CN116980307A - Operation and maintenance fault analysis method and device and computer equipment - Google Patents
Operation and maintenance fault analysis method and device and computer equipment Download PDFInfo
- Publication number
- CN116980307A CN116980307A CN202211210976.2A CN202211210976A CN116980307A CN 116980307 A CN116980307 A CN 116980307A CN 202211210976 A CN202211210976 A CN 202211210976A CN 116980307 A CN116980307 A CN 116980307A
- Authority
- CN
- China
- Prior art keywords
- maintenance
- maintenance fault
- fault
- time sequence
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 311
- 238000004458 analytical method Methods 0.000 title claims abstract description 27
- 230000001788 irregular Effects 0.000 claims abstract description 61
- 238000012549 training Methods 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims description 43
- 230000002159 abnormal effect Effects 0.000 claims description 35
- 238000004891 communication Methods 0.000 claims description 16
- 238000007781 pre-processing Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 15
- 238000010606 normalization Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 11
- 238000010219 correlation analysis Methods 0.000 claims description 4
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 230000000737 periodic effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000010420 art technique Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
The embodiment of the invention relates to the technical field of artificial intelligence and discloses an operation and maintenance fault analysis method, which comprises the following steps: acquiring an operation and maintenance index sequence to be predicted; the operation and maintenance index sequence to be predicted comprises time sequence data corresponding to a plurality of operation and maintenance indexes; inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model to obtain fault information of a target service; the operation and maintenance fault prediction model comprises an irregular convolution network and an LSTM network; and the operation and maintenance fault prediction model is input into the irregular convolution network according to the historical operation and maintenance fault index sequence sample, and the output convolution result is processed into a one-dimensional vector and input into the LSTM network for training. Through the mode, the embodiment of the invention realizes the effect of accurately predicting the operation and maintenance fault information.
Description
Technical Field
The embodiment of the invention relates to the technical field of artificial intelligence, in particular to an operation and maintenance fault analysis method, an operation and maintenance fault analysis device, computer equipment and a computer readable storage medium.
Background
At present, the existing operation and maintenance fault processing mode is mainly that the related research of the existing time sequence prediction method is relatively perfect, and the statistical machine learning-based method comprises a moving average autoregressive model (ARIMA) and regression prediction. The methods based on deep learning are RNN and LSTM. The ARIMA method is used for realizing prediction aiming at time sequence data statistical analysis, and the accuracy of the method for predicting faults is low.
Therefore, the inventor discovers that the prior art and the processing mechanism cannot meet the actual operation and maintenance requirements, and also cannot meet the development trend of future IT.
Disclosure of Invention
In view of the above problems, embodiments of the present application provide an operation and maintenance fault analysis method, apparatus, computer device, and computer readable storage medium, which are used for solving the technical problem of inaccurate fault prediction in the prior art.
According to an aspect of an embodiment of the present application, there is provided an operation and maintenance fault analysis method, including:
acquiring an operation and maintenance index sequence to be predicted; the operation and maintenance index sequence to be predicted comprises time sequence data corresponding to a plurality of operation and maintenance indexes;
inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model to obtain fault information of a target service; the operation and maintenance fault prediction model comprises an irregular convolution network and an LSTM network; and the operation and maintenance fault prediction model is input into the irregular convolution network according to the historical operation and maintenance fault index sequence sample, and the output convolution result is processed into a one-dimensional vector and input into the LSTM network for training.
In an optional manner, the inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model, and before obtaining fault information of the target service in a future preset time period, the method includes:
Preprocessing initial time sequence data of the historical operation and maintenance fault indexes to obtain preprocessed time sequence data corresponding to each historical operation and maintenance fault index;
analyzing the correlation between each historical operation and maintenance fault index and the service performance of the target service;
according to the correlation, screening a preset number of historical operation and maintenance fault indexes from the historical operation and maintenance fault indexes;
and splicing the preprocessed time sequence data corresponding to the preset number of historical operation and maintenance fault indexes to obtain a historical operation and maintenance fault index sequence sample.
In an optional manner, the preprocessing the initial time sequence data of the historical operation and maintenance fault indexes to obtain preprocessed time sequence data corresponding to each historical operation and maintenance fault index, further includes:
acquiring time sequence data of a plurality of historical operation and maintenance fault indexes;
performing date alignment on the time sequence data of the historical operation and maintenance fault indexes to obtain aligned time sequence data;
carrying out data normalization on the time sequence data by adopting a normal normalization method on the time sequence data after the filling to obtain normalized time sequence data;
and identifying abnormal data in the normalized time sequence data according to the data deviation degree, and replacing the abnormal data with a preset value to obtain the preprocessed time sequence data corresponding to the historical operation and maintenance fault index.
In an optional manner, the analyzing the correlation between each historical operation and maintenance fault indicator and the service performance of the target service includes:
and calculating the correlation between each historical operation and maintenance fault index and the service performance of the target service by adopting the Pearson correlation coefficient.
