CN116016122A - Network fault solution prediction method, device, equipment and storage medium - Google Patents
Network fault solution prediction method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN116016122A CN116016122A CN202211548537.2A CN202211548537A CN116016122A CN 116016122 A CN116016122 A CN 116016122A CN 202211548537 A CN202211548537 A CN 202211548537A CN 116016122 A CN116016122 A CN 116016122A
- Authority
- CN
- China
- Prior art keywords
- solution
- target
- network fault
- twin
- trained
- 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
- 238000000034 method Methods 0.000 title claims abstract description 64
- 230000004927 fusion Effects 0.000 claims abstract description 54
- 238000012512 characterization method Methods 0.000 claims abstract description 9
- 238000012549 training Methods 0.000 claims description 70
- 239000013598 vector Substances 0.000 claims description 52
- 238000013507 mapping Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 abstract description 25
- 238000010586 diagram Methods 0.000 description 9
- 238000013459 approach Methods 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 2
- 230000001419 dependent effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application provides a prediction method, a device, equipment and a storage medium of a network fault solution. The method comprises the following steps: receiving target network fault data corresponding to a target network sent by a user terminal; predicting the solution of the target network according to the fault data of the target network by adopting a solution prediction model trained to be converged so as to obtain the target solution; the solution prediction model trained to be converged is a fusion model of a bi-directional encoder characterization quantity Bert model of a plurality of twin converters which are constructed in advance; the target solution is sent to the user terminal to instruct the user terminal to display the target solution. According to the method, a solution prediction model trained to be converged is adopted to predict a target solution, and the method does not depend on operation and maintenance personnel; meanwhile, time can be saved, efficiency of finding a target solution is provided, and user experience is improved.
Description
Technical Field
The present disclosure relates to data processing technologies, and in particular, to a method, an apparatus, a device, and a storage medium for predicting a network failure solution.
Background
With the development of society, the demand of users for networks is continuously increased, the probability of network faults in the use process is increased, and operators do a lot of effort for timely processing network faults.
In the prior art, when a user encounters a network fault in life or work, the user timely informs corresponding operation and maintenance personnel of the network fault condition, then the operation and maintenance personnel determines a solution corresponding to the network fault through the network fault condition, and then informs the user how to solve the solution. For complex network fault conditions, the operation and maintenance personnel may need to determine the corresponding solution by means of off-line investigation.
Therefore, in the prior art, when a user encounters a network fault, the user relies on the expertise of operation and maintenance personnel to find a solution, and then corresponding processing is carried out, so that the user has great dependence on the operation and maintenance personnel; meanwhile, the operation and maintenance personnel need to spend a great deal of time when finding the solution, so the efficiency is lower, and the experience of the user using the network is reduced.
Disclosure of Invention
The application provides a prediction method, a device, equipment and a storage medium of a network fault solution, which are used for solving the problems that a user has great dependence on operation and maintenance personnel, and the operation and maintenance personnel needs to spend a great deal of time when finding the solution, and the efficiency is lower.
In a first aspect, the present application provides a method for predicting a network failure solution, the method comprising:
receiving target network fault data corresponding to a target network sent by a user terminal;
predicting the solution of the target network according to the target network fault data by adopting a solution prediction model trained to be converged so as to obtain a target solution; the solution prediction model trained to be converged is a fusion model of a bi-directional encoder characterization quantity Bert model of a plurality of twin converters which are constructed in advance;
and sending the target solution to the user terminal to instruct the user terminal to display the target solution.
In one mode, the solution prediction model trained to converge includes a plurality of twin Bert models trained to converge; different twin Bert models have different hierarchical configuration parameters; the configuration parameters are parameters of the Bert model on grabbing features of semantic granularity;
the predicting the solution of the target network according to the target network fault data by adopting the solution prediction model trained to be converged so as to obtain the target solution comprises the following steps:
Respectively inputting the target network fault data into each trained-to-converge twin Bert model;
respectively adopting each trained to-be-converged twin Bert model to perform feature extraction of corresponding semantic granularity on the target network fault data so as to obtain corresponding network fault feature vectors;
and predicting the solution of the target network according to a plurality of network fault feature vectors to obtain the target solution.
In one approach, the solution prediction model trained to converge further includes a linear layer therein; the linear layer comprises a preset predictive label formula;
predicting the solution of the target network according to the network fault feature vectors to obtain the target solution, including:
calculating a network fault fusion feature vector based on a network fault weight formula and a plurality of network fault feature vectors;
inputting the network fault fusion feature vector into the preset predictive label formula to calculate a target predictive label value;
determining a corresponding target prediction tag range based on the target prediction tag value;
and determining a corresponding target solution based on the target prediction tag range.
In one manner, the determining a corresponding target solution based on the target prediction tag range includes:
acquiring a pre-stored preset predictive label range and a mapping relation of a corresponding solution;
and responding to the fact that the target prediction tag range is consistent with any preset prediction tag range in the mapping relation, and determining a solution corresponding to the consistent preset prediction tag range as a target solution.
In one manner, before the solution prediction model trained to converge is adopted to predict the solution of the target network according to the fault data of the target network, the method further comprises:
acquiring a training sample set; the network fault data in the training sample set is derived from historical network fault data sent by the user terminal and network fault data in the expert experience knowledge base; the training sample set comprises a plurality of network fault data and predictive label values of solutions corresponding to the network fault data;
training a plurality of twin preset Bert models by adopting the training sample set;
and determining a plurality of twin Bert models meeting preset training convergence conditions as a plurality of twin Bert models trained to converge.
In one manner, after determining the plurality of twin Bert models that meet the preset training convergence condition as the plurality of twin Bert models that have been trained to converge, the method further includes:
constructing a fusion model of a plurality of twin Bert models based on the twin Bert models trained to be converged and the linear layer;
determining a fusion model of the plurality of twin Bert models as a solution prediction model trained to converge.
