and dynamic ring alarm data of dynamic ring alarm equipment according to known incidence relations.
In a second aspect, an embodiment of the present invention provides an alarm data processing apparatus, including:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring base station alarm data of a plurality of base stations and dynamic ring alarm data of a plurality of dynamic ring alarm devices;
the first determining unit is used for determining the incidence relation between a plurality of base stations and a plurality of dynamic ring alarm devices according to the base station alarm data, the dynamic ring alarm data and the trained incidence relation model between the base stations and the dynamic ring alarm devices;
and the incidence relation model is obtained by training base station alarm data of a base station and dynamic ring alarm data of dynamic ring alarm equipment according to known incidence relations.
In a third aspect, an embodiment of the present invention provides a communication device, including a memory, a processor, and a computer program stored in the memory and executable on the processor; the processor, when executing the program, implements the alarm data processing method as any one of the methods provided herein.
In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps in the alarm data processing method according to any one of the methods provided in this application.
The invention has the beneficial effects that:
the alarm data processing method, the device and the readable medium provided by the embodiment of the invention are used for acquiring the base station alarm data of a plurality of base stations and the dynamic ring alarm data of a plurality of dynamic ring alarm devices; and determining the incidence relation between a plurality of base stations and a plurality of dynamic ring alarm devices according to the base station alarm data, the dynamic ring alarm data and the trained incidence relation model between the base stations and the dynamic ring alarm devices. Therefore, the incidence relation between the base station and the moving ring alarm device is accurately determined, in addition, the incidence relation model is obtained by training the base station alarm data of the base station and the moving ring alarm data of the moving ring alarm device according to the known incidence relation, so the accuracy of the determined incidence relation is further improved, and in addition, the coverage rate of the moving ring alarm device is effectively improved based on the incidence relation.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram illustrating the effect of KB station provided in the embodiment of the present invention;
fig. 2 is a schematic flow chart of an alarm data processing method according to an embodiment of the present invention;
fig. 3 is a second schematic flowchart of an alarm data processing method according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a method for training an association model according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart illustrating a process for determining a base station sample according to an embodiment of the present invention;
fig. 6 is a schematic flowchart of screening out a base station related to an alarm time according to an embodiment of the present invention;
fig. 7 is a schematic flowchart of screening out distance-related base stations according to an embodiment of the present invention;
fig. 8 is a schematic flow chart of determining the euclidean distance between two screened base stations according to an embodiment of the present invention;
fig. 9 is a schematic flowchart of determining a probability related to the number of times of occurrence of an alarm in a base station related to a distance according to an embodiment of the present invention;
FIG. 10 is a schematic flow chart illustrating a process for determining a sample of a moving loop according to an embodiment of the present invention;
fig. 11 is a schematic structural diagram of an alarm data processing apparatus according to an embodiment of the present invention;
fig. 12 is a schematic structural diagram of a communication device according to an embodiment of the present invention.
Detailed Description
The alarm data processing method, the alarm data processing device and the readable medium provided by the embodiment of the invention are used for accurately determining the incidence relation between the dynamic ring monitoring equipment and the base station, so that the coverage rate of the dynamic ring monitoring equipment is improved.
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings of the specification, it being understood that the preferred embodiments described herein are merely for illustrating and explaining the present invention, and are not intended to limit the present invention, and that the embodiments and features of the embodiments in the present invention may be combined with each other without conflict.
To facilitate understanding of the invention, the technical terms involved in the invention are as follows:
KB stations, at least two base stations powered by the same power supply, refer to the schematic diagram of the KB station shown in fig. 1; the invention is beneficial to the existing historical alarm data to carry out the combing and the association on the base station through the machine learning, and introduces the KB station thought by the point-band surface, so that the base station belongs to the KB station controlled by one circuit from the machine room in the physical sense, and the alarm influence range of the moving ring of the base station is expanded, thereby improving the alarm coverage rate of the moving ring of the base station.
For better understanding of the present invention, the alarm scenario is analyzed first, and if the base station belongs to a KB station, the following expressions will occur: (1) the base station in the KB station is disconnected due to power reasons, and all the base stations to which the base station belongs can report a station disconnection alarm at the same time; (2) because the power supply is greatly influenced by regional reasons, two base stations with large regional distances cannot be arranged in one KB station, such as: since region 1 is far from region 2, the base stations in region 1 do not belong to the same KB station as the base stations in region 2.
The following situations exist when all base stations are disconnected and alarm in the macro cellular machine room at the same time:
the first condition is as follows: the emergency battery is not installed in the base station machine room, and when power is interrupted, all machines in the machine room are disconnected at the same time and give an alarm of the disconnection.
Case two: the emergency battery is installed in the base station machine room, when the power is interrupted, the base station sends out a low-voltage alarm, and when the electric quantity of the battery is exhausted, the base station sends out a station-breaking alarm.
Case three: when the transmission of the base station machine room is interrupted, all machines in the machine room are simultaneously disconnected, and a disconnected station alarm is reported.
Case four: the base station is a micro-cell, and when the power supply of the micro-cell is interrupted, the micro-cell directly sends out a station-breaking alarm.
Case five: the macro cell has base station faults at the same time, and has station-breaking alarm (the occurrence probability is low and can be ignored).
As shown in fig. 2, a schematic flow chart of the alarm data processing method provided in the embodiment of the present invention may include the following steps:
and S21, acquiring base station alarm data of a plurality of base stations and dynamic ring alarm data of a plurality of dynamic ring alarm devices.
In this step, the alarm platform bears the alarm data, so the base station alarm data of a plurality of base stations and the dynamic ring alarm data of a plurality of dynamic ring alarm devices can be obtained based on the alarm platform. The invention does not limit the number of the base stations and the number of the dynamic ring alarm devices, for example, the base station alarm data of all the base stations in a city and the dynamic ring alarm data of all the dynamic ring alarm devices can be obtained.
