CN110752944A

CN110752944A - Alarm order dispatching method and device

Info

Publication number: CN110752944A
Application number: CN201910962269.0A
Authority: CN
Inventors: 赵良; 张贺; 王光全; 张晨芳; 刘晓村; 孙钦栋; 唐迪; 徐东
Original assignee: China United Network Communications Group Co Ltd
Current assignee: China United Network Communications Group Co Ltd
Priority date: 2019-10-08
Filing date: 2019-10-08
Publication date: 2020-02-04
Anticipated expiration: 2039-10-08
Also published as: CN110752944B

Abstract

The embodiment of the invention provides an alarm dispatching method and device, and relates to the field of communication. The embodiment of the invention can determine the preset model for predicting whether to dispatch a certain fault or not by carrying out classification training on the fault characteristics of each fault in a plurality of faults and the processing results of each fault in the plurality of faults. When the fault characteristics of the fault to be identified are obtained, whether the fault to be identified is subjected to dispatching or not can be predicted by directly utilizing the preset model. The method comprises the following steps: and acquiring the fault characteristics of each fault in the plurality of faults and the processing result corresponding to each fault in the plurality of faults. And training the first preset classifier to generate a first preset model. And acquiring the fault characteristics of the fault to be identified. And outputting a first prediction result by utilizing a first preset model according to the fault characteristics of the fault to be identified. The invention is applied to alarm dispatching.

Description

Alarm order dispatching method and device

Technical Field

The invention relates to the field of communication, in particular to an alarm order sending method and device.

Background

Currently, when a network element device in a target network fails, an alarm mechanism is usually triggered. For the alarm sent by the network element equipment, the operation and maintenance personnel can use the order dispatching rule formulated by the manual experience to judge whether to dispatch the work order for processing the fault to the network element equipment with the fault.

The existing method for judging whether to carry out order dispatching processing through an order dispatching rule excessively depends on manual experience, and the situation of omitting the order dispatching often occurs. Meanwhile, for the fault that the network element equipment can be recovered by itself, the existing order dispatching method still dispatches the work order to the network element equipment, and the network resource is greatly wasted.

Disclosure of Invention

The embodiment of the invention provides an alarm dispatching method and device, which can determine a preset model for predicting whether to dispatch a certain fault or not by performing classification training on the fault characteristics of each fault in a plurality of faults and the processing results of each fault in the plurality of faults. When the fault characteristics of the fault to be identified are obtained, whether the fault to be identified is subjected to dispatching or not can be predicted by directly utilizing the preset model. The efficiency of the work of sending the order is promoted, and the resource waste in the process of sending the order is reduced.

In a first aspect, the present invention provides an alarm dispatch method, including: acquiring fault characteristics of each fault in the plurality of faults and a processing result corresponding to each fault in the plurality of faults; the processing result comprises two results of dispatching and not dispatching; the fault signature is generated based on alarm information caused by the fault. Training a first preset classifier by using the fault characteristics of each fault in the plurality of faults and the processing result corresponding to each fault in the plurality of faults to generate a first preset model; the first preset classifier is a binary classifier. And acquiring the fault characteristics of the fault to be identified. Outputting a first prediction result by utilizing a first preset model according to the fault characteristics of the fault to be identified; the first prediction result is used for predicting whether to dispatch the order to the fault to be identified.

In a second aspect, an embodiment of the present invention provides an alarm dispatch device, including: the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring the fault characteristics of each fault in a plurality of faults and the processing result corresponding to each fault in the plurality of faults; the processing result comprises two results of dispatching and not dispatching; the fault signature is generated based on alarm information caused by the fault. The processing unit is used for training the first preset classifier by using the fault characteristics of each fault in the plurality of faults and the processing result corresponding to each fault in the plurality of faults to generate a first preset model; the first preset classifier is a binary classifier. And the acquisition unit is also used for acquiring the fault characteristics of the fault to be identified. The output unit is used for outputting a first prediction result by utilizing a first preset model according to the fault characteristics of the fault to be identified; the first prediction result is used for predicting whether to dispatch the order to the fault to be identified.

In a third aspect, an embodiment of the present invention provides another alarm ordering apparatus, including: a processor, a memory, a bus, and a communication interface; the memory is used for storing computer execution instructions, the processor is connected with the memory through a bus, and when the alarm ordering device runs, the processor executes the computer execution instructions stored in the memory, so that the alarm ordering device executes the alarm ordering method provided by the first aspect.