In an optional manner, the identifying the abnormal data in the normalized time sequence data according to the data deviation degree, and replacing the abnormal data with a preset value to obtain the preprocessed time sequence data corresponding to the historical operation and maintenance fault index includes:
calculating the median value of each data before any one of the normalized time series data;
determining whether the data is abnormal data according to the data deviation degree of any one of the normalized time sequence data and the median value;
and when the data is abnormal data, replacing the data with a preset numerical value.
In an optional manner, the inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model, and before obtaining fault information of the target service in a future preset time period, the method includes:
constructing an irregular convolution network and an LSTM network, and giving different weights to different positions in convolution kernels in the irregular convolution network;
Inputting the historical operation and maintenance fault index sequence sample into the irregular convolution network to obtain a convolution result;
processing the convolution result into a one-dimensional vector, inputting the one-dimensional vector into the LSTM network, and outputting the one-dimensional vector to a one-dimensional full-connection layer through the full-connection layer to obtain a prediction result;
and optimizing the weight, the irregular convolution network and the LSTM network parameters according to the expected result corresponding to the prediction result and the historical operation and maintenance fault index sequence sample, and continuing training to obtain the operation and maintenance fault prediction model.
According to another aspect of the embodiment of the present invention, there is provided an operation and maintenance fault analysis apparatus, including:
the acquisition module is used for acquiring the operation and maintenance index sequence to be predicted; the operation and maintenance index sequence to be predicted comprises time sequence data corresponding to a plurality of operation and maintenance indexes;
the prediction module is used for inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model to obtain fault information of a target service; the operation and maintenance fault prediction model comprises an irregular convolution network and an LSTM network; and the operation and maintenance fault prediction model is input into the irregular convolution network according to the historical operation and maintenance fault index sequence sample, and the output convolution result is processed into a one-dimensional vector and input into the LSTM network for training.
In an alternative, the apparatus further comprises:
the preprocessing module is used for preprocessing the initial time sequence data of the historical operation and maintenance fault indexes to obtain preprocessed time sequence data corresponding to each historical operation and maintenance fault index;
the correlation analysis module is used for analyzing the correlation between each historical operation and maintenance fault index and the service performance of the target service;
the screening module is used for screening a preset number of historical operation and maintenance fault indexes from the historical operation and maintenance fault indexes according to the correlation;
and the splicing module is used for splicing the preprocessed time sequence data corresponding to the historical operation and maintenance fault indexes with the preset quantity to obtain a historical operation and maintenance fault index sequence sample.
According to another aspect of an embodiment of the present invention, there is provided a computer apparatus including: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is used for storing at least one executable instruction, and the executable instruction enables the processor to execute the operation of the operation and maintenance fault analysis method.
According to yet another aspect of an embodiment of the present invention, there is provided a computer readable storage medium having stored therein at least one executable instruction that, when executed on a computer device, causes the computer device to operate as the operation of the operation and maintenance fault analysis method.
According to the embodiment of the invention, the operation and maintenance index sequence to be predicted is obtained; the operation and maintenance index sequence to be predicted comprises time sequence data corresponding to a plurality of operation and maintenance indexes; inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model to obtain fault information of a target service; the operation and maintenance fault prediction model comprises an irregular convolution network and an LSTM network; the operation and maintenance fault prediction model inputs the irregular convolution network according to the historical operation and maintenance fault index sequence sample, processes the output convolution result into a one-dimensional vector, inputs the one-dimensional vector into the LSTM network for training, and can accurately predict operation and maintenance fault information.
The foregoing description is only an overview of the technical solutions of the embodiments of the present invention, and may be implemented according to the content of the specification, so that the technical means of the embodiments of the present invention can be more clearly understood, and the following specific embodiments of the present invention are given for clarity and understanding.
Drawings
The drawings are only for purposes of illustrating embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
Fig. 1 shows a flow chart of an operation and maintenance fault analysis method provided by an embodiment of the present invention;
fig. 2 is a schematic flow chart of an irregular convolution network in the operation and maintenance fault analysis method according to the embodiment of the present invention;
FIG. 3 is a schematic diagram showing model training in an operation and maintenance fault analysis method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of an operation and maintenance fault analysis device according to an embodiment of the present invention;
fig. 5 shows a schematic structural diagram of a computer device according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein.
Fig. 1 shows a flowchart of an operation and maintenance fault analysis method provided by an embodiment of the present invention, where the method is performed by a computer device. The computer device may be a desktop computer, a notebook computer, a tablet computer, an intelligent terminal device, a distributed computing device, etc., and the embodiment of the invention is not particularly limited. As shown in fig. 1, the method comprises the steps of:
Step 110: acquiring an operation and maintenance index sequence to be predicted; the operation and maintenance index sequence to be predicted comprises time sequence data corresponding to a plurality of operation and maintenance indexes.
In the embodiment of the present invention, the operation and maintenance index sequence to be predicted may be time sequence data corresponding to a plurality of operation and maintenance indexes in a current preset time period. For example, the time sequence data of the current preset time period can be composed of the current time sequence data of each operation and maintenance index of the current time and the historical time sequence data of each operation and maintenance index of the preset time period before the current time. The operation and maintenance index comprises a plurality of indexes related to the target service, such as performance indexes including CPU (Central processing Unit) utilization, memory utilization, disk utilization, network delay and the like.