In one form, the method further comprises:
acquiring a network failure update data set; the network fault updating data in the network fault updating data set is derived from the network fault updating data sent by the user terminal and the network fault updating data in the expert experience knowledge base; the network fault updating data set comprises a plurality of network fault updating data and prediction tag values of solutions corresponding to the network fault updating data;
updating and training a plurality of twin Bert models trained to be converged by adopting the network fault updating data set;
determining a plurality of twin Bert models meeting preset updating training conditions as a plurality of updated twin Bert models trained to be converged;
constructing a fusion model of a plurality of updated twin Bert models based on the updated twin Bert models trained to be converged and the linear layer;
And determining a fusion model of the updated twin Bert models as a latest trained-to-converged solution prediction model.
In a second aspect, the present application provides a network failure solution prediction apparatus, the apparatus comprising:
the receiving module is used for receiving target network fault data corresponding to a target network sent by the user terminal;
the prediction module is used for predicting the solution of the target network according to the target network fault data by adopting the solution prediction model trained to be converged so as to obtain the target solution; the solution prediction model trained to be converged is a fusion model of a bi-directional encoder characterization quantity Bert model of a plurality of twin converters which are constructed in advance;
and the sending module is used for sending the target solution to the user terminal so as to instruct the user terminal to display the target solution.
In a third aspect, the present application provides an electronic device, comprising: a processor, and a memory communicatively coupled to the processor;
the memory stores computer-executable instructions;
the processor executes computer-executable instructions stored in the memory to implement the method as described in the first aspect or any one of the ways.
In a fourth aspect, the present application provides a computer-readable storage medium having stored therein computer-executable instructions which, when executed by a processor, are adapted to carry out the method of the first aspect or any of the ways.
The method, device, equipment and storage medium for predicting the network fault solution provided by the application specifically comprise the following steps: receiving target network fault data corresponding to a target network sent by a user terminal; predicting the solution of the target network according to the fault data of the target network by adopting a solution prediction model trained to be converged so as to obtain the target solution; the solution prediction model trained to be converged is a fusion model of a bi-directional encoder characterization quantity Bert model of a plurality of twin converters which are constructed in advance; the target solution is sent to the user terminal to instruct the user terminal to display the target solution. The predicting device of the network fault solution (hereinafter referred to as predicting device) firstly receives the target network fault data corresponding to the target network sent by the user terminal, then the predicting device predicts the target network solution by adopting the solution predicting model trained to be converged, and the solution predicting model is a better predicting model because the solution predicting model is trained to be converged in advance, and meanwhile, the target network fault data is predicted based on a plurality of twin Bert models because the solution predicting model trained to be converged is a fusion model of a plurality of twin Bert models, so that the finally predicted target solution is more accurate; compared with the prior art, the method and the device for detecting the fault data of the target network are not dependent on the solution of the fault data of the target network by the operation and maintenance personnel, so that the dependence on the operation and maintenance personnel is reduced; further, when the operation and maintenance personnel find the target solution, a lot of time is required, so the efficiency is low, the operation and maintenance personnel are not relied on, the target solution can be predicted by means of the solution prediction model trained to be converged, so the time can be solved, the efficiency of finding the solution is improved, and the user can directly obtain the target solution by himself, so that the user experience is further improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
Fig. 1 is an application scenario diagram of a prediction method of a network failure solution provided in the present application;
fig. 2 is a flow chart of a method for predicting a network failure solution according to an embodiment of the present application;
fig. 3 is a flow chart of a method for predicting a network failure solution according to a second embodiment of the present application;
fig. 4 is a flow chart of a method for predicting a network failure solution according to the third embodiment of the present application;
fig. 5 is a flow chart of a method for predicting a network failure solution according to a fourth embodiment of the present application;
FIG. 6 is a schematic diagram of a solution prediction model trained to converge according to a fourth embodiment of the present application;
fig. 7 is a flow chart of a method for predicting a network failure solution according to a fifth embodiment of the present application;
fig. 8 is a schematic diagram of a prediction apparatus of a network failure solution provided in a sixth embodiment of the present application;
fig. 9 is a schematic structural diagram of an electronic device according to a seventh embodiment of the present application.
Specific embodiments thereof have been shown by way of example in the drawings and will herein be described in more detail. These drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as detailed in the accompanying claims.
The terms referred to in this application are explained first:
bi-directional encoder characterization of the transformer (Bidirectional Encoder Representation from Transformers, bert for short): refers to an unsupervised pre-training language model oriented to natural language processing tasks.
In the prior art, when a user encounters a network fault in life or work, the user timely informs corresponding operation and maintenance personnel of the network fault condition, then the operation and maintenance personnel determines a solution corresponding to the network fault through the network fault condition, and then informs the user how to solve the solution. For complex network fault conditions, the operation and maintenance personnel may need to determine the corresponding solution by means of off-line investigation.
Therefore, in the prior art, when a user encounters a network fault, the user relies on operation and maintenance personnel to find a solution and then performs corresponding processing, so that the user has great dependence on the operation and maintenance personnel; meanwhile, the operation and maintenance personnel need to spend a great deal of time when finding the solution, so the efficiency is lower, and the experience of the user using the network is reduced.
In order to solve the defects of the prior art, the inventor of the scheme designs a new scheme through creative research. The scheme provides a prediction method of a network fault solution, in order to solve the problem that a user has great dependence on operation and maintenance personnel, the scheme prediction device receives target network fault data sent by a user terminal, predicts according to the target network fault data through a trained solution prediction model to converge, and obtains the solution of the target network; in order to solve the problems that an operation and maintenance person needs to spend open time and is low in efficiency when finding a target solution, the target solution is obtained through a machine instead of a person, so that time can be saved, the efficiency of obtaining the target solution is improved, the obtained target solution is directly sent to a user terminal, a user can make corresponding processing based on the target solution displayed by the user terminal, and the user can directly obtain the target solution due to the fact that the target solution can be displayed by the user terminal, and further experience of the user can be improved.
The application provides a prediction method, a device, equipment and an application scene of a storage medium for network fault solutions.
Fig. 1 is an application scenario diagram of a network failure solution prediction method provided in the present application. As shown in fig. 1, the application scenario diagram includes a user terminal 101 and an electronic device 102, where the electronic device 102 includes a prediction apparatus 103 of a network failure solution (hereinafter referred to as a prediction apparatus), and the prediction apparatus 103 includes a prediction model 104 of a solution trained to converge.
The user terminal 101 is communicatively connected to the electronic device 102, where the communication connection may be a wired connection or a wireless connection.