In a fourth aspect, an embodiment of the present invention provides a computer storage medium, which includes instructions that, when running on an alarm ordering apparatus, cause the alarm ordering apparatus to execute an alarm ordering method provided in the first aspect.

In a fifth aspect, an embodiment of the present invention provides a computer program product including instructions, which, when run on a computer, causes the computer to execute the alarm delegation method according to the first aspect and any implementation manner of the first aspect.

The alarm dispatching method and the alarm dispatching device provided by the embodiment of the invention can determine the preset model for predicting whether to dispatch a certain fault or not by carrying out classification training on the fault characteristics of each fault in a plurality of faults and the processing results of each fault in the plurality of faults. When the fault characteristics of the fault to be identified are obtained, whether the fault to be identified is subjected to dispatching or not can be predicted by directly utilizing the preset model. The efficiency of the work of sending the order is promoted, and the resource waste in the process of sending the order is reduced.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below.

Fig. 1 is a schematic structural diagram of a neural network model according to an embodiment of the present invention;

fig. 2 is a schematic flow chart of an artificial experience-based order dispatching method according to an embodiment of the present invention;

fig. 3 is a schematic flow chart of an alarm dispatch method according to an embodiment of the present invention;

fig. 4 is a second schematic flow chart of an alarm dispatch method according to an embodiment of the present invention;

fig. 5 is a third schematic flow chart of an alarm dispatch method according to an embodiment of the present invention;

fig. 6 is a fourth schematic flow chart of an alarm dispatch method according to an embodiment of the present invention;

fig. 7 is a schematic structural diagram of an alarm dispatch device according to an embodiment of the present invention;

fig. 8 is a second schematic structural diagram of an alarm dispatch device according to an embodiment of the present invention;

fig. 9 is a third schematic structural diagram of an alarm order sending device according to an embodiment of the present invention.

Detailed Description

The alarm dispatch method and device provided by the present application will be described in detail below with reference to the accompanying drawings.

The terms "first" and "second", etc. in the description and drawings of the present application are used for distinguishing between different objects and not for describing a particular order of the objects.

Furthermore, the terms "including" and "having," and any variations thereof, as referred to in the description of the present application, are intended to cover non-exclusive inclusions. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may alternatively include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described herein as "exemplary" or "e.g.," is not necessarily to be construed as preferred or advantageous over other embodiments or designs. Rather, use of the word "exemplary" or "such as" is intended to present concepts related in a concrete fashion.

The term "and/or" as used herein includes the use of either or both of the two methods.

In the description of the present application, the meaning of "a plurality" means two or more unless otherwise specified.

The technical terms referred to in the present application are described below:

the neural network model, the neural network is a complex network system formed by a large number of simple neurons which are widely connected with each other, reflects many basic characteristics of human brain functions, is a highly complex nonlinear dynamical learning system, and is suitable for processing inaccurate and fuzzy information processing problems which need to consider many factors and conditions simultaneously. Illustratively, as shown in FIG. 1, the neural network model 10 includes an input layer 101, a hidden layer 102, a hidden layer 103, and an output layer 104. Wherein the input layer 101 is used to receive information from outside the neural network model 10. The information external to the neural network model 10 includes a q-dimensional alarm feature vector. Specifically, a unique alarm number is determined for an alarm name corresponding to each alarm information in a plurality of alarm information, and q alarm names correspond to q alarm numbers. And then acquiring a target fault work order, and determining at least one piece of alarm information related to the target fault by using the target fault work order. And finally, constructing a q-dimensional alarm characteristic vector for at least one alarm message according to the determined alarm number. The input layer 101 is used for inputting q-dimensional alarm feature vectors. The output layer 104 is used for outputting the calculation result of the neural network model 10. Specifically, the output layer 104 is used for outputting the processing result of dispatching or unporting. Hidden layer 102 and hidden layer 103 are used to solve the linear indivisible problem. Specifically, different alarm characteristics may be partitioned from different levels to generate different partitioning results. Therefore, the corresponding relation between the alarm characteristics and the processing result is indicated by dividing a plurality of hidden layers. Because the corresponding relationship between the alarm characteristics and the processing results is too complex, the embodiment of the present invention only provides two hidden layers, namely the hidden layer 102 and the hidden layer 103. However, in the actual operation process, there are more than two hidden layers in the neural network model, and the number of the hidden layers and the number of neurons in each hidden layer are related to the problem to be solved, and are not specifically limited herein. And setting a target activation function and a target optimizer in the hidden layer to make the neural network model converge, and analyzing the test result of the neural network model. The target activation function includes a sigmoid function, a ReLU (linear rectification function), and a softmax function. The target optimizer includes a SGD (steepest decision method) optimizer, an RMS (root mean square) prop optimizer, an adagrad optimizer, an adadelta optimizer, and an adam optimizer.

