CN114840386A - Log monitoring method and device based on deconvolution neural network - Google Patents
Log monitoring method and device based on deconvolution neural network Download PDFInfo
- Publication number
- CN114840386A CN114840386A CN202210508360.7A CN202210508360A CN114840386A CN 114840386 A CN114840386 A CN 114840386A CN 202210508360 A CN202210508360 A CN 202210508360A CN 114840386 A CN114840386 A CN 114840386A
- Authority
- CN
- China
- Prior art keywords
- log
- monitored
- section
- neural network
- subimage
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/302—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a software system
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a log monitoring method and a log monitoring device based on a deconvolution neural network, which relate to the technical field of artificial intelligence, wherein the method comprises the following steps: acquiring a log image to be monitored; performing segmentation processing on the log image to be monitored to obtain a plurality of log subimages to be monitored; inputting each section of log subimage to be monitored into a deconvolution neural network model for self-adaptive key feature extraction to obtain a key feature image corresponding to each section of log subimage to be monitored; the deconvolution neural network model is generated by pre-training a plurality of log image samples; performing keyword log monitoring on the key characteristic image corresponding to each section of log subimage to be monitored to obtain a log monitoring result; and the log monitoring result is used for monitoring the running state of the program. The invention can effectively monitor the abnormal log in time.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to a log monitoring method and device based on a deconvolution neural network.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
The log is extremely important in the program development work, and in order to monitor the program running state in real time and solve the problems in time, the log monitoring is very important in production and life. At present, the log monitoring methods are of various types, and most of the log monitoring methods use behavior anomaly detection and block chains as tools, wherein the behavior anomaly detection method has the following principle: firstly, preprocessing the log (unifying log structures and clustering), then generating a behavior pattern, acquiring an abnormal index, and comparing the abnormal index with a threshold value to determine whether to send out an abnormal early warning. The basic principle of the block chain-based log monitoring method is as follows: and sending the log file to a block chain network, analyzing the log file, verifying reliability and authenticity and the like. The existing log monitoring method has the following defects: most of the existing log monitoring methods are only used for discovering abnormity, cannot carry out real-time monitoring and timely early warning, and have the advantages of small application range and poor performance.
Disclosure of Invention
The embodiment of the invention provides a log monitoring method based on a deconvolution neural network, which is used for effectively monitoring abnormal logs in time and comprises the following steps:
acquiring a log image to be monitored;
performing segmentation processing on the log image to be monitored to obtain a plurality of log subimages to be monitored;
inputting each section of log subimage to be monitored into a deconvolution neural network model for self-adaptive key feature extraction to obtain a key feature image corresponding to each section of log subimage to be monitored; the deconvolution neural network model is generated by pre-training a plurality of log image samples;
performing keyword log monitoring on the key characteristic image corresponding to each section of log subimage to be monitored to obtain a log monitoring result; and the log monitoring result is used for monitoring the running state of the program.
The embodiment of the invention also provides a log monitoring device based on the deconvolution neural network, which is used for effectively monitoring the abnormal logs in time and comprises the following components:
the acquisition unit is used for acquiring a log image to be monitored;
the segmentation processing unit is used for performing segmentation processing on the log image to be monitored to obtain a plurality of log subimages to be monitored;
the extraction unit is used for inputting each section of log subimage to be monitored into the deconvolution neural network model for self-adaptive key feature extraction to obtain a key feature image corresponding to each section of log subimage to be monitored; the deconvolution neural network model is generated by pre-training a plurality of log image samples;
the monitoring unit is used for carrying out keyword log monitoring on the key feature image corresponding to each section of log subimage to be monitored to obtain a log monitoring result; and the log monitoring result is used for monitoring the running state of the program.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can be run on the processor, wherein the log monitoring method based on the deconvolution neural network is realized when the processor executes the computer program.
The embodiment of the invention also provides a computer readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the log monitoring method based on the deconvolution neural network is realized.
An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, the method for monitoring logs based on a deconvolution neural network is implemented.