S22, determining the incidence relation between the plurality of base stations and the plurality of moving ring alarm devices according to the base station alarm data, the moving ring alarm data and the trained incidence relation model between the base stations and the moving ring alarm devices.
The incidence relation model in the invention is obtained by training the base station alarm data of the base station and the dynamic ring alarm data of the dynamic ring alarm device according to the known incidence relation.
In the step, the invention can accurately determine the association relationship between the base station and the moving ring alarm device by deeply mining the base station broken alarm data and the moving ring alarm data and outputting the association between the base station and the association between the base station and the moving ring.
Specifically, when step S22 is implemented, data cleaning may be performed on the base station alarm data and the moving ring alarm data, for example, data with a key value of null or a random code and/or a repeated alarm is cleaned and removed, meanwhile, required characters in the base station alarm data and the moving ring alarm data may be normalized, and then the processed base station alarm data and moving ring alarm data are input into the trained association relationship model, where an output result of the association relationship model is a result of whether the base station is associated with the moving ring alarm device, and a result of whether the base station is associated with the moving ring alarm device.
Optionally, the alarm data processing method provided by the present invention further includes a flow shown in fig. 3, which may include the following steps:
and S31, determining the base station sets which belong to the same power supply path and supply power according to the incidence relation.
In this step, based on the result of the association relationship between the base stations, if the value of the association relationship between any two base stations is greater than the preset threshold, it indicates that the two base stations are related and belong to the same power supply.
S32, determining a first base station configured with the dynamic loop warning device and a second base station not configured with the dynamic loop warning device in the base station set.
Specifically, the result of whether the base station is configured with the moving loop alarm device is obtained in advance, and in the field construction process, which base station is configured with the moving loop alarm device is planned in advance, so that the first base station configured with the moving loop alarm device and the second base station not configured with the moving loop alarm device can be accurately determined from the base station set.
S33, determining that the second base station and the first base station share the dynamic loop warning equipment of the first base station.
Because the first base station and the second base station share one power supply, the moving-ring alarm device of the first base station can be reused for the second base station.
Optionally, the association relationship between the base station and the moving ring alarm device in the invention includes the association relationship between the base station and the association relationship between the base station and the moving ring alarm device, a topology structure diagram can be constructed based on the association relationship, then whether the base station and the base station are controlled by the same route power supply can be found based on the topology structure diagram, if the base station is found to be controlled by the same route power supply, the moving ring alarm device of the base station with the moving ring alarm in the base station set can be reused for the base station without the moving ring alarm, and finally the moving ring alarm coverage rate is improved.
Next, a training process of an association relationship model between the base station and the moving loop alarm device will be described.
As shown in fig. 4, a flowchart of a method for training an association relationship model according to base station alarm data of a base station and dynamic ring alarm data of dynamic ring alarm equipment, which are known in association relationship, provided by the embodiment of the present invention may include the following steps:
and S41, determining base station samples for representing alarm association relation between the base stations according to the base station alarm data of the base stations.
Specifically, base station alarm data and moving ring alarm data in 2G, 3G and 4G preset time periods may be obtained from the alarm platform, where the base station alarm data may be base station outage alarm data, and the preset actual period may be one year. In order to reduce the calculation workload, key cell IDs, base station names, machine room names, alarm occurrence time, alarm ending time and the like can be extracted from the alarm data to serve as the base station alarm data, and the extraction process of the dynamic ring alarm data is similar.
Optionally, in order to train the association relationship model better, data cleaning and the like may be performed on the alarm data, and then the association relationship model may be trained based on the cleaned base station alarm data and the dynamic ring alarm data.
Optionally, the base station alarm data in the present invention includes alarm occurrence time and location information of the base station; then the base station sample for characterizing the alarm association relationship between the base station and the base station may be determined according to the method shown in fig. 5, which includes the following steps:
and S51, screening out the base stations related to the alarm time according to the alarm occurrence time of the plurality of base stations.
In this step, for the base station alarm data, only the alarm data of all base stations in a certain base station room reporting the station-breaking alarm at the same time is screened according to the characteristic that the station-breaking alarm can be reported at the same time when the base station is powered off, and the alarm data is considered to be the station-breaking alarm data of the base station caused by the power-off.
Optionally, for each two base stations in the plurality of base stations, the method shown in fig. 6 may be used to screen out the base stations related to the alarm time, including the following steps:
and S61, determining the alarm time difference of the two base stations according to the alarm occurrence time of the two base stations.
In this step, 8 content analysis feature values in the base station alarm data are selected to form a base station alarm data set X ═ (X1, X2, X3, X4, X5, X6, X7, and X8), where: referring to table 1, x1 to x8 are respectively expressed as:
TABLE 1
| x 1: cell number | x 5: base station longitude |
| x 2: name of base station | x 6: base station longitude |
| x 3: name of machine room | x 7: type of alarm |
| x 4: time of occurrence of alarm | x 8: base station affiliated maintenance area |
In table 1, the alarm type may be, but is not limited to, a 2g alarm, a 4g alarm, or an engineering alarm. The maintenance areas to which the base stations belong may be, for example, city one company and city two company, etc.
Explaining by taking each alarm of the base station as a dimension, aiming at the alarm data of each base station in the set, taking the base station as ne based on the alarm data set of the base stationaFor example, determine the base station neaAnd the base station ne is removed from the alarm data set of the base stationaOther than alarm time difference between each base station, e.g. other than the base station neaEach other base station is nebFor illustration, base station neaAnd base station nebDetermining the alarm occurrence time in the alarm data of the base stationaAnd base station nebThe difference between the alarm times is recorded as Tb,a＝Tb-Ta。
And S62, if the alarm time difference is smaller than the preset time difference threshold value, determining that the two base stations are the base stations related to the alarm time.