The invention principle of the invention is as follows: in the prior art, operation and maintenance personnel usually use a dispatching rule summarized by manual experience to process whether to dispatch an alarm generated in a network. The existing alarm dispatching method, as shown in fig. 2, includes steps S201-S205: s201, when the target network fails, the network element equipment generates alarm information. S202, the target network sends the alarm information generated by the network element equipment to a network management system. S204, the network management system sends the alarm information generated by the network element equipment to the fault dispatching system. Prior to step S204, the existing alarm dispatching method further includes step S203, entering a target dispatching rule into the fault dispatching system according to manual experience. S205, the fault dispatching system sends the processing result of whether dispatching is performed to the operation and maintenance personnel according to the alarm information generated by the network element equipment. Obviously, the existing alarm dispatching method is too dependent on manual experience. Meanwhile, the condition of omitting the dispatching or redundant dispatching often occurs, namely the alarm of the work order to be dispatched is not dispatched, the alarm without dispatching the work order still dispatches the work order, the work efficiency is reduced, and the network resource is wasted. Therefore, an alarm dispatching method is urgently needed, which can systematically determine whether to dispatch a work order to the network element equipment according to the alarm information sent by the network element equipment.

Based on the invention principle, the embodiment of the invention provides an alarm dispatching method. As shown in fig. 3, the method includes S301-S311:

s301, acquiring the fault characteristics of each fault in the plurality of faults and the processing results corresponding to each fault in the plurality of faults.

The processing result comprises two results of dispatching and not dispatching. The fault signature is generated based on alarm information caused by the fault.

Illustratively, as shown in table 1, the fault signature of fault a is signature a, the fault signature of fault B is signature B, the fault signature of fault C is signature C, and the fault signature of fault D is signature D. The processing results corresponding to the fault A, the fault C and the fault D are all dispatched, and the processing result corresponding to the fault B is not dispatched.

Fault of	Failure characterization	Processing the results
			Failure A	Characteristic a	Dispatch sheet
Failure B	Characteristic b	No-dispatch list
			Failure C	Characteristic c	Dispatch sheet
Failure D	Characteristic d	Dispatch sheet

TABLE 1

In an implementation manner of the present invention, the step S301 of obtaining the fault characteristics of each fault in the multiple faults specifically includes the steps S301a-S301 c:

s301a, acquiring a plurality of alarm information within preset time.

Specifically, different alarm information may be divided by using a preset time. The preset time may be 30 seconds or 1 minute, and is not particularly limited herein. Meanwhile, the alarm information with the overlarge interval time cannot represent the fault characteristics of the same fault, so that the embodiment of the invention divides different alarm information by preset time and is also a primary screening process for the input sample in the first preset model.

Illustratively, as shown in table 2, is a selected portion of the alert information. The embodiment of the invention only provides the alarm information number, the number of the target equipment where the alarm occurs, the alarm name and the alarm occurrence time in the alarm information. The alarm information disclosed by the present invention includes, but is not limited to, the four types of information, and the alarm information further includes an alarm level, an alarm ending time, and a port rate at which an alarm occurs, which is not specifically limited herein.

Alarm information numbering	Target device number	Alarm name	Time of occurrence of alarm
				001	01	Link disconnection	2019/1/1 8:47
002	01	ISIS adjacency change	2019/1/1 8:47
				003	02	LOS	2019/1/1 8:47
004	02	Link disconnection	2019/1/1 8:47
				005	03	Physical port down	2019/1/1 8:47
006	02	Remote fault warning	2019/1/1 11:24
				007	01	Physical port down	2019/1/1 16:35

TABLE 2

A plurality of alarm information within the preset time are obtained from table 2, and a plurality of alarm information within the preset time shown in table 3 is obtained. Wherein the preset time is the alarm generated within one minute of the alarm time of 2019/1/18: 47.

Alarm information numbering	Target device number	Alarm name	Time of occurrence of alarm
				001	01	Link disconnection	2019/1/1 8:47
002	01	ISIS adjacency change	2019/1/1 8:47
				003	02	LOS	2019/1/1 8:47
004	02	Link disconnection	2019/1/1 8:47
				005	03	Physical port down	2019/1/1 8:47

Table 3S301b, selecting alarm information caused by the target fault from the plurality of alarm information.

The target failure is one of a plurality of failures.