Step 120: and inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model to obtain the fault information of the target service.
The operation and maintenance fault prediction model comprises an irregular convolution network and an LSTM network; and the operation and maintenance fault prediction model is input into the irregular convolution network according to the historical operation and maintenance fault index sequence sample, and the output convolution result is processed into a one-dimensional vector and input into the LSTM network for training.
In the embodiment of the invention, the fault information of the target service is a fault alarm corresponding to the target service.
The embodiment of the invention trains the neural network in advance through the historical operation and maintenance fault index sequence sample to obtain an operation and maintenance fault prediction model. Firstly, data processing is carried out to obtain a historical operation and maintenance fault index sequence sample, wherein the historical operation and maintenance fault index sequence sample comprises time sequence data corresponding to each historical operation and maintenance fault index and corresponding service performance time sequence data. Specifically, the method comprises the following steps:
step 001: preprocessing the initial time sequence data of the historical operation and maintenance fault indexes to obtain preprocessed time sequence data corresponding to each historical operation and maintenance fault index. Firstly, time sequence data of a plurality of historical operation and maintenance fault indexes are acquired. And then, carrying out date filling on the time sequence data of the historical operation and maintenance fault indexes to obtain the filled time sequence data. Specifically, the time sequence data is subjected to date filling, the completeness of the periodic data is ensured, and the filled data is subjected to null value processing. The embodiment of the invention can carry out null filling by a linear interpolation method. And then, the numerical ranges of different indexes are inconsistent, data normalization is needed, a normal normalization method is adopted for the time sequence data after the normalization, and the data normalization is carried out on the time sequence data, so that normalized time sequence data is obtained. And finally, identifying abnormal data in the normalized time sequence data according to the data deviation degree, and replacing the abnormal data with a preset value to obtain the preprocessed time sequence data corresponding to the historical operation and maintenance fault index. Specifically, calculating a median value of each data before any one of the normalized time series data; determining whether the data is abnormal data according to the data deviation degree of any one of the normalized time sequence data and the median value; and when the data is abnormal data, replacing the data with a preset numerical value. Wherein the preset value may be a null value. And when the deviation degree is larger than a preset deviation degree threshold value, determining the data as abnormal data.
The deviation can be calculated by the following formula:
wherein x is i Indicating the i-th value in the time series data,represents the median before the ith value of the sequence.
Step 002: and analyzing the correlation between each historical operation and maintenance fault index and the service performance of the target service. And calculating the correlation between each historical operation and maintenance fault index and the service performance and the like of the target service by adopting the Pearson correlation coefficient. The service performance may be a service response rate, etc. The service performance data of each historical moment can be obtained, so that the time sequence data of the service performance can be obtained. And (3) corresponding the time sequence data of each historical operation and maintenance fault index to the corresponding service performance time sequence, and determining the influence of each historical operation and maintenance fault index on the service performance by adopting the pearson correlation coefficient. If the service response rate is used as a predicted target time sequence, the pearson correlation coefficient is adopted to calculate the correlation between the target sequence and a plurality of operation and maintenance indexes such as the CPU utilization rate, the memory utilization rate, the disk utilization rate, the network delay and the like.
Step 003: and screening a preset number of historical operation and maintenance fault indexes from the historical operation and maintenance fault indexes according to the correlation. According to the correlation, the operation and maintenance index of 5 ranking can be selected as the index data of the service performance corresponding to the target service.
Step 004: and splicing the preprocessed time sequence data corresponding to the preset number of historical operation and maintenance fault indexes to obtain a historical operation and maintenance fault index sequence sample.
Wherein, according to the correlation analysis result, the time sequence data S of each historical moment of the 5 operation and maintenance indexes with highest correlation is obtained 1 ,S 2 ,S 3 ,S 4 ,S 5 ]And transversely splicing to obtain a time sequence data matrix of the historical operation and maintenance indexes, and determining time sequence data of service performance corresponding to the time sequence data matrix of the historical operation and maintenance indexes to form a historical operation and maintenance fault index sequence sample.
As shown in fig. 3, before inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model to obtain fault information of a target service in a preset time period in the future, the embodiment of the invention further includes:
step 005: and constructing an irregular convolution network and an LSTM network, and giving different weights to different positions in convolution kernels in the irregular convolution network. As shown in fig. 2, the convolution network is usually used in the image processing direction to extract the characteristics of the pixel region, and two-dimensional convolution (convolution kernel is 5×5) is adopted, and in the processing process of the convolution network, the maximum pooling processing is adopted.
In order to enable the network to identify the time sequence dislocation problem, the embodiment of the invention applies the method of the irregular convolution network to the time sequence feature extraction and improves the prediction effect. Irregular convolution networks are used in some prior art techniques to address the problem of irregular samples of a target image in image recognition. The embodiment of the invention optimizes different positions in the convolution kernel by giving different weights in the irregular convolution network. In the pooling process, the influence on the target result is relatively large due to the difference of the position weights. According to the embodiment of the invention, an irregular convolution network is adopted, different weights are given to different positions in the time sequence data characteristic matrix, and the position weights are continuously trained and optimized in the training iteration process of the neural network, so that errors caused by time sequence dislocation can be well reduced. To capture the time domain variation of the time series data, the LSTM network is added after the irregular convolution network.