In this step, the preset time difference threshold is taken as δ for explanation, and if T is determinedb,aIf delta is less than the value of base station neaAnd base station nebThe base station alarm data may be reported aiming at the same alarm event, which indicates the base station neaAnd base station nebThe correlation between them is true, i.e. base station neaAnd base station nebPossibly KB stations. If Tb,aIf the value is more than or equal to delta, the base station ne is indicatedaAnd base station nebUncorrelated, possibly noisy points.
Specifically, in the present inventionδ may be adjusted according to actual conditions to obtain more accurate clustering result, for example, δ in the present invention may be but not limited to 120S, etc., and by implementing steps S61 and S62, base station ne may be obtainedaAnd a series of base stations with base station disconnection alarms within 120s after the station disconnection occurs.
Based on the method, the base stations related to the alarm time can be screened out from the alarm data set of the base stations. For example, for convenience of subsequent description, the base stations related to the alarm time may form a time-related base station set T.
And S52, screening the base stations related to the distance based on the position information of the screened base stations.
In this step, distance-related base stations are screened out from the time-related base station set T, aiming at determining time-related and distance-related base stations.
Specifically, step S52 may be implemented according to the flow shown in fig. 7 for each two base stations in the screened base stations, and includes the following steps:
and S71, determining the Euclidean distance between the two screened base stations based on the position information of the two screened base stations.
Alternatively, the euclidean distance in step S71 may be a straight line distance or an actual straight line distance, or the like.
Optionally, the location information of the base station in the present invention includes a latitude and an absolute longitude of the base station; step S71 may be implemented according to the flow shown in fig. 8, including the following steps:
and S81, determining the deflection angle between the two base stations according to the latitude and the absolute longitude of the two base stations.
Specifically, the deflection angle between two base stations can be determined according to formula (1) for base station neaAnd base station nebFor illustration, base station neaAnd base station nebAngle of deflection C betweenb,aThe expression of (a) is:
Cb,a＝sin(LatA)*sin(LatB)+cos(LatA)*cos(LatB)*cos(MLonA-MLonB) (1)
in formula (1), LatA is the base station ne of the two base stationsaOf two base stations, LatB is base station nebDimension (d); MLonA is base station ne of two base stationsaIs the base station ne of the two base stations, MLonBbAbsolute longitude of (c).
And S82, determining the Euclidean distance between the two base stations according to the formula (2) according to the deflection angle and the radius of the earth.
D＝R*arccos(Cb,a)*π/180 (2)
R is the radius of the earth, and the value of R is 6371004 meters;
d is the euclidean distance between two base stations.
The base station ne can be determined by using the formulas (1) and (2)aAnd base station nebHas a Euclidean distance D betweena,b。
And S72, if the Euclidean distance is determined to be larger than a preset Euclidean distance threshold value, determining that the two screened base stations are determined to be the base stations related to the distance.
Specifically, the preset euclidean distance threshold in the present invention may be represented by θ, and the threshold may be adjusted according to actual conditions in order to obtain a better clustering result. Taking the preset euclidean distance threshold θ of 1000 meters as an example, if D is determineda,bIf theta is less than theta, then station ne is indicatedaAnd base station nebThe distance is relatively short, and the base stations belong to distance-related base stations; otherwise base station neaAnd base station nebUncorrelated, possibly noisy points.
Based on this, the distance-related base stations can be determined from the time-related base station set, and for convenience of subsequent description, the distance-related base stations screened from the time-related base station set T form a distance-related base station set M, and the base stations in the distance-related base station set M satisfy both time correlation and distance correlation.
And S53, determining the alarm occurrence frequency correlation probability in the distance-related base station based on the distance-related base station.
Alternatively, for each base station related to the distance, step S53 may be implemented according to the flow shown in fig. 9, including the following steps:
and S91, determining the alarm frequency of the base station based on the base station alarm data of the base station.
In this step, each base station in the distance-dependent base station set M formed based on the distance-dependent base stations takes the base station as neaFor example, the alarm occurrence times of the base station and each base station in the alarm data set X of the base station, that is, the alarm occurrence times of the base station that alarms, may be determined and recorded as
Wherein n is the number of base stations in the alarm data set X of the base station.
And S92, determining the times of the related alarms in the alarms of the base station and other base stations related to the distance.
In this step, the base station ne in the distance-dependent base station set M can be determinedaAnd the base station ne in the setaOther base stations than that (in ne)bFor example) the number of alarms associated among the alarms occurring is noted
Wherein m is the number of base stations in the distance-dependent base station set minus 1.
S93, determining the ratio of the related alarm times and the alarm times of the base station as the alarm occurrence time correlation probability between the base station and the other base stations.
In this step, the base station ne can be determined by the following formulaaWith said other base stations nebThe probability ρ of the alarm occurrence times correlation therebetweena,b：ρa,b＝CNTa,b/CNTa。
And S54, determining the base station with the occurrence frequency correlation probability larger than the preset probability threshold value as the base station sample.
In this step, if rho is determineda,bIf the probability is greater than the preset probability threshold, the base station ne is determinedaRelating to the base station neb, it can be regarded as the final set of base station samples with correlation, denoted as R, and R ═ R (R1, R2, R3, R4, R2)5, R6, R7), wherein, referring to table 2, table 2 lists the meanings of R1 to R7:
TABLE 2
Thus, a base station set of base stations related to each base station in the distance-related set M can be determined, and then each base station set constitutes a base station sample.