Specifically, a plurality of alarm messages may appear within a preset time, and the plurality of alarm messages may be alarm messages of the same fault or alarm messages of different faults. Therefore, the alarm information caused by the target fault is selected from the plurality of alarm information, and the alarm characteristic of the target fault is determined through the alarm information caused by the target fault.

Illustratively, an example of a selected portion of the faulty work orders is shown in table 4. The fault work order comprises a work order number, a work order theme and a fault type. As can be seen from table 3, although the 5 alarm messages in table 3 all occur at the same time point, it is obvious that the alarm message No. 005 does not occur from the same fault as the other four alarm messages. The No. 001 warning information, the No. 002 warning information, the No. 003 warning information and the No. 004 warning information are all caused by the target equipment 01 and the target equipment 02, namely all belong to faults with work order numbers GZ20190101-0163, and the No. 005 warning information is caused by the target equipment 03 and belongs to faults with work order numbers GZ 20190101-0164. Therefore, the 001 # alarm information, the 002 # alarm information, the 003 # alarm information, and the 004 # alarm information can be selected from the faults with the work order numbers GZ20190101-0163, and the 005 # alarm information can be selected from the faults with the work order numbers GZ 20190101-0164.

And 4S301c, determining the alarm characteristics of the target fault according to the alarm information caused by the target fault.

Specifically, the target failure is one of a plurality of failures. And determining the fault characteristics of each fault in the plurality of faults by determining the alarm characteristics of the target fault.

For example, as shown in tables 3 and 4, if the fault with the work order number GZ20190101-0163 is the target fault, the alarm characteristic of the fault with the work order number GZ20190101-0163 is determined according to the alarm information 001, the alarm information 002, the alarm information 003, and the alarm information 004.

S302, training a first preset classifier by using the fault characteristics of each fault in the plurality of faults and the processing results corresponding to each fault in the plurality of faults to generate a first preset model.

The first preset classifier is a binary classifier.

Specifically, the fault characteristics of each fault in the plurality of faults and the processing results corresponding to each fault in the plurality of faults are trained to generate a first preset model containing the fault characteristics and the processing results. Furthermore, when the fault feature of one fault to be identified is obtained, the processing result corresponding to the fault to be identified can be predicted according to the fault feature of the fault to be identified.

Exemplarily, as shown in fig. 4, the generation process of the first preset model may be understood as a data-driven process. S401, target data are obtained. The target data comprises alarm information of each fault in the plurality of faults and a processing result corresponding to each fault in the plurality of faults. S402, analyzing the target data. And S403, selecting a target model. Wherein the target model comprises a neural network model. And S404, designing the target model. S405, initializing the target model. And S406, designing a preset function for the target model. The preset function design comprises an objective function design and a cost loss function design. And S407, performing gradient calculation or error back transmission on the preset function. And S408, updating the parameters in the preset function. And S409, judging whether the preset function converges or meets the preset condition. If not, the process returns to S407. If yes, go to S410. And S410, outputting the target model meeting the preset conditions.

Exemplarily, as shown in fig. 5, a schematic flow chart of an alarm dispatch method provided by an embodiment of the present invention is shown. Wherein, the method comprises the following steps: s501, determining a q-dimensional alarm characteristic vector from historical alarm information. Specifically, different alarm information in the target network may be numbered differently, and the target fault and the alarm information corresponding to the target fault may be determined from a plurality of faults corresponding to the historical alarm information according to the preset time. And S502, taking the q-dimensional alarm characteristic vector as input data of a first preset model. S503, determining processing results corresponding to different faults from the historical fault work order. S504, processing results corresponding to different faults are used as label data of the first preset model. Specifically, the processing result of the order dispatching or the order non-dispatching is used as the label data of the first preset model. And S505, combining the input data of the first preset model with the tag data of the first preset model to generate a first data set. S506, dividing the first data set into a first training set and a first testing set according to a preset proportion. Specifically, the predetermined ratio comprises 1: 8. And S507, constructing and generating a first training model by using the data in the first training set. And S508, outputting a first training result by using the first training model. And the first training result is used for representing the corresponding relation between the fault characteristics and the processing result in the first training set. S509, first test data are obtained from the first test set. S510, the first training model is tested by using the first test data, and a first test result is output. Wherein the first test result comprises an accuracy of the first training model. And S511, if the first test result meets the preset accuracy, outputting a first training model. The first training model with the first test result meeting the preset accuracy is a first preset model.

And S303, acquiring the fault characteristics of the fault to be identified.