Step and 006: and inputting the historical operation and maintenance fault index sequence samples into the irregular convolution network to obtain a convolution result.
According to the embodiment of the invention, firstly, the historical operation and maintenance fault index sequence samples are input into the irregular convolution network, and the convolution results are obtained through weighting variables at different positions in the convolution kernel.
Step 010: and processing the convolution result into a one-dimensional vector, inputting the one-dimensional vector into the LSTM network, and outputting the one-dimensional vector to a one-dimensional full-connection layer through the full-connection layer to obtain a prediction result. Specifically, the convolution result is reshaped into a one-dimensional vector, then an LSTM network is added, and finally the one-dimensional vector is output to a one-dimensional full-connection layer through the full-connection layer, so that a prediction result is obtained.
Step 011: and optimizing the weight and the parameters of the irregular convolution network and the LSTM network according to the expected result corresponding to the prediction result and the historical operation and maintenance fault index sequence sample, and continuing training to obtain the operation and maintenance fault prediction model.
And calculating a loss function according to the expected result corresponding to the predicted result and the historical operation and maintenance fault index sequence sample, wherein the loss function can adopt a Mean Square Error (MSE). And adjusting the weight and the parameters of the irregular convolution network and the LSTM network according to the loss function, and then continuously inputting the historical operation and maintenance fault index sequence samples for training until the loss function converges or reaches the preset iteration training times, so as to obtain the operation and maintenance fault prediction model of the embodiment of the invention.
After the operation and maintenance fault prediction model is obtained, the operation and maintenance index sequence to be predicted is input into a preset operation and maintenance fault prediction model, and time sequence data of the service performance of the corresponding target service can be obtained. The time sequence data of the service performance of the target service is the time sequence data of the service performance of the target service in a preset time period in the future, and whether operation and maintenance faults exist can be determined according to the time sequence data of the service performance, so that fault information of the target service is obtained. The future preset time period may be a preset time period after the current time, where the future preset time period and the current preset time period are periodic time, and may be periodic time of hours, days, weeks, and the like, which is not limited in particular. For example, the time series data of the service performance of the target service on the next day can be predicted by the operation and maintenance index sequence to be predicted on the current day. In the embodiment of the invention, when the target service is determined to have faults in a preset time period in the future according to the fault information of the target service, alarm information is sent to a user.
According to the embodiment of the invention, the operation and maintenance index sequence to be predicted is obtained; the operation and maintenance index sequence to be predicted comprises time sequence data corresponding to a plurality of operation and maintenance indexes; inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model to obtain fault information of a target service; the operation and maintenance fault prediction model comprises an irregular convolution network and an LSTM network; the operation and maintenance fault prediction model inputs the irregular convolution network according to the historical operation and maintenance fault index sequence sample, processes the output convolution result into a one-dimensional vector, inputs the one-dimensional vector into the LSTM network for training, and can accurately predict operation and maintenance fault information.
Fig. 4 shows a schematic structural diagram of an operation and maintenance fault analysis device according to an embodiment of the present invention. As shown in fig. 4, the apparatus 300 includes:
an obtaining module 310, configured to obtain an operation and maintenance index sequence to be predicted; the operation and maintenance index sequence to be predicted comprises time sequence data corresponding to a plurality of operation and maintenance indexes;
the prediction module 320 is configured to input the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model to obtain fault information of the target service; the operation and maintenance fault prediction model comprises an irregular convolution network and an LSTM network; and the operation and maintenance fault prediction model is input into the irregular convolution network according to the historical operation and maintenance fault index sequence sample, and the output convolution result is processed into a one-dimensional vector and input into the LSTM network for training.
In an alternative, the apparatus further comprises:
the preprocessing module is used for preprocessing the initial time sequence data of the historical operation and maintenance fault indexes to obtain preprocessed time sequence data corresponding to each historical operation and maintenance fault index;
the correlation analysis module is used for analyzing the correlation between each historical operation and maintenance fault index and the service performance of the target service;
the screening module is used for screening a preset number of historical operation and maintenance fault indexes from the historical operation and maintenance fault indexes according to the correlation;
And the splicing module is used for splicing the preprocessed time sequence data corresponding to the historical operation and maintenance fault indexes with the preset quantity to obtain a historical operation and maintenance fault index sequence sample.
In an optional manner, the preprocessing the initial time sequence data of the historical operation and maintenance fault indexes to obtain preprocessed time sequence data corresponding to each historical operation and maintenance fault index, further includes:
acquiring time sequence data of a plurality of historical operation and maintenance fault indexes;
performing date alignment on the time sequence data of the historical operation and maintenance fault indexes to obtain aligned time sequence data;
carrying out data normalization on the time sequence data by adopting a normal normalization method on the time sequence data after the filling to obtain normalized time sequence data;
and identifying abnormal data in the normalized time sequence data according to the data deviation degree, and replacing the abnormal data with a preset value to obtain the preprocessed time sequence data corresponding to the historical operation and maintenance fault index.