Optionally, in order to better output the association relationship between the base station and the moving ring alarm device, the base station sample may be further screened, and specifically, the base station alarm data of each base station in the base station sample may be compared with the complaint work order to eliminate the alarm caused by the transmission reason, and finally, the base station sample used for characterizing the alarm association relationship between the base station and the base station is determined.
And S42, determining a dynamic loop sample for representing the alarm association relationship between the base station and the base station with dynamic loop alarm according to the base station alarm data of the base stations and the dynamic loop alarm data of the dynamic loop alarm devices.
Optionally, the base station alarm data in the present invention includes a first alarm occurrence time and location information of the base station; the moving loop alarm data includes second alarm occurrence time of the base station with the moving loop, position information of the base station with the moving loop, and the like.
Specifically, for the moving loop alarm data, the interference of equipment faults and other influencing factors of the moving loop alarm data is eliminated, and only the data with the three-phase voltage of 0V and the low-voltage alarm of less than 50V is selected, and the time is considered to be the moving loop alarm data generated by power failure.
On the basis, the moving loop sample can be determined according to the method shown in fig. 10, and the method comprises the following steps:
s101, determining a base station related to alarm time according to first alarm occurrence time of the base station with the base station alarm data and second alarm occurrence time of the base station with the dynamic ring.
Specifically, 8 analysis feature values in the dynamic ring alarm data are selected to form a dynamic ring alarm data set P, where P ═ (P1, P2, P3, P4, P5, P6, P7, and P8), as shown in reference table 3, table 3 lists the meanings of P1 to P8:
TABLE 3
In table 3, the alarm type may be, but is not limited to, a 2g alarm, a 4g alarm, or an engineering alarm. The maintenance areas to which the base stations belong may be, for example, city one company and city two company, etc.
In this step, each alarm of the dynamic ring is taken as a dimension, and the base station to which the alarm of the dynamic ring belongs is set as necThe base station necBelongs to the set P, and determines the base station necAnd the base station related to the alarm time in the alarm data set X of the base station.
Specifically, when determining the relevant base station in step S101, the process executed may refer to the flow in fig. 6, and the specific process is:
determine the base station necWith base station ne in base station alarm data set XdThe alarm time difference between the formed base station data pairs is marked as Tc,dAnd the expression is: t isc,d＝Td-TcWherein, TdIs a base station nedFirst alarm occurrence time, TcIs a base station necTime of occurrence of the second alarm.
Taking the preset difference threshold value of α as an example, if T is determinedc,d< α, this indicates the base station necAnd base station nedThe base station alarm data may be reported aiming at the same alarm event, which indicates the base station necAnd base station nedThe correlation between them is true, i.e. base station necAnd base station nedPossibly KB stations.If Tc,dIf > α, it indicates the base station necAnd base station nedUncorrelated, possibly noisy points.
Specifically, α in the present invention can be adjusted according to actual conditions to obtain more accurate clustering result, for example, α in the present invention can be, but is not limited to 120s, etc., and by implementing the process of determining the time-dependent base station, the base station ne can be obtainedcAnd a series of base stations with base station disconnection alarms within 120s after the station disconnection occurs.
Based on the method, a base station alarm data set and a dynamic ring alarm data set can be determined, and a base station related to alarm time can be determined. For example, for convenience of subsequent description, the base stations related to the alarm time may form a time-related moving loop-base station set K.
S102, based on the position information of the screened base stations, the base stations related to the distance are screened out.
In this step, a distance-related base station is screened out from the time-related moving loop-base station set K, aiming at determining a time-related and distance-related base station.
Specifically, step S102 may be implemented according to the flow of fig. 7, and the general process is as follows:
base station ne exists in time-dependent dynamic ring-base station set KcAnd base station nedFor illustration, the dynamic ring alarm data includes the base station necPosition information of, base station nedThe base station alarm data includes location information, which may be, but not limited to, longitude and latitude and absolute longitude and latitude, and the base station ne may be determined according to a formulacAnd base station nedAngle of deflection C betweenc,d，Cc,dThe expression of (a) is: cc,dSin (LatC) sin (latd) + cos (LatC) cos (MLonC-MLonD), where LatC is one of the two bss necOf the two base stations, LatD is base station nedDimension (d); MLonC is base station ne of two base stationscIs the base station ne of the two base stations, MLonddAbsolute longitude of (c).
On the basis of the formula Dc,d＝R*arccos(Cc,d) Pi/180 determination of base station necAnd base station nedThe euclidean distance between them.
The euclidean distance threshold value of β is taken as an example for explanation, and the threshold value can be adjusted according to actual conditions in order to obtain better clustering results, and the euclidean distance threshold value θ is taken as an example of 1000 meters, and if D is determinedc,d< β, this indicates station necAnd base station nedThe distance is relatively short, and the base stations belong to distance-related base stations; otherwise base station necAnd base station nedUncorrelated, possibly noisy points.
Based on this, a distance-related base station can be determined from the time-related moving ring-base station set K, and for convenience of subsequent description, a distance-related base station set G is formed by the moving ring-base stations, which are selected from the time-related moving ring-base station set K and are related to the distance, and the base stations in the distance-related moving ring-base station set G satisfy both time correlation and distance correlation.
S103, based on the distance-related base stations, determining the related probability of the alarm occurrence times in the distance-related base stations.
Specifically, the process can be implemented by referring to the flow shown in fig. 9, and the general process is as follows:
based on each base station in the distance-dependent moving ring-base station set G, taking the base station as necFor illustration, the base station ne may be determinedcThe alarm occurrence frequency of each base station in the alarm data set X of the base station, namely the alarm occurrence frequency of the base station alarm is recorded as
Wherein g is the number of base stations in the alarm data set X of the base station.