In the embodiment of the invention, the log monitoring scheme based on the deconvolution neural network comprises the following steps: acquiring a log image to be monitored; performing segmentation processing on the log image to be monitored to obtain a plurality of log subimages to be monitored; inputting each section of log subimage to be monitored into a deconvolution neural network model for self-adaptive key feature extraction to obtain a key feature image corresponding to each section of log subimage to be monitored; the deconvolution neural network model is generated by pre-training a plurality of log image samples; performing keyword log monitoring on the key characteristic image corresponding to each section of log subimage to be monitored to obtain a log monitoring result; the log monitoring result is used for monitoring the running state of the program, and abnormal logs can be effectively monitored in time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
FIG. 1 is a schematic flow chart of a log monitoring method based on a deconvolution neural network according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a log monitoring method based on a deconvolution neural network according to another embodiment of the present invention;
FIG. 3 is a schematic flow chart of a log monitoring method based on a deconvolution neural network according to another embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a log monitoring apparatus based on a deconvolution neural network according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a log monitoring apparatus based on a deconvolution neural network according to another embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
The embodiment of the invention provides a log monitoring scheme based on a deconvolution neural network, which utilizes a self-adaptive deconvolution neural network to extract important information features of segmented log images, captures key characteristics for real-time monitoring and ensures the running state of a program. The log monitoring scheme based on the deconvolution neural network is described in detail below.
Fig. 1 is a schematic flow chart of a log monitoring method based on a deconvolution neural network in an embodiment of the present invention, and as shown in fig. 1, the method includes the following steps:
step 101: acquiring a log image to be monitored;
step 102: performing segmentation processing on the log image to be monitored to obtain a plurality of log subimages to be monitored;
step 103: inputting each section of log subimage to be monitored into a deconvolution neural network model for self-adaptive key feature extraction to obtain a key feature image corresponding to each section of log subimage to be monitored; the deconvolution neural network model is generated by pre-training a plurality of log image samples;
step 104: performing keyword log monitoring on the key characteristic image corresponding to each section of log subimage to be monitored to obtain a log monitoring result; and the log monitoring result is used for monitoring the running state of the program.
The log monitoring method based on the deconvolution neural network provided by the embodiment of the invention is operated as follows: acquiring a log image to be monitored; performing segmentation processing on the log image to be monitored to obtain a plurality of log subimages to be monitored; inputting each section of log subimage to be monitored into a deconvolution neural network model for self-adaptive key feature extraction to obtain a key feature image corresponding to each section of log subimage to be monitored; the deconvolution neural network model is generated by pre-training a plurality of log image samples; performing keyword log monitoring on the key feature image corresponding to each section of log sub-image to be monitored to obtain a log monitoring result; the log monitoring result is used for monitoring the running state of the program, and abnormal logs can be effectively monitored in time. The log monitoring method based on the deconvolution neural network is described in detail below.
In consideration of the technical problem that if the information in the log is too much, the extraction of the character outline features is easy to be unobvious, therefore, the inventor provides a scheme for partitioning the log, improving the accuracy rate of keyword outline recognition and further improving the log monitoring accuracy.
Firstly, before the invention is implemented, a deconvolution neural network model is established in advance, the network structure of the model has high self-adaptive characteristics, the network parameters are variable along with the network input, and the optimal network parameters are determined based on the principle of objective function minimization in multiple iterations, so that the design expands the application scene of the neural network. The input of the deconvolution neural network model is a log sub-image, and the output is a key feature image corresponding to the log sub-image.
In an embodiment, the segmenting processing the log image to be monitored to obtain a plurality of log sub-images to be monitored may include: and according to the precision requirement of the real-time monitoring, performing segmentation processing on the log image to be monitored to obtain a plurality of log subimages to be monitored.
During specific implementation, monitoring requirements and real-time precision requirements are determined, log image preprocessing (segmentation, denoising and normalization), feature extraction and keyword monitoring are carried out on the basis, and the precision of log monitoring is further improved.