Specifically, the user inputs the target network fault data corresponding to the target network through the user terminal 101, then the user terminal 101 sends the target network fault data to the electronic device 102, and the electronic device 102 transmits the target network fault data to the prediction apparatus 103.
Further, the prediction device 103 inputs the target network fault data into the solution prediction model 104 trained to converge, and then predicts the target fault data by using the solution prediction model 104 trained to converge to obtain the target solution.
Further, the prediction means 103 sends the target solution to the user terminal 101 to instruct the user terminal 101 to display the target solution.
The method for predicting the network fault solution aims to solve the technical problems in the prior art.
The following describes the technical solutions of the present application and how the technical solutions of the present application solve the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Example 1
Fig. 2 is a flow chart of a method for predicting a network failure solution according to an embodiment of the present application. The main implementation body of the method of the present embodiment is a prediction device (hereinafter referred to as a prediction device) of a network failure solution, and specific steps are as follows, as shown in fig. 2.
S201, receiving target network fault data corresponding to a target network sent by a user terminal.
The user terminal is a device used by a user, and may be a mobile phone or a computer, and the like, which is not limited herein.
Wherein the target network is a network used in a user society or work.
The target network fault data is a description of the condition that the target network fails.
Specifically, the user inputs the target network failure data in the user terminal, and then transmits the target network failure data to the prediction apparatus, and the prediction apparatus receives the target network failure data.
The user terminal can load network fault application software, and a user opens the network fault application software to input target network fault data.
S202, predicting a solution of a target network according to the fault data of the target network by adopting a solution prediction model trained to be converged so as to obtain the target solution; the solution prediction model trained to converge is a fusion model of the bi-directional encoder characterizer Bert model of a plurality of twin transformers built in advance.
Wherein the solution prediction model trained to converge is a fusion model of a plurality of twin Bert models constructed in advance.
Specifically, the target network failure data is input to a solution prediction model trained to converge, and then the solution prediction model trained to converge predicts the target solution by semantic description of the target network failure data.
And S203, the target solution is sent to the user terminal so as to instruct the user terminal to display the target solution.
Specifically, the prediction means transmits the target solution to the user terminal by a wired or wireless manner, so that the target solution will be displayed in the user terminal.
In one approach, when the target solution is sent to the user terminal, a reminder message is also generated, reminding the user to view the target solution through the user terminal.
The embodiment provides a prediction method of a network fault solution, which specifically includes: receiving target network fault data corresponding to a target network sent by a user terminal; predicting the solution of the target network according to the fault data of the target network by adopting a solution prediction model trained to be converged so as to obtain the target solution; the solution prediction model trained to be converged is a fusion model of a bi-directional encoder characterization quantity Bert model of a plurality of twin converters which are constructed in advance; the target solution is sent to the user terminal to instruct the user terminal to display the target solution. The predicting device of the network fault solution of the embodiment (hereinafter referred to as predicting device) firstly receives the target network fault data corresponding to the target network sent by the user terminal, then the predicting device predicts the target network solution by adopting the solution predicting model trained to be converged, and the solution predicting model is a better predicting model because the solution predicting model is trained to be converged in advance, and meanwhile, the target network fault data is predicted based on a plurality of twin Bert models because the solution predicting model trained to be converged is a fusion model of a plurality of twin Bert models, so that the finally predicted target solution is more accurate; compared with the prior art, the method and the device for detecting the fault data of the target network are not dependent on the solution of the fault data of the target network by the operation and maintenance personnel, so that the dependence on the operation and maintenance personnel is reduced; further, when the operation and maintenance personnel find the target solution, a lot of time is required, so the efficiency is low, the operation and maintenance personnel are not relied on, the target solution can be predicted by means of the solution prediction model trained to be converged, so the time can be solved, the efficiency of finding the solution is improved, and the user can directly obtain the target solution by himself, so that the user experience is further improved.
Example two
This embodiment is a further refinement of the first embodiment described above, in which the solution prediction model trained to converge includes a plurality of twin Bert models trained to converge; different twin Bert models have different hierarchical configuration parameters; the configuration parameters are parameters of the Bert model with respect to grabbing features on semantic granularity.
The configuration parameters may be the number of convectors with different layers and the number of hidden layers.
Fig. 3 is a flow chart of a prediction method of a network fault solution according to a second embodiment of the present application. The present embodiment is an alternative way to predict the solution of the target network according to the fault data of the target network by using the solution prediction model trained to converge, and the specific steps are as follows, as shown in fig. 3.
S301, the target network fault data are respectively input into each twin Bert model trained to be converged.
Specifically, the prediction device inputs the target network fault data in parallel into the twin Bert model trained to converge.
S302, feature extraction of corresponding semantic granularity is carried out on the target network fault data by adopting each trained to-be-converged twin Bert model, so as to obtain corresponding network fault feature vectors.
The semantic granularity refers to whether text is segmented, and the input characteristics of a sentence are represented by words or characters.
Wherein the network failure feature vector is a fixed length vector.
Specifically, each trained to converged twin Bert model performs feature extraction of corresponding semantic granularity on the same network fault data, and because the semantic granularity is inconsistent, the obtained network fault feature vectors are inconsistent, and further the corresponding network fault feature vectors are respectively obtained.
S303, predicting the solution of the target network according to the plurality of network fault feature vectors to obtain the target solution.
Specifically, a target solution is predicted according to characteristics of a plurality of network fault feature vectors.
The embodiment provides a method for predicting a network fault solution, wherein a solution prediction model trained to be converged in the embodiment comprises a plurality of twin Bert models trained to be converged; different twin Bert models have different hierarchical configuration parameters; the configuration parameters are parameters of the Bert model with respect to grabbing features on semantic granularity. When a solution prediction model trained to be converged is adopted to predict a solution of a target network according to target network fault data so as to obtain the target solution, the method specifically comprises the following steps: respectively inputting the target network fault data into each trained to-be-converged twin Bert model; respectively adopting each trained to-be-converged twin Bert model to perform feature extraction of corresponding semantic granularity on the target network fault data so as to obtain corresponding network fault feature vectors; the solution of the target network is predicted according to the plurality of network fault feature vectors to obtain the target solution. In this embodiment, a plurality of trained-to-converged twin Bert models are used to predict network fault data, and because the Bert models are trained-to-converged, the network fault data is a better model, and meanwhile, in this embodiment, a plurality of trained-to-converged twin Bert models are used, different twin Bert models have different hierarchical configuration parameters, and because the configuration parameters are grabbing feature parameters of the Bert models on semantic granularity, the network fault feature vectors corresponding to the Bert models can be obtained by using the plurality of trained-to-converged twin Bert models, the network fault feature vectors are accurate, and are considered from the plurality of configuration parameters, so that the network fault feature vectors are more comprehensive, and then a target solution is predicted based on the plurality of network fault feature vectors.