S304, outputting a first prediction result by utilizing a first preset model according to the fault characteristics of the fault to be identified.

The first prediction result is used for predicting whether to dispatch the order to the fault to be identified.

Specifically, by obtaining the fault characteristics of the fault to be identified and utilizing the first preset model, a first prediction result for predicting whether to dispatch the order to the fault to be identified can be output, so that the accuracy of alarm processing is improved, and the efficiency of the order dispatching work is improved.

For example, as shown in fig. 6, the alarm dispatching method disclosed in the embodiment of the present invention is equivalent to a process including input and output without knowing the inside of the first preset model 60 for the operator in actual operation. That is, the first predetermined model 60 outputs features regarding the result by inputting only some data into the first predetermined model 60. The method comprises the following specific steps: s601, inputting fault characteristics of the fault to be identified to the first preset model 60. S602, the first preset model 60 outputs the first prediction result.

And S310, if the first prediction result shows that the order dispatching processing needs to be carried out on the fault to be recognized, outputting a second prediction result by utilizing a second preset model according to the fault characteristics of the fault to be recognized.

The second prediction result is used for predicting the fault reason of the fault to be identified. The second preset model is generated by training a second preset classifier by using the fault characteristics of each fault in the m faults and the fault reasons of each fault in the m faults. The second preset classifier is used for classifying the m faults into n types of faults, and the n types of faults respectively correspond to different fault reasons.

Specifically, the second preset classifier may be trained by using the fault feature of each fault in the m faults and the fault cause of each fault in the m faults, so as to generate a second preset model including the fault feature and the fault cause. And then, according to the fault characteristics of the fault to be identified, predicting the fault reason of the fault to be identified by using a second preset model. According to the embodiment of the invention, the fault reason of the fault to be identified is predicted through the second preset model, and then the corresponding processing mode is allocated according to the fault reason of the fault to be identified as the fault to be identified, so that the fault can be repaired conveniently.

It should be noted that, in the embodiment of the present invention, after the first prediction result is output by using the first preset model according to the fault characteristics of the fault to be identified, the fault characteristics of each fault in m faults and the fault cause of each fault in m faults are used to train the second preset classifier. The m faults are random and are not subject to any restrictions. In an implementation manner of the present invention, m faults may also be combined with the first preset model, that is, m faults are faults processed by the first preset model. When the m faults are faults processed by the first preset model, if the first prediction result indicates that the fault to be recognized needs to be subjected to the order dispatching processing in step S310, before outputting a second prediction result by using the second preset model according to the fault characteristics of the fault to be recognized, the method further includes:

s305, acquiring fault characteristics of x faults.

S306, according to the fault characteristics of the x faults, judging whether to perform order dispatching processing on each fault in the x faults by using a first preset model, and generating a judgment result.

Specifically, according to the fault characteristics of the x faults, a judgment result is generated by using a first preset model. The determination result is used to indicate whether to dispatch each of the x faults.

S307, according to the judgment result, m faults needing to be subjected to order dispatching are selected from the x faults.

Specifically, x is more than or equal to m.

S308, acquiring the fault reason of each fault in the m faults.

Illustratively, an example of another selected portion of the faulty work order is shown in Table 5. The fault reason corresponding to the fault with the work order number of GZ20190101-0163 is removal breaking, the fault reason corresponding to the fault with the work order number of GZ20190101-0164 is removal breaking, the fault reason corresponding to the fault with the work order number of GZ20190105-0012 is base station tail fiber fault, the fault reason corresponding to the fault with the work order number of GZ20190106-0147 is base station tail fiber fault, the fault reason corresponding to the fault with the work order number of GZ20190108-0110 is construction breaking, and the fault reason corresponding to the fault with the work order number of GZ20190110-0128 is construction breaking.

Work order number	Cause of failure
		GZ20190101-0163	Broken when being disassembled
GZ20190101-0164	Broken when being disassembled
		GZ20190105-0012	Base station tail fiber fault
GZ20190106-0147	Base station tail fiber fault
		GZ20190108-0110	Construction is dug absolutely
GZ20190110-0128	Construction is dug absolutely

Table 5S309, train the second preset classifier using the fault feature of each fault in the m faults and the fault cause of each fault in the m faults, and generate a second preset model.

Specifically, after m faults needing to be subjected to order dispatching are selected from the x faults, the fault characteristics of each fault in the m faults and the fault reasons of each fault in the m faults are used for training the second preset classifier, and a second preset model containing the fault characteristics and the fault reasons is generated. Furthermore, when the fault characteristics of the fault to be identified are obtained, the fault reason of the fault to be identified can be predicted by using the second preset model.