Secondly, the base station ne in the distance-dependent moving-ring-base station set G can be determinedcAnd the base station ne in the setcOther base stations than that (in ne)dFor example) the number of alarms associated among the alarms occurring is noted
Wherein h is the number of base stations in the distance-dependent base station set minus 1.
At the moment of determining CNTcAnd CNTc,dThereafter, the base station ne can be determined by the following formulacWith said other base stations nedThe probability ρ of the alarm occurrence times correlation therebetweenc,d：ρc,d＝CNTc,d/CNTc。
And S104, determining the base station with the occurrence frequency correlation probability larger than a preset probability threshold value as a moving loop sample.
If it is determined that rho is determinedc,dIf the probability is greater than the preset probability threshold, the base station ne is determinedcAnd base station nedThe correlation can be regarded as a set of base station samples having final correlation, denoted as S, and S ═ S (S1, S2, S3, S4, S5, S6, S7), where table 4 refers to table 4, where the meanings of S1 to S7 are listed in table 4:
TABLE 4
| S1: base station ne with correlationc | S5: alarm occurrence frequency correlation probability rhoc,d |
| S2: base station ne with correlationd | S6: base station necMaintenance area |
| S3: alarm time difference Tc,d | S7: base station nedMaintenance area |
| S4: euclidean distance Dc,d |
Therefore, a base station set of base stations related to each base station in the distance-related moving ring-base station set G can be determined, and then each base station set forms a moving ring sample.
Optionally, in order to better output the association relationship between the base station and the moving loop alarm device, the moving loop sample may be further screened, specifically, the base station alarm data of each base station in the moving loop sample may be compared with the complaint work order to eliminate the alarm caused by the transmission reason, and finally, the moving loop sample used for characterizing the alarm association relationship between the base station and the base station having the moving loop alarm is determined.
And S43, training a random forest learning machine by using the base station sample and the moving loop sample to obtain the incidence relation model.
Specifically, a base station sample and a moving loop sample are input into a random forest learning machine, and a decision tree in a random forest is trained, so that a decision tree model of the incidence relation between the base station and the moving loop, namely, the incidence relation model in the invention, can be obtained through training.
Optionally, the method provided by the present invention may be applied to a gateway center and each company network, then verify the output result of the association relation model, output a verification report and a use result, and adjust the input base station sample and the moving loop sample based on the verification report and the use result, so that the result is more accurate.
The alarm data processing method provided by the invention obtains base station alarm data of a plurality of base stations and dynamic ring alarm data of a plurality of dynamic ring alarm devices; and determining the incidence relation between a plurality of base stations and a plurality of dynamic ring alarm devices according to the base station alarm data, the dynamic ring alarm data and the trained incidence relation model between the base stations and the dynamic ring alarm devices. Therefore, the incidence relation between the base station and the moving ring alarm device is accurately determined, in addition, the incidence relation model is obtained by training the base station alarm data of the base station and the moving ring alarm data of the moving ring alarm device according to the known incidence relation, so the accuracy of the determined incidence relation is further improved, and in addition, the coverage rate of the moving ring alarm device is effectively improved based on the incidence relation.
Based on the same inventive concept, the embodiment of the present invention further provides an alarm data processing apparatus, and because the principle of the apparatus for solving the problem is similar to the alarm data processing method, the implementation of the apparatus may refer to the implementation of the method, and repeated details are not repeated.
As shown in fig. 11, a schematic structural diagram of an alarm data processing apparatus provided in an embodiment of the present invention includes:
an obtaining unit 111, configured to obtain base station alarm data of multiple base stations and dynamic ring alarm data of multiple dynamic ring alarm devices;
a first determining unit 112, configured to determine, according to the base station alarm data, the dynamic ring alarm data, and a trained association relationship model between a base station and a dynamic ring alarm device, an association relationship between multiple base stations and multiple dynamic ring alarm devices;
and the incidence relation model is obtained by training base station alarm data of a base station and dynamic ring alarm data of dynamic ring alarm equipment according to known incidence relations.
Optionally, the apparatus further comprises:
a second determining unit 113, configured to determine, according to the association relationship, a set of base stations that belong to the same power supply; determining a first base station configured with a dynamic ring alarm device and a second base station not configured with the dynamic ring alarm device in the base station set; and determining that the second base station and the first base station share the dynamic ring alarm equipment of the first base station.
Optionally, the apparatus further comprises:
a model training unit 114, configured to determine, according to base station alarm data of multiple base stations, a base station sample for characterizing an alarm association relationship between the base stations; determining a moving loop sample for representing the alarm association relationship between the base station and the base station with moving loop alarm according to the base station alarm data of the base stations and the moving loop alarm data of the moving loop alarm devices; and training a random forest learning machine by using the base station sample and the moving loop sample to obtain the incidence relation model.
Optionally, the base station alarm data includes alarm occurrence time and location information of the base station; then
The model training unit 114 is specifically configured to screen out base stations related to alarm time according to the alarm occurrence time of the plurality of base stations; screening base stations relevant to the distance based on the position information of the screened base stations; determining the alarm occurrence frequency correlation probability in the distance-related base station based on the distance-related base station; and determining the base station with the occurrence frequency correlation probability larger than a preset probability threshold value as a base station sample.
Optionally, the model training unit 114 is specifically configured to perform the following processes for each two base stations in the plurality of base stations: determining the alarm time difference of the two base stations according to the alarm occurrence time of the two base stations; and if the alarm time difference is smaller than the preset time difference threshold value, determining that the two base stations are the base stations related to the alarm time.
Optionally, the model training unit 114 is specifically configured to perform the following processes for each two base stations of the screened multiple base stations: determining the Euclidean distance between the two screened base stations based on the position information of the two screened base stations; and if the Euclidean distance is determined to be larger than a preset Euclidean distance threshold value, determining that the two screened base stations are determined to be the base stations related to the distance.