Example III
This embodiment is a further refinement of any of the embodiments described above, further comprising a linear layer in the solution prediction model trained to converge; the linear layer includes a preset predictive tag formula.
The preset predictive tag formula may be a Softmax function. The preset predictive label formula is a predictive label formula which is trained to be converged and is obtained after training. In the training process, training parameters in the predictive label formula, and obtaining a final preset predictive label formula after reaching convergence conditions.
Fig. 4 is a flow chart of a method for predicting a network failure solution according to the third embodiment of the present application. This embodiment is a further refinement of any of the embodiments described above, in which the solution of the target network is predicted according to a plurality of network fault feature vectors, so as to obtain an alternative way of obtaining the target solution, as shown in fig. 4, and the specific steps are as follows.
S401, calculating a network fault fusion feature vector based on a network fault weight formula and a plurality of network fault feature vectors.
The network fault weight formula is preset, wherein the weights can be configured according to own requirements or the importance of each network fault feature vector, and the network fault weight formula is not limited herein.
In one approach, the network failure weight formula may be as shown in equation (1):
(1)V＝ω 1 V 1 +ω 2 V 2 +……+ω i V i
wherein V represents a network fault fusion feature vector, vi represents each network fault feature vector, i represents the number of twin Bert models, and ω represents the number of twin Bert models i Representing the respective corresponding weight parameters.
Specifically, the prediction device inputs a plurality of network fault feature vectors into a network fault weight formula, so as to calculate a network fault fusion feature vector. Wherein the network failure fusion feature vector is a fixed length vector.
S402, inputting the network fault fusion feature vector into a preset predictive label formula to calculate a target predictive label value.
In one manner, the preset predictive label formula may be as shown in formula (2):
(2)Y＝f(WV+b)
wherein f (V) represents an activation function, which may be a Softmax function, V represents a network fault fusion feature vector, b represents a preset deviation, W represents a weight matrix of a linear layer, Y represents an output of the linear layer, and is a fixed length vector, namely Y= [ Y ] 1 ,...Y m ] T Wherein Y is m Is an element of Y, and m is the number of elements.
Specifically, the network fault fusion feature vector V is input into the formula (2) to obtain the output Y of the linear layer, and then a maximum element Y is determined from a plurality of elements of the Y max And taking the target predicted tag value as a target predicted tag value.
S403, determining a corresponding target prediction tag range based on the target prediction tag value.
The target prediction tag range is a range to which a target prediction tag value belongs, and the prediction tag range can be determined according to the total number of preset solutions.
Specifically, Y is the output of the Softmax function, Y m The value of (2) is [0,1]]All elements in Y are normalized, and all elements are added up to be equal to 1. Assuming the total number of preset solutions is n, the interval [0,1]The method comprises the steps of dividing the method into n interval ranges, wherein each interval range is a prediction label range, and each prediction label range corresponds to a preset solution to which the prediction label range belongs.
For example, assuming that the total number of preset solutions is 5, the interval [0,1] is divided into 5 interval ranges, specifically, [0,0.2], (0.2, 0.4], (0.4,0.6 ], (0.6,0.8), and (0.8,1 ]. Simultaneously, each of the prediction tag ranges corresponds to one preset solution.
Further, a corresponding target prediction tag range is determined from the target prediction tag value, and according to the above exemplary example, assuming that the target prediction tag value is 0.88, the target prediction tag range is determined to be (0.8,1).
S404, determining a corresponding target solution based on the target prediction tag range.
Illustratively, the target predicted tag range (0.8,1) corresponds to the preset solution 10 in the mapping relationship, and then the preset solution 10 is determined as the target solution corresponding to the target predicted tag range.
The present embodiment provides a method for predicting a network failure solution, when predicting a solution of a target network according to a plurality of network failure feature vectors to obtain the target solution, the method specifically includes: calculating a network fault fusion feature vector based on a network fault weight formula and a plurality of network fault feature vectors; inputting the network fault fusion feature vector into a preset predictive label formula to calculate a target predictive label value; determining a corresponding target prediction tag range based on the target prediction tag value; and determining a corresponding target solution based on the target prediction tag range. The prediction apparatus of this embodiment first calculates a network failure fusion feature vector based on a network failure weight formula and a plurality of network failure feature vectors, and then inputs the network failure fusion feature vector into a preset prediction tag formula to calculate a target prediction tag value.
In one mode, the method is an optional mode for determining a corresponding target solution based on the target prediction tag range, and the specific steps are as follows.
And acquiring a pre-stored preset predictive label range and a mapping relation of a corresponding solution.
Wherein the corresponding solution may be determined by an experienced expert.
The mapping relationship may be represented in a table form, or otherwise, without limitation.
Specifically, the prediction device obtains a mapping relation between a preset prediction tag range and a solution corresponding to the preset prediction tag range from the storage area of the prediction device, and the mapping relation can contain a plurality of prediction tag ranges and corresponding solutions.
For example, assuming that the total number of preset solutions is n, the mapping relationship is shown in table 1 below.
Table 1: preset predictive label range and mapping relation of corresponding solutions
| Preset predictive tag range | Corresponding solution |
| [0,1/n] | Solution 1 |
| (1/n,2/n] | Solution 2 |
| (3/n,4/n] | Solution 3 |
| …… | Solution … … |
| (n-1/n,1] | Solution n |
And responding to the fact that the target prediction tag range is consistent with any preset prediction tag range in the mapping relation, and determining a solution corresponding to the consistent preset prediction tag range as a target solution.