In an embodiment, as shown in fig. 2, the log monitoring method based on the deconvolution neural network may further include step 201: performing log image preprocessing on each section of log subimage to be monitored to obtain each preprocessed section of log subimage to be monitored;
inputting each section of log subimage to be monitored into a deconvolution neural network model for self-adaptive key feature extraction, and obtaining a key feature image corresponding to each section of log subimage to be monitored, wherein the method comprises the following steps: and inputting each preprocessed section of log subimage to be monitored into a deconvolution neural network model for self-adaptive key feature extraction to obtain a key feature image corresponding to each section of log subimage to be monitored.
In specific implementation, each section of log sub-image to be monitored is input into the deconvolution neural network model for self-adaptive key feature extraction after being subjected to log image preprocessing, so that the log monitoring precision is further improved. In addition, regarding the extraction of key features: the log picture contains a plurality of Chinese characters and English characters, and the character outline characteristics can be effectively enhanced by extracting the texture characteristics in the horizontal direction and the vertical direction of the picture, so that the log picture is beneficial to identifying abnormal keywords of the log.
In an embodiment, the performing log image preprocessing on each section of log sub-image to be monitored to obtain each preprocessed section of log sub-image to be monitored may include: and denoising and normalizing the log image of each section of log subimage to be monitored to obtain each section of pre-processed log subimage to be monitored.
In specific implementation, the operation of performing log image preprocessing on each section of log sub-image to be monitored may include: each section of log subimage to be monitored is preprocessed in a denoising and normalization mode, and therefore the accuracy of log monitoring is further improved.
In an embodiment, as shown in fig. 3, inputting each section of log sub-image to be monitored into a deconvolution neural network model to perform adaptive key feature extraction, so as to obtain a key feature image corresponding to each section of log sub-image to be monitored, which may include: inputting each section of log subimage to be monitored into a deconvolution neural network model, and extracting key features of the image based on the principle of minimization of a target function to obtain a key feature image corresponding to each section of log subimage to be monitored; the objective function is a deconvolution neural network objective function designed based on requirements.
In specific implementation, a target function of the deconvolution neural network is designed, the processed image is input into the deconvolution neural network, the characteristic of the image is extracted based on the principle of minimization of the target function, an important characteristic image is obtained, and the precision of log monitoring is further improved. The form of the objective function can be various, and the objective function is established mainly based on the principle of minimization.
In the step 104, (1) if the information in the log is too much, the extraction of the character outline features is easy to be unobvious, so that the log is partitioned, and the keyword outline identification accuracy is improved. The trained deconvolution neural network model has 'memory' of abnormal keywords, and the characteristic is applied to key feature image recognition to judge whether the key feature image has the abnormal keywords so as to determine whether to alarm. (2) The keywords may include: the log monitoring results obtained in (3) are two outputs of 'abnormal existence' and 'abnormal nonexistence'.
In order to understand how the present invention is implemented, the overall flow of the log monitoring method based on the deconvolution neural network is described below.
The first step is as follows: segmenting the log image according to the differentiation requirement, and preprocessing (denoising, normalizing and the like) the segmented image;
the second step is that: inputting the processed image into a deconvolution neural network for self-adaptive important feature extraction to obtain a feature image;
the third step: and monitoring the key words of the characteristic images, following the running state in time and finding running problems.
In order to implement the embodiment of the present invention, the embodiment of the present invention may include the following modules:
the log preprocessing module: blocking the acquired log image according to the real-time precision requirement, and denoising and normalizing the blocked image;
a feature extraction module: designing a target function according to requirements, inputting the processed log image into a deconvolution neural network for feature extraction based on a minimization principle, and obtaining an important feature image;
a monitoring result feedback module: and carrying out keyword monitoring on the characteristic image and feeding back a monitoring result.
And a log preprocessing module is added, so that the monitoring interference caused by redundant information in the log is favorably reduced.