In an implementation manner of the present invention, in step S310, if the first prediction result indicates that the order assignment process needs to be performed on the fault to be identified, after outputting the second prediction result by using the second preset model according to the fault feature of the fault to be identified, the method further includes step S311:

and S311, outputting a target processing mode according to the fault reason of the fault to be identified.

The target processing mode comprises equipment replacement and optical cable fusion.

Exemplarily, as shown in table 6, a corresponding relationship between a failure cause and a processing method provided in the embodiment of the present invention is provided. The failure reason is the optical cable fusion because of the processing mode of removal and breaking. The failure reason is that the treatment mode of the base station tail fiber failure is to replace equipment. Specifically, the method comprises the step of replacing the tail fiber. The failure reason is that the construction is dug to be broken by the optical cable fusion. That is, if the cause of the failure to be identified is due to a construction break, the target processing method is optical cable fusion.

Cause of failure	Treatment method
		Broken when being disassembled	Optical cable fusion splice
Base station tail fiber fault	Replacing device
		Construction is dug absolutely	Optical cable fusion splice

TABLE 6

The present application provides an alarm order dispatching device, configured to execute the aforementioned alarm order dispatching method, as shown in fig. 7, which is a schematic structural diagram of a possible alarm order dispatching device 70 according to an embodiment of the present invention. Wherein, the device includes:

an obtaining unit 701, configured to obtain a fault feature of each fault in the multiple faults and a processing result corresponding to each fault in the multiple faults. The processing result comprises two results of dispatching and not dispatching. The fault signature is generated based on alarm information caused by the fault.

The processing unit 702 is configured to train the first preset classifier by using the fault feature of each fault in the multiple faults and the processing result corresponding to each fault in the multiple faults, so as to generate a first preset model. The first preset classifier is a binary classifier.

The obtaining unit 701 is further configured to obtain a fault feature of the fault to be identified.

The output unit 703 is configured to output a first prediction result by using a first preset model according to a fault feature of the fault to be identified. The first prediction result is used for presetting whether to dispatch the order to the fault to be identified.

Optionally, the obtaining unit 701 is specifically configured to obtain multiple pieces of alarm information within a preset time;

the processing unit 702 is specifically configured to select alarm information caused by a target fault from a plurality of alarm information. The target failure is one of a plurality of failures.

The processing unit 702 is further specifically configured to determine an alarm characteristic of the target fault according to the alarm information caused by the target fault.

Optionally, the output unit 703 is further configured to, if the first prediction result indicates that the order dispatching processing needs to be performed on the fault to be identified, output a second prediction result by using a second preset model according to the fault feature of the fault to be identified. The second prediction result is used for predicting the fault reason of the fault to be identified. The second preset model is generated by training a second preset classifier by using the fault characteristics of each fault in the m faults and the fault reasons of each fault in the m faults. The second preset classifier is used for classifying the m faults into n types of faults, and the n types of faults respectively correspond to different alarm reasons.

Optionally, the obtaining unit 701 is further configured to obtain the fault features of x faults before the output unit 703 outputs the second prediction result by using the second preset model according to the fault feature of the fault to be identified.

The processing unit 702 is further configured to determine, according to the fault characteristics of the x faults, whether to perform order dispatching processing on each fault of the x faults by using the first model, and generate a determination result.

The processing unit 702 is further configured to select m faults that need to be subjected to the order dispatching processing from the x faults according to the determination result.

The obtaining unit 701 is further configured to obtain a failure cause of each of the m failures.

The processing unit 702 is further configured to train a second preset classifier by using the fault feature of each fault in the m faults and the fault cause of each fault in the m faults, so as to generate a second preset model.

Optionally, the output unit 703 is further configured to output a target processing manner according to a fault cause of the fault to be identified. The target processing mode comprises equipment replacement and optical cable fusion.

In the embodiment of the present application, the alarm ordering device may be divided into the functional modules or the functional units according to the method example, for example, each functional module or functional unit may be divided corresponding to each function, or two or more functions may be integrated into one processing module. The integrated module may be implemented in a form of hardware, or may be implemented in a form of a software functional module or a functional unit. The division of the modules or units in the embodiment of the present application is schematic, and is only a logic function division, and there may be another division manner in actual implementation.