In an optional manner, the analyzing the correlation between each historical operation and maintenance fault indicator and the service performance of the target service includes:
and calculating the correlation between each historical operation and maintenance fault index and the service performance of the target service by adopting the Pearson correlation coefficient.
In an optional manner, the identifying the abnormal data in the normalized time sequence data according to the data deviation degree, and replacing the abnormal data with a preset value to obtain the preprocessed time sequence data corresponding to the historical operation and maintenance fault index includes:
calculating the median value of each data before any one of the normalized time series data;
determining whether the data is abnormal data according to the data deviation degree of any one of the normalized time sequence data and the median value;
and when the data is abnormal data, replacing the data with a preset numerical value.
In an optional manner, the inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model, and before obtaining fault information of the target service in a future preset time period, the method includes:
constructing an irregular convolution network and an LSTM network, and giving different weights to different positions in convolution kernels in the irregular convolution network;
inputting the historical operation and maintenance fault index sequence sample into the irregular convolution network to obtain a convolution result;
processing the convolution result into a one-dimensional vector, inputting the one-dimensional vector into the LSTM network, and outputting the one-dimensional vector to a one-dimensional full-connection layer through the full-connection layer to obtain a prediction result;
And optimizing the weight, the irregular convolution network and the LSTM network parameters according to the expected result corresponding to the prediction result and the historical operation and maintenance fault index sequence sample, and continuing training to obtain the operation and maintenance fault prediction model.
The specific working process of the operation and maintenance fault analysis device in the embodiment of the present invention is substantially identical to the flow steps in the above method embodiment, and will not be described herein.
According to the embodiment of the invention, the operation and maintenance index sequence to be predicted is obtained; the operation and maintenance index sequence to be predicted comprises time sequence data corresponding to a plurality of operation and maintenance indexes; inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model to obtain fault information of a target service; the operation and maintenance fault prediction model comprises an irregular convolution network and an LSTM network; the operation and maintenance fault prediction model inputs the irregular convolution network according to the historical operation and maintenance fault index sequence sample, processes the output convolution result into a one-dimensional vector, inputs the one-dimensional vector into the LSTM network for training, and can accurately predict operation and maintenance fault information.
Fig. 5 shows a schematic structural diagram of a computer device according to an embodiment of the present invention, and the specific embodiment of the present invention is not limited to the specific implementation of the computer device.
As shown in fig. 5, the computer device may include: a processor 402, a communication interface (Communications Interface) 404, a memory 406, and a communication bus 408.
Wherein: processor 402, communication interface 404, and memory 406 communicate with each other via communication bus 408. A communication interface 404 for communicating with network elements of other devices, such as clients or other servers. The processor 402 is configured to execute the program 410, and may specifically perform the relevant steps in the above-described embodiment of the operation and maintenance fault analysis method.
In particular, program 410 may include program code including computer-executable instructions.
The processor 402 may be a central processing unit CPU, or a specific integrated circuit ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of the present invention. The one or more processors included in the computer device may be the same type of processor, such as one or more CPUs; but may also be different types of processors such as one or more CPUs and one or more ASICs.
Memory 406 for storing programs 410. Memory 406 may comprise high-speed RAM memory or may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
Program 410 may be specifically invoked by processor 402 to cause a computer device to:
acquiring an operation and maintenance index sequence to be predicted; the operation and maintenance index sequence to be predicted comprises time sequence data corresponding to a plurality of operation and maintenance indexes;
inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model to obtain fault information of a target service; the operation and maintenance fault prediction model comprises an irregular convolution network and an LSTM network; and the operation and maintenance fault prediction model is input into the irregular convolution network according to the historical operation and maintenance fault index sequence sample, and the output convolution result is processed into a one-dimensional vector and input into the LSTM network for training.
In an optional manner, the inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model, and before obtaining fault information of the target service in a future preset time period, the method includes:
preprocessing initial time sequence data of the historical operation and maintenance fault indexes to obtain preprocessed time sequence data corresponding to each historical operation and maintenance fault index;
analyzing the correlation between each historical operation and maintenance fault index and the service performance of the target service;
according to the correlation, screening a preset number of historical operation and maintenance fault indexes from the historical operation and maintenance fault indexes;
And splicing the preprocessed time sequence data corresponding to the preset number of historical operation and maintenance fault indexes to obtain a historical operation and maintenance fault index sequence sample.
In an optional manner, the preprocessing the initial time sequence data of the historical operation and maintenance fault indexes to obtain preprocessed time sequence data corresponding to each historical operation and maintenance fault index, further includes:
acquiring time sequence data of a plurality of historical operation and maintenance fault indexes;
performing date alignment on the time sequence data of the historical operation and maintenance fault indexes to obtain aligned time sequence data;
carrying out data normalization on the time sequence data by adopting a normal normalization method on the time sequence data after the filling to obtain normalized time sequence data;
and identifying abnormal data in the normalized time sequence data according to the data deviation degree, and replacing the abnormal data with a preset value to obtain the preprocessed time sequence data corresponding to the historical operation and maintenance fault index.