Based on the above design of the modular rapid, the log monitoring method based on the deconvolution neural network may have the following flow:
1. inputting the log image into a log preprocessing module: partitioning the image based on the accuracy required by real-time performance, and then carrying out denoising, normalization and other processing;
2. inputting the processed image into a feature extraction module: designing a target function of a deconvolution neural network, inputting the processed image into the deconvolution neural network, and extracting the features of the image based on the principle of minimization of the target function to obtain an important feature image;
3. inputting the characteristic image into a monitoring result feedback module: and carrying out keyword monitoring on the characteristic image and feeding back a monitoring result.
In summary, the log monitoring method based on the deconvolution neural network provided by the embodiment of the present invention has the advantages that: the log image is preprocessed based on requirements, important information of the image is extracted by using a deconvolution neural network with high adaptivity, and then keyword monitoring is carried out on the characteristic image to obtain a monitoring result. The invention has wide application range and strong practicability.
According to the technical scheme, the data acquisition, storage, use, processing and the like meet relevant regulations of national laws and regulations.
The embodiment of the invention also provides a log monitoring device based on the deconvolution neural network, which is described in the following embodiment. Because the principle of the device for solving the problems is similar to the log monitoring method based on the deconvolution neural network, the implementation of the device can refer to the implementation of the log monitoring method based on the deconvolution neural network, and repeated parts are not repeated.
Fig. 4 is a schematic structural diagram of a log monitoring apparatus based on a deconvolution neural network in an embodiment of the present invention, and as shown in fig. 4, the apparatus includes:
the acquisition unit 01 is used for acquiring a log image to be monitored;
the segmentation processing unit 02 is used for performing segmentation processing on the log image to be monitored to obtain a plurality of log subimages to be monitored;
the extraction unit 03 is used for inputting each section of log subimage to be monitored into the deconvolution neural network model for adaptive key feature extraction to obtain a key feature image corresponding to each section of log subimage to be monitored; the deconvolution neural network model is generated by pre-training a plurality of log image samples;
the monitoring unit 04 is configured to perform keyword log monitoring on the key feature image corresponding to each section of log sub-image to be monitored, so as to obtain a log monitoring result; and the log monitoring result is used for monitoring the running state of the program.
In one embodiment, the segmentation processing unit is specifically configured to: and according to the precision requirement of the real-time monitoring, performing segmentation processing on the log image to be monitored to obtain a plurality of log subimages to be monitored.
In an embodiment, as shown in fig. 5, the log monitoring apparatus based on a deconvolution neural network may further include: the preprocessing unit 21 is configured to perform log image preprocessing on each segment of log sub-image to be monitored to obtain each preprocessed segment of log sub-image to be monitored;
the extraction unit is specifically configured to: and inputting each preprocessed section of log subimage to be monitored into a deconvolution neural network model for self-adaptive key feature extraction to obtain a key feature image corresponding to each section of log subimage to be monitored.
In one embodiment, the preprocessing unit is specifically configured to: and denoising and normalizing the log image of each section of log subimage to be monitored to obtain each preprocessed section of log subimage to be monitored.
In an embodiment, the extracting unit is specifically configured to: inputting each section of log sub-image to be monitored into a deconvolution neural network model, and extracting key features of the image based on the principle of objective function minimization to obtain a key feature image corresponding to each section of log sub-image to be monitored; the objective function is a deconvolution neural network objective function designed based on requirements.
The embodiment of the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can be run on the processor, wherein the log monitoring method based on the deconvolution neural network is realized when the processor executes the computer program.
The embodiment of the invention also provides a computer readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the log monitoring method based on the deconvolution neural network is realized.
An embodiment of the present invention further provides a computer program product, where the computer program product includes a computer program, and when the computer program is executed by a processor, the method for monitoring logs based on a deconvolution neural network is implemented.