In the case of an integrated unit, fig. 8 shows a schematic diagram of a possible structure of the alarm ordering device in the above embodiment. The alarm assigning device 80 includes: a processing module 801, a communication module 802 and a storage module 803. The processing module 801 is configured to control and manage the actions of the alert assignment device 80, for example, the processing module 801 is configured to support the alert assignment device 80 to perform the processes S301 to S311 in fig. 3. The communication module 802 is used to support the communication of the alarm ordering apparatus 80 with other entities. The storage module 803 is used for storing program codes and data of the alarm dispatching device.

The processing module 801 may be a processor or a controller, such as a Central Processing Unit (CPU), a general-purpose processor, a Digital Signal Processor (DSP), an application-specific integrated circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, a transistor logic device, a hardware component, or any combination thereof. Which may implement or perform the various illustrative logical blocks, modules, and circuits described in connection with the disclosure. A processor may also be a combination of computing functions, e.g., comprising one or more microprocessors, a DSP and a microprocessor, or the like. The communication module 802 may be a transceiver, a transceiving circuit or a communication interface, etc. The storage module 803 may be a memory.

When the processing module 801 is the processor shown in fig. 9, the communication module 802 is the transceiver shown in fig. 9, and the storage module 803 is the memory shown in fig. 9, the alarm ordering apparatus according to the embodiment of the present invention may be the alarm ordering apparatus 90 as follows.

Referring to fig. 9, the alarm assigning unit 90 includes: a processor 901, a transceiver 902, a memory 903, and a bus 904.

The processor 901, the transceiver 902 and the memory 903 are connected to each other through a bus 904; the bus 904 may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown, but this does not mean that there is only one bus or one type of bus.

Processor 901 may be a general-purpose Central Processing Unit (CPU), a microprocessor, an Application-Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to control the execution of programs in accordance with the present invention.

The Memory 903 may be a Read-Only Memory (ROM) or other type of static storage device that can store static information and instructions, a Random Access Memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable Programmable Read-Only Memory (EEPROM), a Compact Disc Read-Only Memory (CD-ROM) or other optical Disc storage, optical Disc storage (including Compact Disc, laser Disc, optical Disc, digital versatile Disc, blu-ray Disc, etc.), magnetic disk storage media or other magnetic storage devices, 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, but is not limited to these. The memory may be self-contained and coupled to the processor via a bus. The memory may also be integral to the processor.

The memory 903 is used for storing application program codes for implementing the present invention, and the processor 901 controls the execution. The transceiver 902 is configured to receive content input by an external device, and the processor 901 is configured to execute application program codes stored in the memory 903, so as to implement an alarm dispatching method provided in an embodiment of the present invention.

It should be understood that, in various embodiments of the present invention, the sequence numbers of the above-mentioned processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. 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 invention.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented using a software program, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. The procedures or functions described in accordance with the embodiments of the invention are all or partially effected when the computer program instructions are loaded and executed on a computer. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optics, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or can comprise one or more data storage devices, such as a server, a data center, etc., that can be integrated with the medium. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An alarm dispatch method, comprising:

acquiring fault characteristics of each fault in a plurality of faults and a processing result corresponding to each fault in the plurality of faults; the processing result comprises two results of dispatching and not dispatching; the fault characteristics are generated according to alarm information caused by faults;

training a first preset classifier by using the fault characteristics of each fault in the faults and the processing result corresponding to each fault in the faults to generate a first preset model; the first preset classifier is a binary classifier;

acquiring fault characteristics of a fault to be identified;

outputting a first prediction result by utilizing the first preset model according to the fault characteristics of the fault to be identified; and the first prediction result is used for predicting whether to dispatch the fault to be identified.

2. The alarm dispatching method according to claim 1, wherein the obtaining the fault characteristics of each fault in the plurality of faults specifically comprises:

acquiring a plurality of alarm messages within preset time;

selecting alarm information caused by a target fault from the plurality of alarm information; the target fault is one of the plurality of faults;

and determining the alarm characteristics of the target fault according to the alarm information caused by the target fault.

3. The alarm dispatching method according to claim 2, wherein after outputting a first prediction result according to the fault characteristic of the fault to be identified by using the first preset model, the method further comprises:

if the first prediction result shows that the order dispatching processing needs to be carried out on the fault to be recognized, outputting a second prediction result by utilizing a second preset model according to the fault characteristics of the fault to be recognized; the second prediction result is used for predicting the fault reason of the fault to be identified; the second preset model is generated by training a second preset classifier by using the fault characteristics of each fault in m faults and the fault reason of each fault in m faults; the second preset classifier is used for classifying the m faults into n types of faults, and the n types of faults respectively correspond to different fault reasons.