According to the above illustrative example, the prediction means compares the target predicted tag range with the preset predicted tag ranges in table 1, finds any one of the preset predicted tag ranges in table 1 to coincide with the target predicted tag range, for example, the target predicted tag range is (3/n, 4/n ], corresponds to the preset predicted tag range in table 1 to be (3/n, 4/n ], and further determines that the solution corresponding to the preset predicted tag range (3/n, 4/n) is solution 3, thereby determining solution 3 as the target solution.
When determining a corresponding target solution based on a target prediction tag range, the method specifically comprises the following steps: acquiring a pre-stored preset predictive label range and a mapping relation of a corresponding solution; and responding to the fact that the target prediction tag range is consistent with any preset prediction tag range in the mapping relation, and determining a solution corresponding to the consistent preset prediction tag range as a target solution. The prediction apparatus of this embodiment obtains a mapping relationship between a preset predicted tag range and a solution corresponding to the preset predicted tag range, and because the mapping relationship can accurately reflect the solution corresponding to the preset predicted tag range, further responds to the fact that the target predicted tag range is consistent with the preset predicted tag range in the mapping relationship, and then determines the solution corresponding to the consistent preset predicted tag range as the target solution, so that the determined target solution is accurate.
Example IV
Fig. 5 is a flow chart of a method for predicting a network failure solution according to a fourth embodiment of the present application. This embodiment is a further refinement of any of the embodiments described above, in which an alternative manner before the solution prediction model trained to converge is used to predict the solution of the target network according to the target network failure data is shown in fig. 5, and the specific steps are as follows.
S501, acquiring a training sample set; the network fault data in the training sample set is derived from historical network fault data sent by the user terminal and network fault data in the expert experience knowledge base; the training sample set comprises a plurality of network fault data and predictive label values of solutions corresponding to the network fault data.
The historical network fault data refers to data sent by the user terminal before. The expert experience knowledge base is the data summarized by the expert of the operator.
The predicted tag value of the solution corresponding to each network fault data contained in the training sample set may be a tag value set manually through preprocessing. Wherein the predictive label value of the solution corresponding to the network failure data can reflect the solution of the network failure data.
Specifically, the prediction device acquires network fault data from the user terminal and the expert experience knowledge base, then the prediction device displays the network fault data to the expert through the display, the expert inputs the set prediction tag value of the solution and sends the set prediction tag value to the prediction device, and the network fault data set comprises a plurality of network fault data and the prediction tag value of the solution corresponding to each network fault data.
S502, training a plurality of twin preset Bert models by using a training sample set.
Specifically, all network fault data in the training sample set and the predicted tag values of solutions corresponding to the network fault data are input into a plurality of twin preset Bert models for training, so that the preset Bert models optimize model parameters based on the training sample set.
S503, determining a plurality of twin Bert models meeting preset training convergence conditions as a plurality of twin Bert models trained to converge.
And obtaining a plurality of twin Bert models trained to be converged after the preset training convergence conditions are met.
The embodiment provides a method for predicting a network failure solution, which specifically includes, before predicting a solution of a target network according to target network failure data by using a solution prediction model trained to converge: acquiring a training sample set; the network fault data in the training sample set is derived from historical network fault data sent by the user terminal and network fault data in the expert experience knowledge base; the training sample set comprises a plurality of network fault data and predictive label values of solutions corresponding to the network fault data; training a plurality of twin preset Bert models by using a training sample set; and determining a plurality of twin Bert models meeting preset training convergence conditions as a plurality of twin Bert models trained to converge. The prediction device of the embodiment firstly acquires a training sample set, trains a plurality of twin preset Bert models based on the training sample set, then determines the twin Bert models meeting training convergence conditions as a plurality of twin Bert models trained to be converged, and because the network fault data in the training sample set is derived from the network fault data sent by a user terminal and is the historical network fault data and the network fault data in an expert experience knowledge base, and the training sample set also comprises the prediction label value of the solution corresponding to each network fault data, the training sample set has wide and comprehensive sources, the data accords with the actual condition of a user, and the obtained twin Bert models trained to be converged are better, are professional and also accord with the actual condition of the user
In one mode, the method is an optional mode after determining a plurality of twin Bert models meeting preset training convergence conditions as a plurality of twin Bert models trained to converge, and the specific content is as follows.
And constructing a fusion model of the plurality of twin Bert models based on the plurality of twin Bert models trained to converge and the linear layer.
A fusion model of a plurality of twin Bert models is determined as a solution prediction model trained to converge.
Fig. 6 is a schematic diagram of a solution prediction model trained to converge according to a fourth embodiment of the present application. As shown in fig. 6, the plurality of the trained-to-converged twin Bert models are Bert model 1, bert model 2, bert model 3 and Bert model 4, respectively, and the plurality of the trained-to-converged twin Bert models and the linear layer construct a fusion model, i.e. the trained-to-converged solution prediction model. Wherein the configuration parameters of the plurality of twin Bert models trained to converge are different.
After determining a plurality of twin Bert models meeting preset training convergence conditions as a plurality of twin Bert models trained to converge, the method specifically comprises the following steps: constructing a fusion model of a plurality of twin Bert models based on the twin Bert models trained to be converged and the linear layer; a fusion model of a plurality of twin Bert models is determined as a solution prediction model trained to converge. The prediction device constructs a fusion model of a plurality of twin Bert models trained to be converged and a linear layer, wherein the fusion model is a solution prediction model trained to be converged, and the solution prediction model is a better model because the plurality of twin Bert models trained to be converged and the linear layer are contained in the solution prediction model trained to be converged.
Example five
Fig. 7 is a flow chart of a method for predicting a network failure solution according to a fifth embodiment of the present application. This embodiment is a further refinement of any of the embodiments described above, as shown in fig. 7, and the specific steps are as follows.
S701, acquiring a network fault update data set; the network fault updating data in the network fault updating data set is derived from the network fault updating data sent by the user terminal and the network fault updating data in the expert experience knowledge base; the network failure update data set includes a plurality of network failure update data and a predictive label value for a solution corresponding to each network failure update data.