In the embodiment of the invention, the log monitoring scheme based on the deconvolution neural network comprises the following steps: acquiring a log image to be monitored; performing segmentation processing on the log image to be monitored to obtain a plurality of log subimages to be monitored; inputting each section of log subimage to be monitored into a deconvolution neural network model for self-adaptive key feature extraction to obtain a key feature image corresponding to each section of log subimage to be monitored; the deconvolution neural network model is generated by pre-training a plurality of log image samples; performing keyword log monitoring on the key characteristic image corresponding to each section of log subimage to be monitored to obtain a log monitoring result; the log monitoring result is used for monitoring the running state of the program, and abnormal logs can be effectively monitored in time.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (13)
1. A log monitoring method based on a deconvolution neural network is characterized by comprising the following steps:
acquiring a log image to be monitored;
performing segmentation processing on the log image to be monitored to obtain a plurality of log subimages to be monitored;
inputting each section of log subimage to be monitored into a deconvolution neural network model for self-adaptive key feature extraction to obtain a key feature image corresponding to each section of log subimage to be monitored; the deconvolution neural network model is generated by pre-training a plurality of log image samples;
performing keyword log monitoring on the key characteristic image corresponding to each section of log subimage to be monitored to obtain a log monitoring result; and the log monitoring result is used for monitoring the running state of the program.
2. The log monitoring method based on the deconvolution neural network of claim 1, wherein the step of performing segmentation processing on the log image to be monitored to obtain a plurality of log sub-images to be monitored comprises: and according to the precision requirement of the real-time monitoring, performing segmentation processing on the log image to be monitored to obtain a plurality of log subimages to be monitored.
3. The deconvolution neural network-based log monitoring method of claim 1, further comprising: performing log image preprocessing on each section of log subimage to be monitored to obtain each preprocessed section of log subimage to be monitored;
inputting each section of log subimage to be monitored into a deconvolution neural network model for self-adaptive key feature extraction to obtain a key feature image corresponding to each section of log subimage to be monitored, wherein the method comprises the following steps: and inputting each preprocessed section of log subimage to be monitored into a deconvolution neural network model for self-adaptive key feature extraction to obtain a key feature image corresponding to each section of log subimage to be monitored.
4. The log monitoring method based on the deconvolution neural network of claim 3, wherein the log image preprocessing is performed on each section of log sub-image to be monitored to obtain each section of log sub-image to be monitored after preprocessing, and the method comprises the following steps: and denoising and normalizing the log image of each section of log subimage to be monitored to obtain each section of pre-processed log subimage to be monitored.
5. The log monitoring method based on the deconvolution neural network of claim 1, wherein each section of log sub-image to be monitored is input into a deconvolution neural network model for adaptive key feature extraction, so as to obtain a key feature image corresponding to each section of log sub-image to be monitored, and the method comprises the following steps: inputting each section of log subimage to be monitored into a deconvolution neural network model, and extracting key features of the image based on the principle of minimization of a target function to obtain a key feature image corresponding to each section of log subimage to be monitored; the objective function is a deconvolution neural network objective function designed based on requirements.
6. A log monitoring apparatus based on a deconvolution neural network, comprising:
the acquisition unit is used for acquiring a log image to be monitored;
the sectional processing unit is used for performing sectional processing on the log image to be monitored to obtain a plurality of sections of log sub-images to be monitored;
the extraction unit is used for inputting each section of log subimage to be monitored into the deconvolution neural network model for self-adaptive key feature extraction to obtain a key feature image corresponding to each section of log subimage to be monitored; the deconvolution neural network model is generated by pre-training according to a plurality of log image samples;
the monitoring unit is used for carrying out keyword log monitoring on the key feature image corresponding to each section of log subimage to be monitored to obtain a log monitoring result; and the log monitoring result is used for monitoring the running state of the program.
7. The deconvolution neural network-based log monitoring device of claim 6, wherein the segmentation processing unit is specifically configured to: and according to the precision requirement of the real-time monitoring, performing segmentation processing on the log image to be monitored to obtain a plurality of log subimages to be monitored.