In an optional manner, the analyzing the correlation between each historical operation and maintenance fault indicator and the service performance of the target service includes:
and calculating the correlation between each historical operation and maintenance fault index and the service performance of the target service by adopting the Pearson correlation coefficient.
In an optional manner, the identifying the abnormal data in the normalized time sequence data according to the data deviation degree, and replacing the abnormal data with a preset value to obtain the preprocessed time sequence data corresponding to the historical operation and maintenance fault index includes:
calculating the median value of each data before any one of the normalized time series data;
determining whether the data is abnormal data according to the data deviation degree of any one of the normalized time sequence data and the median value;
and when the data is abnormal data, replacing the data with a preset numerical value.
In an optional manner, the inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model, and before obtaining fault information of the target service in a future preset time period, the method includes:
constructing an irregular convolution network and an LSTM network, and giving different weights to different positions in convolution kernels in the irregular convolution network;
inputting the historical operation and maintenance fault index sequence sample into the irregular convolution network to obtain a convolution result;
processing the convolution result into a one-dimensional vector, inputting the one-dimensional vector into the LSTM network, and outputting the one-dimensional vector to a one-dimensional full-connection layer through the full-connection layer to obtain a prediction result;
And optimizing the weight, the irregular convolution network and the LSTM network parameters according to the expected result corresponding to the prediction result and the historical operation and maintenance fault index sequence sample, and continuing training to obtain the operation and maintenance fault prediction model.
According to the embodiment of the invention, the operation and maintenance index sequence to be predicted is obtained; the operation and maintenance index sequence to be predicted comprises time sequence data corresponding to a plurality of operation and maintenance indexes; inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model to obtain fault information of a target service; the operation and maintenance fault prediction model comprises an irregular convolution network and an LSTM network; the operation and maintenance fault prediction model inputs the irregular convolution network according to the historical operation and maintenance fault index sequence sample, processes the output convolution result into a one-dimensional vector, inputs the one-dimensional vector into the LSTM network for training, and can accurately predict operation and maintenance fault information.
The embodiment of the invention provides a computer readable storage medium, which stores at least one executable instruction, and the executable instruction when running on a computer device, causes the computer device to execute the operation and maintenance fault analysis method in any of the method embodiments.
The executable instructions may be particularly useful for causing a computer device to:
acquiring an operation and maintenance index sequence to be predicted; the operation and maintenance index sequence to be predicted comprises time sequence data corresponding to a plurality of operation and maintenance indexes;
inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model to obtain fault information of a target service; the operation and maintenance fault prediction model comprises an irregular convolution network and an LSTM network; and the operation and maintenance fault prediction model is input into the irregular convolution network according to the historical operation and maintenance fault index sequence sample, and the output convolution result is processed into a one-dimensional vector and input into the LSTM network for training.
In an optional manner, the inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model, and before obtaining fault information of the target service in a future preset time period, the method includes:
preprocessing initial time sequence data of the historical operation and maintenance fault indexes to obtain preprocessed time sequence data corresponding to each historical operation and maintenance fault index;
analyzing the correlation between each historical operation and maintenance fault index and the service performance of the target service;
according to the correlation, screening a preset number of historical operation and maintenance fault indexes from the historical operation and maintenance fault indexes;
And splicing the preprocessed time sequence data corresponding to the preset number of historical operation and maintenance fault indexes to obtain a historical operation and maintenance fault index sequence sample.
In an optional manner, the preprocessing the initial time sequence data of the historical operation and maintenance fault indexes to obtain preprocessed time sequence data corresponding to each historical operation and maintenance fault index, further includes:
acquiring time sequence data of a plurality of historical operation and maintenance fault indexes;
performing date alignment on the time sequence data of the historical operation and maintenance fault indexes to obtain aligned time sequence data;
carrying out data normalization on the time sequence data by adopting a normal normalization method on the time sequence data after the filling to obtain normalized time sequence data;
and identifying abnormal data in the normalized time sequence data according to the data deviation degree, and replacing the abnormal data with a preset value to obtain the preprocessed time sequence data corresponding to the historical operation and maintenance fault index.
In an optional manner, the analyzing the correlation between each historical operation and maintenance fault indicator and the service performance of the target service includes:
and calculating the correlation between each historical operation and maintenance fault index and the service performance of the target service by adopting the Pearson correlation coefficient.
In an optional manner, the identifying the abnormal data in the normalized time sequence data according to the data deviation degree, and replacing the abnormal data with a preset value to obtain the preprocessed time sequence data corresponding to the historical operation and maintenance fault index includes:
calculating the median value of each data before any one of the normalized time series data;
determining whether the data is abnormal data according to the data deviation degree of any one of the normalized time sequence data and the median value;
and when the data is abnormal data, replacing the data with a preset numerical value.