Specifically, the prediction device acquires network fault update data from the user terminal and the expert experience knowledge base, then the prediction device displays the network fault update data to the expert through the display, the expert inputs the set prediction tag value of the solution and sends the set prediction tag value to the prediction device, and the network fault update data set comprises a plurality of network fault update data and the prediction tag value of the solution corresponding to each network fault update data.
S702, updating and training a plurality of twin Bert models trained to be converged by adopting a network fault updating data set.
Specifically, all network fault update data in the network fault update data set and the prediction label value of the solution corresponding to each network fault update data are input into the trained twin Bert model for update training, so that model parameters in the trained twin Bert model are further optimized.
S703, determining a plurality of twin Bert models meeting preset updated training conditions as a plurality of updated twin Bert models trained to converge.
Wherein, the preset update training conditions are conditions specially preset for update training.
Specifically, when the multiple twin Bert models meet the preset updating training conditions, the twin Bert models trained to be converged are updated, and the model parameters contained in the twin Bert models are optimized.
Further, the prediction device determines a plurality of twin Bert models meeting preset updated training conditions as a plurality of updated twin Bert models trained to converge.
S704, constructing a fusion model of the updated twin Bert models based on the updated twin Bert models trained to be converged and the linear layer.
Specifically, the prediction device will reselect a plurality of updated twin Bert models trained to converge and construct a fusion model of the plurality of updated twin Bert models from the linear layer. Therefore, the finally obtained fusion model of the updated twin Bert model is the nearest and meets the actual requirements better.
In one mode, the prediction device can update and train the linear layer, so as to obtain a better preset prediction label formula.
S705, determining a fusion model of a plurality of updated twin Bert models as the latest solution prediction model trained to be converged.
The embodiment provides a method for predicting a network fault solution, which specifically further includes: acquiring a network failure update data set; the network fault updating data in the network fault updating data set is derived from the network fault updating data sent by the user terminal and the network fault updating data in the expert experience knowledge base; the network fault updating data set comprises a plurality of network fault updating data and prediction tag values of solutions corresponding to the network fault updating data; updating and training a plurality of twin Bert models trained to be converged by adopting a network fault updating data set; determining a plurality of twin Bert models meeting preset updating training conditions as a plurality of updated twin Bert models trained to be converged; constructing a fusion model of a plurality of updated twin Bert models based on the plurality of updated twin Bert models trained to converge and the linear layer; a fusion model of the plurality of updated twin Bert models is determined as the latest trained-to-converged solution prediction model. The prediction device of the embodiment can acquire the network fault update data set, so that update training is performed based on the network fault update data contained in the network fault update data set and the prediction label value of the solution corresponding to each network fault update data, and then the latest trained-to-converged solution prediction model can be constructed, and the latest trained-to-converged solution prediction model can be obtained due to update training, so that the actual situation is more met; meanwhile, the network fault data in the network fault update data set is derived from the network fault update data sent by the user terminal and the network fault update data in the expert experience knowledge base, so that the latest trained solution prediction model is more comprehensive.
Example six
The following is an embodiment of the apparatus of the present application, and fig. 8 is a schematic diagram of a prediction apparatus of a network failure solution provided in the sixth embodiment of the present application, and as shown in fig. 8, the apparatus 800 includes the following modules.
A receiving module 801, configured to receive target network fault data corresponding to a target network sent by a user terminal;
a prediction module 802, configured to predict a solution of the target network according to the target network fault data by using the solution prediction model trained to converge, so as to obtain a target solution; the solution prediction model trained to be converged is a fusion model of a bi-directional encoder characterization quantity Bert model of a plurality of twin converters which are constructed in advance;
a sending module 803, configured to send the target solution to the user terminal, so as to instruct the user terminal to display the target solution.
In one approach, the trained-to-converged solution prediction model comprises a plurality of trained-to-converged twin Bert models; different twin Bert models have different hierarchical configuration parameters; the configuration parameters are parameters of the Bert model on grabbing features of semantic granularity; the prediction module 802 is specifically configured to, when predicting a solution of the target network according to the target network failure data using the solution prediction model trained to converge to obtain the target solution:
Respectively inputting the target network fault data into each trained to-be-converged twin Bert model; respectively adopting each trained to-be-converged twin Bert model to perform feature extraction of corresponding semantic granularity on the target network fault data so as to obtain corresponding network fault feature vectors; the solution of the target network is predicted according to the plurality of network fault feature vectors to obtain the target solution.
In one approach, the solution prediction model trained to converge also includes a linear layer; the linear layer comprises a preset predictive label formula; the prediction module 802 is specifically configured to, when predicting a solution of a target network according to a plurality of network fault feature vectors to obtain the target solution:
calculating a network fault fusion feature vector based on a network fault weight formula and a plurality of network fault feature vectors; inputting the network fault fusion feature vector into a preset predictive label formula to calculate a target predictive label value;
determining a corresponding target prediction tag range based on the target prediction tag value; and determining a corresponding target solution based on the target prediction tag range.
In one manner, the prediction module 802, when determining a corresponding target solution based on a target prediction tag range, is specifically configured to:
Acquiring a pre-stored preset predictive label range and a mapping relation of a corresponding solution; and responding to the fact that the target prediction tag range is consistent with any preset prediction tag range in the mapping relation, and determining a solution corresponding to the consistent preset prediction tag range as a target solution.
In one manner, the present embodiment provides a network failure solution prediction apparatus before predicting a solution of a target network according to target network failure data using a solution prediction model trained to converge, further comprising: the device comprises an acquisition module, a training module and a determination module.
The acquisition module is used for acquiring a training sample set; the network fault data in the training sample set is derived from historical network fault data sent by the user terminal and network fault data in the expert experience knowledge base; the training sample set comprises a plurality of network fault data and predictive label values of solutions corresponding to the network fault data; the training module is used for training a plurality of twin preset Bert models by adopting a training sample set; and the determining module is used for determining a plurality of twin Bert models meeting preset training convergence conditions as a plurality of twin Bert models trained to converge.
In one manner, after determining a plurality of twin Bert models satisfying a preset training convergence condition as a plurality of twin Bert models trained to converge, the present embodiment provides a prediction apparatus of a network failure solution, further including: and constructing a module.
The construction module is used for constructing a fusion model of the twin Bert models based on the twin Bert models trained to be converged and the linear layer; the determination module is further used for determining a fusion model of the plurality of twin Bert models as a solution prediction model trained to be converged.