8. The deconvolution neural network-based log monitoring apparatus of claim 6, further comprising: the preprocessing unit is used for preprocessing the log image of each section of log subimage to be monitored to obtain each preprocessed section of log subimage to be monitored;
the extraction unit is specifically configured to: and inputting each preprocessed section of log subimage to be monitored into a deconvolution neural network model for self-adaptive key feature extraction to obtain a key feature image corresponding to each section of log subimage to be monitored.
9. The deconvolution neural network-based log monitoring device of claim 8, wherein the preprocessing unit is specifically configured to: and denoising and normalizing the log image of each section of log subimage to be monitored to obtain each section of pre-processed log subimage to be monitored.
10. The deconvolution neural network-based log monitoring device of claim 6, wherein the extraction unit is specifically configured to: inputting each section of log subimage to be monitored into a deconvolution neural network model, and extracting key features of the image based on the principle of minimization of a target function to obtain a key feature image corresponding to each section of log subimage to be monitored; the objective function is a deconvolution neural network objective function designed based on requirements.
11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the method of any one of claims 1 to 5 when executing the computer program.
12. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program which, when executed by a processor, implements the method of any of claims 1 to 5.
13. A computer program product, characterized in that the computer program product comprises a computer program which, when being executed by a processor, carries out the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210508360.7A CN114840386A (en) | 2022-05-11 | 2022-05-11 | Log monitoring method and device based on deconvolution neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210508360.7A CN114840386A (en) | 2022-05-11 | 2022-05-11 | Log monitoring method and device based on deconvolution neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114840386A true CN114840386A (en) | 2022-08-02 |
Family
ID=82569053
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210508360.7A Pending CN114840386A (en) | 2022-05-11 | 2022-05-11 | Log monitoring method and device based on deconvolution neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114840386A (en) |
-
2022
- 2022-05-11 CN CN202210508360.7A patent/CN114840386A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111931179B (en) | Cloud malicious program detection system and method based on deep learning | |
| CN113742205B (en) | Code vulnerability intelligent detection method based on man-machine cooperation | |
| CN110866318A (en) | Dangerous rock instability mode discrimination method and device based on deep learning technology | |
| CN109635823A (en) | The method and apparatus and engineering machinery of elevator disorder cable for identification | |
| CN111177731A (en) | Software source code vulnerability detection method based on artificial neural network | |
| CN113870207A (en) | Cutter detection method, device, computer equipment and storage medium | |
| CN115994099A (en) | Automatic checking method, device and equipment for numerical control machine tool codes and storage medium | |
| CN118262282A (en) | Visual image information extraction method and system for underground fully-mechanized mining face of coal mine | |
| US10043108B2 (en) | Method and apparatus for detecting and classifying active matrix organic light emitting diode panel | |
| CN115984158A (en) | Defect analysis method and device, electronic equipment and computer readable storage medium | |
| CN117114420A (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN117938430A (en) | Webshell detection method based on Bert model | |
| CN114840386A (en) | Log monitoring method and device based on deconvolution neural network | |
| CN116630809A (en) | Geological radar data automatic identification method and system based on intelligent image analysis | |
| CN115766090A (en) | Multi-feature fusion neural network security detection method | |
| CN113591856A (en) | Bill picture processing method and device | |
| CN112597498A (en) | Webshell detection method, system and device and readable storage medium | |
| EP2573694A1 (en) | Conversion method and system | |
| CN117592061B (en) | Source code security detection method and device integrating code vulnerability characteristics and attribute graphs | |
| CN114118195B (en) | Method and system for identifying vibration of breaker operating mechanism based on decision tree | |
| CN118378896B (en) | Intelligent analysis method and system for geological disaster debugging and investigation report | |
| CN111292293B (en) | Intelligent manipulator fault detection method and system | |
| Yu et al. | Research on surface defect detection method of solid wood board based on improved YOLOv5s | |
| CN115098348A (en) | Real-time anomaly detection method and device for high-risk user instruction | |
| CN118587496A (en) | Automatic part machining precision recognition system and method based on computer vision |
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 |