In an optional manner, the inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model, and before obtaining fault information of the target service in a future preset time period, the method includes:
constructing an irregular convolution network and an LSTM network, and giving different weights to different positions in convolution kernels in the irregular convolution network;
inputting the historical operation and maintenance fault index sequence sample into the irregular convolution network to obtain a convolution result;
processing the convolution result into a one-dimensional vector, inputting the one-dimensional vector into the LSTM network, and outputting the one-dimensional vector to a one-dimensional full-connection layer through the full-connection layer to obtain a prediction result;
And optimizing the weight, the irregular convolution network and the LSTM network parameters according to the expected result corresponding to the prediction result and the historical operation and maintenance fault index sequence sample, and continuing training to obtain the operation and maintenance fault prediction model.
According to the embodiment of the invention, the operation and maintenance index sequence to be predicted is obtained; the operation and maintenance index sequence to be predicted comprises time sequence data corresponding to a plurality of operation and maintenance indexes; inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model to obtain fault information of a target service; the operation and maintenance fault prediction model comprises an irregular convolution network and an LSTM network; the operation and maintenance fault prediction model inputs the irregular convolution network according to the historical operation and maintenance fault index sequence sample, processes the output convolution result into a one-dimensional vector, inputs the one-dimensional vector into the LSTM network for training, and can accurately predict operation and maintenance fault information.
The embodiment of the invention provides an operation and maintenance fault analysis device which is used for executing the operation and maintenance fault analysis method.
Embodiments of the present invention provide a computer program that may be invoked by a processor to cause a computer device to perform the operation and maintenance fault analysis method of any of the method embodiments described above.
Embodiments of the present invention provide a computer program product comprising a computer program stored on a computer readable storage medium, the computer program comprising program instructions which, when run on a computer, cause the computer to perform the method of operation and maintenance fault analysis in any of the method embodiments described above.
The algorithms or displays presented herein are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with the teachings herein. The required structure for a construction of such a system is apparent from the description above. In addition, embodiments of the present invention are not directed to any particular programming language. It will be appreciated that the teachings of the present invention described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the above description of exemplary embodiments of the invention, various features of the embodiments of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component, and they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order. These words may be interpreted as names. The steps in the above embodiments should not be construed as limiting the order of execution unless specifically stated.
Claims (10)
1. An operation and maintenance fault analysis method, characterized in that the method comprises:
acquiring an operation and maintenance index sequence to be predicted; the operation and maintenance index sequence to be predicted comprises time sequence data corresponding to a plurality of operation and maintenance indexes;
Inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model to obtain fault information of a target service; the operation and maintenance fault prediction model comprises an irregular convolution network and an LSTM network; and the operation and maintenance fault prediction model is input into the irregular convolution network according to the historical operation and maintenance fault index sequence sample, and the output convolution result is processed into a one-dimensional vector and input into the LSTM network for training.
2. The method according to claim 1, wherein the inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model, before obtaining fault information of the target service in a future preset time period, includes:
preprocessing initial time sequence data of the historical operation and maintenance fault indexes to obtain preprocessed time sequence data corresponding to each historical operation and maintenance fault index;
analyzing the correlation between each historical operation and maintenance fault index and the service performance of the target service;
according to the correlation, screening a preset number of historical operation and maintenance fault indexes from the historical operation and maintenance fault indexes;
and splicing the preprocessed time sequence data corresponding to the preset number of historical operation and maintenance fault indexes to obtain a historical operation and maintenance fault index sequence sample.
3. The method of claim 2, wherein preprocessing the initial time sequence data of the historical operation and maintenance fault indexes to obtain preprocessed time sequence data corresponding to each historical operation and maintenance fault index, further comprises:
acquiring time sequence data of a plurality of historical operation and maintenance fault indexes;
performing date alignment on the time sequence data of the historical operation and maintenance fault indexes to obtain aligned time sequence data;
carrying out data normalization on the time sequence data by adopting a normal normalization method on the time sequence data after the filling to obtain normalized time sequence data;
and identifying abnormal data in the normalized time sequence data according to the data deviation degree, and replacing the abnormal data with a preset value to obtain the preprocessed time sequence data corresponding to the historical operation and maintenance fault index.
4. The method of claim 2, wherein said analyzing correlations between each historical operational failure indicator and the traffic performance of the target traffic comprises:
and calculating the correlation between each historical operation and maintenance fault index and the service performance of the target service by adopting the Pearson correlation coefficient.
5. The method according to claim 2, wherein the identifying the abnormal data in the normalized time series data according to the data deviation degree and replacing the abnormal data with a preset value to obtain the preprocessed time series data corresponding to the historical operation and maintenance fault index includes:
Calculating the median value of each data before any one of the normalized time series data;
determining whether the data is abnormal data according to the data deviation degree of any one of the normalized time sequence data and the median value;
and when the data is abnormal data, replacing the data with a preset numerical value.