In one form, the present embodiment provides a network failure solution prediction apparatus.
The acquisition module is also used for acquiring a network fault update data set; the network fault updating data in the network fault updating data set is derived from the network fault updating data sent by the user terminal and the network fault updating data in the expert experience knowledge base; the network fault updating data set comprises a plurality of network fault updating data and prediction tag values of solutions corresponding to the network fault updating data; the training module is also used for updating and training a plurality of twin Bert models trained to be converged by adopting a network fault updating data set; the determining module is further used for determining a plurality of twin Bert models meeting preset updating training conditions as a plurality of updated twin Bert models trained to be converged; the construction module is also used for constructing a fusion model of the updated twin Bert models based on the updated twin Bert models trained to be converged and the linear layer; the determining module is further configured to determine a fusion model of the plurality of updated twin Bert models as a latest solution prediction model trained to converge.
Example seven
Fig. 9 is a schematic structural diagram of an electronic device according to a seventh embodiment of the present application. As shown in fig. 9, the electronic device 900 may include: a processor 901, and a memory 902 communicatively coupled to the processor 901. Wherein the memory 902 stores computer-executable instructions; the processor 901 executes computer-executable instructions stored in the memory 902 to implement any method embodiment from the first embodiment to the fifth embodiment, and the specific implementation manner and technical effect are similar, and are not repeated here.
In this embodiment, the memory 902 and the processor 901 are connected via a bus. The bus may be an industry standard architecture (Industry Standard Architecture, abbreviated ISA) bus, an external device interconnect (Peripheral Component Interconnect, abbreviated PCI) bus, or an extended industry standard architecture (Extended Industry Standard Architecture, abbreviated EISA) bus, among others. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 9, but not only one bus or one type of bus.
Example eight
The present application provides a computer readable storage medium, in which computer executable instructions are stored, where the computer executable instructions are used to implement any one of the method embodiments of the first to fifth embodiments when executed by a processor, and the specific implementation manner and technical effect are similar, and are not repeated herein.
Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the present application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (10)
1. A method of predicting a network failure solution, the method comprising:
receiving target network fault data corresponding to a target network sent by a user terminal;
predicting the solution of the target network according to the target network fault data by adopting a solution prediction model trained to be converged so as to obtain a target solution; the solution prediction model trained to be converged is a fusion model of a bi-directional encoder characterization quantity Bert model of a plurality of twin converters which are constructed in advance;
And sending the target solution to the user terminal to instruct the user terminal to display the target solution.
2. The method of claim 1, wherein the trained-to-converged solution prediction model comprises a plurality of trained-to-converged twin Bert models; different twin Bert models have different hierarchical configuration parameters; the configuration parameters are parameters of the Bert model on grabbing features of semantic granularity;
the predicting the solution of the target network according to the target network fault data by adopting the solution prediction model trained to be converged so as to obtain the target solution comprises the following steps:
respectively inputting the target network fault data into each trained-to-converge twin Bert model;
respectively adopting each trained to-be-converged twin Bert model to perform feature extraction of corresponding semantic granularity on the target network fault data so as to obtain corresponding network fault feature vectors;
and predicting the solution of the target network according to a plurality of network fault feature vectors to obtain the target solution.
3. The method of claim 2, wherein the solution prediction model trained to converge further comprises a linear layer; the linear layer comprises a preset predictive label formula;
Predicting the solution of the target network according to the network fault feature vectors to obtain the target solution, including:
calculating a network fault fusion feature vector based on a network fault weight formula and a plurality of network fault feature vectors;
inputting the network fault fusion feature vector into the preset predictive label formula to calculate a target predictive label value;
determining a corresponding target prediction tag range based on the target prediction tag value;
and determining a corresponding target solution based on the target prediction tag range.
4. The method of claim 3, wherein the determining a corresponding target solution based on the target prediction tag range comprises:
acquiring a pre-stored preset predictive label range and a mapping relation of a corresponding solution;
and responding to the fact that the target prediction tag range is consistent with any preset prediction tag range in the mapping relation, and determining a solution corresponding to the consistent preset prediction tag range as a target solution.
5. The method of any of claims 1-4, wherein prior to predicting a solution to a target network from the target network failure data using the trained solution prediction model, further comprising:
Acquiring a training sample set; the network fault data in the training sample set is derived from historical network fault data sent by the user terminal and network fault data in the expert experience knowledge base; the training sample set comprises a plurality of network fault data and predictive label values of solutions corresponding to the network fault data;
training a plurality of twin preset Bert models by adopting the training sample set;
and determining a plurality of twin Bert models meeting preset training convergence conditions as a plurality of twin Bert models trained to converge.
6. The method according to claim 5, wherein after determining the plurality of twin Bert models satisfying the preset training convergence condition as the plurality of twin Bert models trained to converge, further comprising:
constructing a fusion model of a plurality of twin Bert models based on the twin Bert models trained to be converged and the linear layer;
determining a fusion model of the plurality of twin Bert models as a solution prediction model trained to converge.
7. The method according to claim 1, wherein the method further comprises:
acquiring a network failure update data set; the network fault updating data in the network fault updating data set is derived from the network fault updating data sent by the user terminal and the network fault updating data in the expert experience knowledge base; the network fault updating data set comprises a plurality of network fault updating data and prediction tag values of solutions corresponding to the network fault updating data;
Updating and training a plurality of twin Bert models trained to be converged by adopting the network fault updating data set;
determining a plurality of twin Bert models meeting preset updating training conditions as a plurality of updated twin Bert models trained to be converged;
constructing a fusion model of a plurality of updated twin Bert models based on the updated twin Bert models trained to be converged and the linear layer;
and determining a fusion model of the updated twin Bert models as a latest trained-to-converged solution prediction model.
8. A network failure solution prediction apparatus, the apparatus comprising:
the receiving module is used for receiving target network fault data corresponding to a target network sent by the user terminal;
the prediction module is used for predicting the solution of the target network according to the target network fault data by adopting the solution prediction model trained to be converged so as to obtain the target solution; the solution prediction model trained to be converged is a fusion model of a bi-directional encoder characterization quantity Bert model of a plurality of twin converters which are constructed in advance;
and the sending module is used for sending the target solution to the user terminal so as to instruct the user terminal to display the target solution.