Optionally, the location information of the base station includes a latitude and an absolute longitude of the base station; then
The model training unit 114 is specifically configured to determine a deflection angle between the two base stations according to the latitude and the absolute longitude of the two base stations; determining the Euclidean distance between the two base stations according to the deflection angle and the radius of the earth according to the following formula:
D＝R*arccos(C)*π/180
where C is a deflection angle between two base stations, and the expression of C is: c ═ sin (lata) · sin (latb) + cos (lata) · cos (MLonA-MLonB);
LatA is the base station ne of the two base stationsaOf two base stations, LatB is base station nebDimension (d);
MLonA is base station ne of two base stationsaIs the base station ne of the two base stations, MLonBbAbsolute longitude of (d);
r is the radius of the earth;
d is the euclidean distance between two base stations.
Optionally, the model training unit 114 is specifically configured to perform the following process for each base station related to the distance: determining the alarm frequency of the base station for alarm based on the base station alarm data of the base station; determining the times of related alarms in the alarms of the base station and other base stations related to the distance; and determining the ratio of the related alarm times to the alarm times of the base station as the alarm occurrence time correlation probability between the base station and the other base stations.
Optionally, the base station alarm data includes a first alarm occurrence time and location information of the base station; the dynamic ring alarm data comprises second alarm occurrence time of a base station with a dynamic ring and position information of the base station with the dynamic ring; then
The model training unit 114 is specifically configured to determine a base station related to an alarm time according to a first alarm occurrence time of a base station with base station alarm data and a second alarm occurrence time of the base station with a moving loop; screening base stations relevant to the distance based on the position information of the screened base stations; determining the alarm occurrence frequency correlation probability in the distance-related base station based on the distance-related base station; and determining the base station with the occurrence frequency correlation probability larger than a preset probability threshold value as a dynamic loop sample.
For convenience of description, the above parts are separately described as modules (or units) according to functional division. Of course, the functionality of the various modules (or units) may be implemented in the same or in multiple pieces of software or hardware in practicing the invention.
Based on the same technical concept, the embodiment of the present application further provides a communication device, which can implement the method in the foregoing embodiment.
Referring to fig. 12, a schematic structural diagram of a communication device according to an embodiment of the present invention is shown in fig. 12, where the communication device may include: a processor 1201, a memory 1202, a transceiver 1203, and a bus interface.
The processor 1201 is responsible for managing a bus architecture and general processing, and the memory 1202 may store data used by the processor 1201 in performing operations. The transceiver 1203 is configured to receive and transmit data under the control of the processor 1201.
The bus architecture may include any number of interconnected buses and bridges, with one or more processors, represented by the processor 1201, and various circuits, represented by the memory 1202, being linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. The bus interface provides an interface. The processor 1201 is responsible for managing a bus architecture and general processing, and the memory 1202 may store data used by the processor 1201 in performing operations.
The process disclosed by the embodiment of the invention can be applied to the processor 1201, or can be implemented by the processor 1201. In implementation, the steps of the signal processing flow may be implemented by integrated logic circuits of hardware or instructions in the form of software in the processor 1201. The processor 1201 may be a general purpose processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or the like that may implement or perform the methods, steps, and logic blocks disclosed in embodiments of the present invention. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the alarm data processing method disclosed by the embodiment of the invention can be directly embodied as the execution of a hardware processor, or the combination of hardware and software modules in the processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in the memory 1202, and the processor 1201 reads information in the memory 1202 and completes the steps of the signal processing flow in conjunction with hardware thereof.
Specifically, the processor 1201 is configured to read a program in a memory and execute any step of any one of the methods described above.
Based on the same technical concept, the embodiment of the application also provides a computer storage medium. The computer-readable storage medium stores computer-executable instructions for causing the computer to perform any of the steps of any of the methods described above.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (14)
1. An alarm data processing method, characterized by comprising:
acquiring base station alarm data of a plurality of base stations and dynamic ring alarm data of a plurality of dynamic ring alarm devices;
determining the incidence relation between a plurality of base stations and a plurality of dynamic ring alarm devices according to the base station alarm data, the dynamic ring alarm data and the trained incidence relation model between the base stations and the dynamic ring alarm devices;
and the incidence relation model is obtained by training base station alarm data of a base station and dynamic ring alarm data of dynamic ring alarm equipment according to known incidence relations.
2. The method of claim 1, further comprising:
determining a base station set which belongs to the same power supply path and supplies power according to the incidence relation;
determining a first base station configured with a dynamic ring alarm device and a second base station not configured with the dynamic ring alarm device in the base station set;
and determining that the second base station and the first base station share the dynamic ring alarm equipment of the first base station.
3. The method according to claim 1 or 2, characterized in that the association model is trained on the base station alarm data of base stations and the dynamic loop alarm data of dynamic loop alarm devices whose association is known according to the following method:
determining a base station sample for representing the alarm association relationship between the base stations according to the base station alarm data of the base stations;
determining a moving loop sample for representing the alarm association relationship between the base station and the base station with moving loop alarm according to the base station alarm data of the base stations and the moving loop alarm data of the moving loop alarm devices;
and training a random forest learning machine by using the base station sample and the moving loop sample to obtain the incidence relation model.
4. The method of claim 3, wherein the base station alarm data includes alarm occurrence time and location information of a base station; then
Determining a base station sample for representing the alarm association relationship between the base stations according to the base station alarm data of the base stations, which specifically comprises the following steps:
screening out base stations related to alarm time according to the alarm occurrence time of the base stations;
screening base stations relevant to the distance based on the position information of the screened base stations;
determining the alarm occurrence frequency correlation probability in the distance-related base station based on the distance-related base station;
and determining the base station with the occurrence frequency correlation probability larger than a preset probability threshold value as a base station sample.