4. The alarm dispatching method according to claim 3, wherein before outputting a second prediction result by using a second preset model according to the fault characteristics of the fault to be identified, the method further comprises:

acquiring fault characteristics of x faults;

according to the fault characteristics of the x faults, judging whether to perform order dispatching processing on each fault in the x faults by using the first preset model, and generating a judgment result;

according to the judgment result, selecting the m faults needing to be subjected to order dispatching processing from the x faults;

acquiring a fault reason of each fault in the m faults;

and training a second preset classifier by using the fault characteristics of each fault in the m faults and the fault reason of each fault in the m faults to generate a second preset model.

5. The alarm dispatching method according to claim 4, wherein after outputting a second prediction result according to the fault characteristic of the fault to be identified by using a second preset model, the method further comprises:

outputting a target processing mode according to the fault reason of the fault to be identified; the target processing mode comprises equipment replacement and optical cable fusion.

6. An alarm dispatch device, comprising:

the device comprises an acquisition unit, a processing unit and a processing unit, wherein the acquisition unit is used for acquiring fault characteristics of each fault in a plurality of faults and a processing result corresponding to each fault in the plurality of faults; the processing result comprises two results of dispatching and not dispatching; the fault characteristics are generated according to alarm information caused by faults;

the processing unit is used for training a first preset classifier by using the fault characteristics of each fault in the faults and the processing results corresponding to each fault in the faults after the acquiring unit acquires the fault characteristics of each fault in the faults and the processing results corresponding to each fault in the faults, so as to generate a first preset model; the first preset classifier is a binary classifier;

the acquiring unit is further configured to train a first preset classifier by using the fault feature of each of the multiple faults and the processing result corresponding to each of the multiple faults in the processing unit to generate a first preset model, and then acquire the fault feature of the fault to be identified;

the output unit is used for outputting a first prediction result by utilizing the first preset model according to the fault characteristics of the fault to be identified after the fault characteristics of the fault to be identified are acquired by the acquisition unit; and the first prediction result is used for predicting whether to dispatch the fault to be identified.

7. The alarm ordering device according to claim 6,

the acquiring unit is specifically used for acquiring a plurality of alarm information within a preset time;

the processing unit is specifically configured to select alarm information caused by a target fault from the plurality of alarm information; the target fault is one of the plurality of faults;

the processing unit is specifically further configured to determine an alarm characteristic of the target fault according to alarm information caused by the target fault.

8. The alarm ordering device according to claim 7,

the output unit is further configured to, after the output unit outputs a first prediction result according to the fault feature of the fault to be identified by using the first preset model, if the first prediction result indicates that order distribution processing needs to be performed on the fault to be identified, output a second prediction result according to the fault feature of the fault to be identified by using a second preset model; the second prediction result is used for predicting the fault reason of the fault to be identified; the second preset model is generated by training a second preset classifier by using the fault characteristics of each fault in m faults and the fault reason of each fault in m faults; the second preset classifier is used for classifying the m faults into n types of faults, and the n types of faults respectively correspond to different fault reasons.

9. The alarm ordering device according to claim 8,

the acquiring unit is further configured to acquire fault characteristics of x faults before the output unit outputs a second prediction result by using a second preset model according to the fault characteristics of the fault to be identified;

the processing unit is further configured to determine, according to the fault characteristics of the x faults, whether to perform order dispatching processing on each fault of the x faults by using the first preset model, and generate a determination result;

the processing unit is further configured to select the m faults needing to be subjected to the order dispatching processing from the x faults according to the judgment result;

the acquiring unit is further configured to acquire a failure cause of each of the m failures;

the processing unit is further configured to train a second preset classifier by using the fault feature of each fault in the m faults and the fault cause of each fault in the m faults, and generate the second preset model.

10. The alarm ordering device according to claim 9,

the output unit is further configured to output a target processing mode according to the fault reason of the fault to be identified after the output unit outputs a second prediction result by using a second preset model according to the fault feature of the fault to be identified; the target processing mode comprises equipment replacement and optical cable fusion.

11. An alarm dispatch device, comprising: a processor, a communication interface, and a memory; wherein the memory is used for storing one or more programs, the one or more programs comprising computer executable instructions, and when the alarm ordering apparatus is running, the processor executes the computer executable instructions stored in the memory to make the alarm ordering apparatus execute the alarm ordering method according to any one of claims 1 to 5.

12. A computer readable storage medium having instructions stored therein, which when run on a computer, cause the computer to perform the alarm delegation method of any of claims 1-5.