9. An electronic device, comprising: a processor, and a memory communicatively coupled to the processor;
the memory stores computer-executable instructions;
the processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1-8.
10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211548537.2A CN116016122B (en) | 2022-12-05 | 2022-12-05 | Network fault solution prediction method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211548537.2A CN116016122B (en) | 2022-12-05 | 2022-12-05 | Network fault solution prediction method, device, equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116016122A true CN116016122A (en) | 2023-04-25 |
| CN116016122B CN116016122B (en) | 2024-10-01 |
Family
ID=86034383
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211548537.2A Active CN116016122B (en) | 2022-12-05 | 2022-12-05 | Network fault solution prediction method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116016122B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116614344A (en) * | 2023-05-29 | 2023-08-18 | 北京城建智控科技股份有限公司 | Fault diagnosis method and system based on digital twinning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242171A (en) * | 2019-12-31 | 2020-06-05 | 中移（杭州）信息技术有限公司 | Model training, diagnosis and prediction method and device for network fault and electronic equipment |
| CN113065356A (en) * | 2021-03-19 | 2021-07-02 | 南方电网调峰调频发电有限公司信息通信分公司 | IT equipment operation and maintenance fault suggestion processing method based on semantic analysis algorithm |
| CN113094200A (en) * | 2021-06-07 | 2021-07-09 | 腾讯科技（深圳）有限公司 | Application program fault prediction method and device |
| CN114201920A (en) * | 2021-12-15 | 2022-03-18 | 苏州华光智控电子科技有限公司 | Laser cutting numerical control system fault diagnosis method based on digital twinning and deep transfer learning |
| CN114548803A (en) * | 2022-02-28 | 2022-05-27 | 浙江绿城未来数智科技有限公司 | Future community digital twin management system based on AI digital people |
| US20220318504A1 (en) * | 2021-03-30 | 2022-10-06 | Microsoft Technology Licensing, Llc | Interpreting text-based similarity |
-
2022
- 2022-12-05 CN CN202211548537.2A patent/CN116016122B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242171A (en) * | 2019-12-31 | 2020-06-05 | 中移（杭州）信息技术有限公司 | Model training, diagnosis and prediction method and device for network fault and electronic equipment |
| CN113065356A (en) * | 2021-03-19 | 2021-07-02 | 南方电网调峰调频发电有限公司信息通信分公司 | IT equipment operation and maintenance fault suggestion processing method based on semantic analysis algorithm |
| US20220318504A1 (en) * | 2021-03-30 | 2022-10-06 | Microsoft Technology Licensing, Llc | Interpreting text-based similarity |
| CN113094200A (en) * | 2021-06-07 | 2021-07-09 | 腾讯科技（深圳）有限公司 | Application program fault prediction method and device |
| CN114201920A (en) * | 2021-12-15 | 2022-03-18 | 苏州华光智控电子科技有限公司 | Laser cutting numerical control system fault diagnosis method based on digital twinning and deep transfer learning |
| CN114548803A (en) * | 2022-02-28 | 2022-05-27 | 浙江绿城未来数智科技有限公司 | Future community digital twin management system based on AI digital people |
Non-Patent Citations (2)
| Title |
|---|
| MENG, FQ等: "Creating Knowledge Graph of Electric Power Equipment Faults Based on BERT-BiLSTM-CRF Model", 《 JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY》, 13 March 2022 (2022-03-13) * |
| 徐济仁;刘敬芝;牛纪海;江从俊;: "电子设备故障诊断技术综述", 电子工艺技术, no. 05, 18 September 2008 (2008-09-18) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116614344A (en) * | 2023-05-29 | 2023-08-18 | 北京城建智控科技股份有限公司 | Fault diagnosis method and system based on digital twinning |
| CN116614344B (en) * | 2023-05-29 | 2024-03-26 | 北京城建智控科技股份有限公司 | Fault diagnosis method and system based on digital twinning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116016122B (en) | 2024-10-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116016122B (en) | Network fault solution prediction method, device, equipment and storage medium | |
| CN106104636A (en) | Use the automobile detection system of network computing infrastructure | |
| US11989700B2 (en) | Management methods and management internet of things systems for maintenance personnel of smart gas | |
| CN111860893B (en) | Data processing method and device | |
| CN116128472A (en) | Power distribution room fault operation and maintenance management method and system | |
| US20230087199A1 (en) | Method and internet of things system of charging service for new energy vehicle in smart city | |
| CN114727313A (en) | Information processing method, device, equipment and storage medium | |
| CN111882119A (en) | Battery SOH prediction optimization method based on SA-BP neural network | |
| CN114779747B (en) | Vehicle fault cause determining system and method | |
| CN117791596A (en) | Power dispatching method, system, electronic equipment and storage medium of fault power grid | |
| CN114331384A (en) | Power grid topology data acquisition method and device, computer equipment and storage medium | |
| CN103616877A (en) | Monitoring diagnostic method and system for energy pipe network | |
| CN113704058A (en) | Business model monitoring method and device and electronic equipment | |
| CN117670106A (en) | Energy consumption analysis method, device, chip and terminal based on digital twin system | |
| CN104346763A (en) | Graduate education and career guidance database management method | |
| KR101872826B1 (en) | Apparatus for supporting rejoining through machine learning and the method by using the same | |
| CN115115131A (en) | Multi-center power system fault prediction method and system based on transfer learning | |
| CN114492905A (en) | Customer appeal rate prediction method and device based on multi-model fusion and computer equipment | |
| CN112733450A (en) | Method and device for analyzing node faults in power network | |
| CN109492906A (en) | Response executes reliability estimation method, device and equipment | |
| CN115865714B (en) | Network demand prediction and network scheduling method | |
| CN116170349A (en) | Communication network traffic prediction method and device | |
| CN114037355B (en) | Optimal dispatching method and system for generating vehicle, electronic equipment and storage medium | |
| JP2024098405A (en) | Maintenance support system, maintenance support method, and program | |
| CN115719176A (en) | Multi-time scale self-adaptive power supply reliability control method and system |
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 |