5. The method of claim 4, wherein the step of screening out the base stations related to the alarm time according to the alarm occurrence time of the plurality of base stations comprises:
for each two of the plurality of base stations, performing the following:
determining the alarm time difference of the two base stations according to the alarm occurrence time of the two base stations;
and if the alarm time difference is smaller than the preset time difference threshold value, determining that the two base stations are the base stations related to the alarm time.
6. The method of claim 4, wherein the step of screening the base stations related to the distance based on the location information of the screened base stations comprises:
for each two base stations in the screened base stations, the following processes are executed:
determining the Euclidean distance between the two screened base stations based on the position information of the two screened base stations;
and if the Euclidean distance is determined to be larger than a preset Euclidean distance threshold value, determining that the two screened base stations are determined to be the base stations related to the distance.
7. The method of claim 6, wherein the location information of the base station comprises a latitude and an absolute longitude of the base station; then
Based on the position information of the two screened base stations, determining the Euclidean distance between the two screened base stations, which specifically comprises the following steps:
determining a deflection angle between the two base stations according to the latitude and the absolute longitude of the two base stations;
determining the Euclidean distance between the two base stations according to the deflection angle and the radius of the earth according to the following formula:
D＝R＊arccos(C)*π/180
wherein C is the deflection angle between two base stations, and the expression of C is C ═ sin (lata) ＊ sin (latb) + cos (lata) ＊ cos (latb) ＊ cos (MLonA-MLonB);
LatA is the base station ne of the two base stationsaOf two base stations, LatB is base station nebDimension (d);
MLonA is base station ne of two base stationsaIs the base station ne of the two base stations, MLonBbAbsolute longitude of (d);
r is the radius of the earth;
d is the euclidean distance between two base stations.
8. The method of claim 7, wherein determining the probability associated with the number of times of occurrence of an alarm in the distance-dependent base station based on the distance-dependent base station specifically comprises:
for each base station that is distance dependent, the following procedure is performed:
determining the alarm frequency of the base station for alarm based on the base station alarm data of the base station;
determining the times of related alarms in the alarms of the base station and other base stations related to the distance;
and determining the ratio of the related alarm times to the alarm times of the base station as the alarm occurrence time correlation probability between the base station and the other base stations.
9. The method of claim 3, wherein the base station alarm data includes a first alarm occurrence time and location information of a base station; the dynamic ring alarm data comprises second alarm occurrence time of a base station with a dynamic ring and position information of the base station with the dynamic ring; then
Determining a moving loop sample for representing the alarm association relationship between the base station and the base station with the moving loop alarm according to the base station alarm data of the base stations and the moving loop alarm data of the moving loop alarm devices, which specifically comprises the following steps:
determining a base station related to alarm time according to first alarm occurrence time of a base station with base station alarm data and second alarm occurrence time of the base station with a moving ring;
screening base stations relevant to the distance based on the position information of the screened base stations;
determining the alarm occurrence frequency correlation probability in the distance-related base station based on the distance-related base station;
and determining the base station with the occurrence frequency correlation probability larger than a preset probability threshold value as a dynamic loop sample.
10. An alarm data processing apparatus, comprising:
the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring base station alarm data of a plurality of base stations and dynamic ring alarm data of a plurality of dynamic ring alarm devices;
the first determining unit is used for determining the incidence relation between a plurality of base stations and a plurality of dynamic ring alarm devices according to the base station alarm data, the dynamic ring alarm data and the trained incidence relation model between the base stations and the dynamic ring alarm devices;
and the incidence relation model is obtained by training base station alarm data of a base station and dynamic ring alarm data of dynamic ring alarm equipment according to known incidence relations.
11. The apparatus of claim 10, further comprising:
the second determining unit is used for determining the base station sets which belong to the same power supply and supply power according to the incidence relation; determining a first base station configured with a dynamic ring alarm device and a second base station not configured with the dynamic ring alarm device in the base station set; and determining that the second base station and the first base station share the dynamic ring alarm equipment of the first base station.
12. The apparatus of claim 10 or 11, further comprising:
the model training unit is used for determining a base station sample for representing the alarm association relationship between the base stations according to the base station alarm data of the base stations; determining a moving loop sample for representing the alarm association relationship between the base station and the base station with moving loop alarm according to the base station alarm data of the base stations and the moving loop alarm data of the moving loop alarm devices; and training a random forest learning machine by using the base station sample and the moving loop sample to obtain the incidence relation model.
13. A communication device comprising a memory, a processor and a computer program stored on the memory and executable on the processor; characterized in that the processor implements the alarm data processing method according to any one of claims 1 to 9 when executing the program.
14. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, carries out the steps of the alarm data processing method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811531988.9A CN111327438B (en) | 2018-12-14 | 2018-12-14 | Alarm data processing method and device and readable medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811531988.9A CN111327438B (en) | 2018-12-14 | 2018-12-14 | Alarm data processing method and device and readable medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111327438A true CN111327438A (en) | 2020-06-23 |
| CN111327438B CN111327438B (en) | 2022-08-23 |
Family
ID=71170264
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811531988.9A Active CN111327438B (en) | 2018-12-14 | 2018-12-14 | Alarm data processing method and device and readable medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111327438B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115083166A (en) * | 2022-07-14 | 2022-09-20 | 深圳市维力谷无线技术股份有限公司 | Vehicle-road communication testing system and method based on 5G technology |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101242549A (en) * | 2007-11-22 | 2008-08-13 | 中国移动通信集团山东有限公司 | Neutral network construction method for communication network alarm association |
| CN102075344A (en) * | 2009-11-20 | 2011-05-25 | 中国移动通信集团北京有限公司 | Work order distributing method and alarm information filtering device in communication network |
| CN102082616A (en) * | 2009-11-30 | 2011-06-01 | 中国移动通信集团河北有限公司 | Locating maintenance method, device and system |
| CN104125087A (en) * | 2013-04-28 | 2014-10-29 | 中国移动通信集团设计院有限公司 | Alarm information processing method and device |
| CN104254095A (en) * | 2013-06-25 | 2014-12-31 | 中国移动通信集团设计院有限公司 | Method and device for positioning transmission fault causing large-scale base station service failure |
| CN105049253A (en) * | 2015-07-28 | 2015-11-11 | 浪潮通信信息系统有限公司 | Method for obtaining mobile network fault location and fault early warning |
| CN204967427U (en) * | 2015-09-21 | 2016-01-13 | 北京宏光星宇科技发展有限公司 | Based on stock basic station direct current remote power supply system |
| CN106685736A (en) * | 2017-02-13 | 2017-05-17 | 中国联合网络通信集团有限公司 | Method and device for determining the fault base station of correlation failure |
| WO2018170866A1 (en) * | 2017-03-24 | 2018-09-27 | 深圳中兴力维技术有限公司 | Data acquisition method and apparatus |
-
2018
- 2018-12-14 CN CN201811531988.9A patent/CN111327438B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101242549A (en) * | 2007-11-22 | 2008-08-13 | 中国移动通信集团山东有限公司 | Neutral network construction method for communication network alarm association |
| CN102075344A (en) * | 2009-11-20 | 2011-05-25 | 中国移动通信集团北京有限公司 | Work order distributing method and alarm information filtering device in communication network |
| CN102082616A (en) * | 2009-11-30 | 2011-06-01 | 中国移动通信集团河北有限公司 | Locating maintenance method, device and system |
| CN104125087A (en) * | 2013-04-28 | 2014-10-29 | 中国移动通信集团设计院有限公司 | Alarm information processing method and device |
| CN104254095A (en) * | 2013-06-25 | 2014-12-31 | 中国移动通信集团设计院有限公司 | Method and device for positioning transmission fault causing large-scale base station service failure |
| CN105049253A (en) * | 2015-07-28 | 2015-11-11 | 浪潮通信信息系统有限公司 | Method for obtaining mobile network fault location and fault early warning |
| CN204967427U (en) * | 2015-09-21 | 2016-01-13 | 北京宏光星宇科技发展有限公司 | Based on stock basic station direct current remote power supply system |
| CN106685736A (en) * | 2017-02-13 | 2017-05-17 | 中国联合网络通信集团有限公司 | Method and device for determining the fault base station of correlation failure |
| WO2018170866A1 (en) * | 2017-03-24 | 2018-09-27 | 深圳中兴力维技术有限公司 | Data acquisition method and apparatus |
Non-Patent Citations (1)
| Title |
|---|
| 葛中魁等: "基于自身告警关联实现基站故障精准定位", 《电信技术》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115083166A (en) * | 2022-07-14 | 2022-09-20 | 深圳市维力谷无线技术股份有限公司 | Vehicle-road communication testing system and method based on 5G technology |
| CN115083166B (en) * | 2022-07-14 | 2022-11-11 | 深圳市维力谷无线技术股份有限公司 | Vehicle-road communication testing system and method based on 5G technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111327438B (en) | 2022-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | A planning-oriented resilience assessment framework for transmission systems under typhoon disasters | |
| CN105894172B (en) | Combined power failure research and judgment method based on marketing and distribution fusion | |
| US11196638B2 (en) | Network event prediction method and apparatus and method and apparatus for establishing network-event prediction model | |
| CN102116639B (en) | Method and device for automatically checking traffic limit information of electronic map | |
| CN106781509A (en) | A kind of collaborative urban road congestion detection method based on V2V | |
| WO2022111068A1 (en) | Rru undervoltage risk prediction method, apparatus, and system, device, and medium | |
| WO2019116418A1 (en) | Failure analysis device, failure analysis method, and failure analysis program | |
| CN104915897A (en) | Computer implementation method for power grid planning evaluation service | |
| CN111461399A (en) | Method for configuring stagnation point coordinates based on fault nonlinear discrete distribution | |
| CN111327438B (en) | Alarm data processing method and device and readable medium | |
| WO2019137052A1 (en) | Method and device for network operation and maintenance | |
| CN104636859A (en) | Inspection management system | |
| CN105574299A (en) | Safety pre-evaluation method for rail transit signal system | |
| CN111063049A (en) | Power grid line engineering attendance checking method and system | |
| WO2019087382A1 (en) | Operation state prediction system, operation state prediction method, and operation state prediction program | |
| CN112836843B (en) | Base station out-of-service alarm prediction method and device | |
| JP7173273B2 (en) | Failure analysis device, failure analysis method and failure analysis program | |
| CN109788501B (en) | 2G +4G mobile network voice quality joint evaluation method and device | |
| CN105554793A (en) | Method and device for evaluating operation stability of wireless network | |
| CN109359800A (en) | A kind of evaluation method and system of power distribution automation main station system running state | |
| Lan et al. | Crucial states estimation in radio block center handover using Petri nets with unobservable transitions | |
| CN104821898B (en) | A method of it reducing judicial community correction and manages system overshoot rate of false alarm | |
| US11938984B2 (en) | Multi-layer coupling relationship-based train operation deviation propagation condition recognition method | |
| CN111597691A (en) | Secondary model implementation method and system for monitoring mechanism simulation | |
| US20180317047A1 (en) | Active radio frequency tag indoor positioning method |
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 |