6. The method according to claim 1, wherein the inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model, before obtaining fault information of the target service in a future preset time period, includes:
constructing an irregular convolution network and an LSTM network, and giving different weights to different positions in convolution kernels in the irregular convolution network;
inputting the historical operation and maintenance fault index sequence sample into the irregular convolution network to obtain a convolution result;
processing the convolution result into a one-dimensional vector, inputting the one-dimensional vector into the LSTM network, and outputting the one-dimensional vector to a one-dimensional full-connection layer through the full-connection layer to obtain a prediction result;
and optimizing the weight, the irregular convolution network and the LSTM network parameters according to the expected result corresponding to the prediction result and the historical operation and maintenance fault index sequence sample, and continuing training to obtain the operation and maintenance fault prediction model.
7. An operation and maintenance fault analysis device, characterized in that the device comprises:
the acquisition module is used for acquiring the operation and maintenance index sequence to be predicted; the operation and maintenance index sequence to be predicted comprises time sequence data corresponding to a plurality of operation and maintenance indexes;
the prediction module is used for inputting the operation and maintenance index sequence to be predicted into a preset operation and maintenance fault prediction model to obtain fault information of a target service; the operation and maintenance fault prediction model comprises an irregular convolution network and an LSTM network; and the operation and maintenance fault prediction model is input into the irregular convolution network according to the historical operation and maintenance fault index sequence sample, and the output convolution result is processed into a one-dimensional vector and input into the LSTM network for training.
8. The apparatus of claim 5, wherein the apparatus further comprises:
the preprocessing module is used for preprocessing the initial time sequence data of the historical operation and maintenance fault indexes to obtain preprocessed time sequence data corresponding to each historical operation and maintenance fault index;
the correlation analysis module is used for analyzing the correlation between each historical operation and maintenance fault index and the service performance of the target service;
the screening module is used for screening a preset number of historical operation and maintenance fault indexes from the historical operation and maintenance fault indexes according to the correlation;
And the splicing module is used for splicing the preprocessed time sequence data corresponding to the historical operation and maintenance fault indexes with the preset quantity to obtain a historical operation and maintenance fault index sequence sample.
9. A computer device, comprising: the device comprises a processor, a memory, a communication interface and a communication bus, wherein the processor, the memory and the communication interface complete communication with each other through the communication bus;
the memory is configured to store at least one executable instruction that causes the processor to perform the operations of the operation and maintenance fault analysis method according to any one of claims 1 to 6.
10. A computer readable storage medium, wherein at least one executable instruction is stored in the storage medium, which when executed on a computer device, causes the computer device to perform the operations of the operation and maintenance fault analysis method according to any one of claims 1-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211210976.2A CN116980307A (en) | 2022-09-30 | 2022-09-30 | Operation and maintenance fault analysis method and device and computer equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211210976.2A CN116980307A (en) | 2022-09-30 | 2022-09-30 | Operation and maintenance fault analysis method and device and computer equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116980307A true CN116980307A (en) | 2023-10-31 |
Family
ID=88480299
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211210976.2A Pending CN116980307A (en) | 2022-09-30 | 2022-09-30 | Operation and maintenance fault analysis method and device and computer equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116980307A (en) |
-
2022
- 2022-09-30 CN CN202211210976.2A patent/CN116980307A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10360517B2 (en) | Distributed hyperparameter tuning system for machine learning | |
US11650968B2 (en) | Systems and methods for predictive early stopping in neural network training | |
CN113541985B (en) | Internet of things fault diagnosis method, model training method and related devices | |
US20230092453A1 (en) | Parameter updating method and apparatus and storage medium | |
WO2023207411A1 (en) | Traffic determination method and apparatus based on spatio-temporal data, and device and medium | |
CN116684330A (en) | Traffic prediction method, device, equipment and storage medium based on artificial intelligence | |
CN114962390A (en) | Hydraulic system fault diagnosis method and system and working machine | |
CN111522736A (en) | Software defect prediction method and device, electronic equipment and computer storage medium | |
CN113326177A (en) | Index anomaly detection method, device, equipment and storage medium | |
CN116304884B (en) | Spacecraft telemetry data health prediction method, system, equipment and storage medium | |
US20230161653A1 (en) | Method of managing system health | |
CN111783883A (en) | Abnormal data detection method and device | |
CN116739154A (en) | Fault prediction method and related equipment thereof | |
CN113825165A (en) | 5G slice network congestion early warning method and device based on time chart network | |
CN116980307A (en) | Operation and maintenance fault analysis method and device and computer equipment | |
CN112203311A (en) | Network element abnormity diagnosis method, device, equipment and computer storage medium | |
CN111190800B (en) | Method, system, device and storage medium for predicting batch operation duration of host | |
CN116992937A (en) | Neural network model restoration method and related equipment | |
CN113535522A (en) | Abnormal condition detection method, device and equipment | |
US20240152805A1 (en) | Systems, methods, and non-transitory computer-readable storage devices for training deep learning and neural network models using overfitting detection and prevention | |
CN115640336B (en) | Business big data mining method, system and cloud platform | |
CN117058498B (en) | Training method of segmentation map evaluation model, and segmentation map evaluation method and device | |
CN111325278B (en) | Image processing method, device and storage medium | |
CN111382761B (en) | CNN-based detector, image detection method and terminal | |
CN115345637A (en) | Consumption prediction method, consumption prediction device, electronic equipment and computer readable storage medium |
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 |