CN116824515B - Graphic fault diagnosis method and device, electronic equipment and storage medium - Google Patents
Graphic fault diagnosis method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116824515B CN116824515B CN202311100009.5A CN202311100009A CN116824515B CN 116824515 B CN116824515 B CN 116824515B CN 202311100009 A CN202311100009 A CN 202311100009A CN 116824515 B CN116824515 B CN 116824515B
- Authority
- CN
- China
- Prior art keywords
- fault
- image data
- data
- diagnosis
- monitoring image
- 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.)
- Active
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 190
- 238000000034 method Methods 0.000 title claims abstract description 123
- 238000012544 monitoring process Methods 0.000 claims abstract description 212
- 238000003709 image segmentation Methods 0.000 claims abstract description 37
- 230000009466 transformation Effects 0.000 claims abstract description 28
- 238000012545 processing Methods 0.000 claims description 46
- 238000001914 filtration Methods 0.000 claims description 40
- 230000008569 process Effects 0.000 claims description 29
- 230000004044 response Effects 0.000 claims description 29
- 238000012423 maintenance Methods 0.000 claims description 24
- 238000004590 computer program Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 5
- 230000001131 transforming effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 19
- 238000004458 analytical method Methods 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000009193 crawling Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Landscapes
- Debugging And Monitoring (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The embodiment of the invention provides a graphic-based fault diagnosis method, a graphic-based fault diagnosis device, electronic equipment and a storage medium, and relates to the technical field of computer systems and fault diagnosis; comprising the following steps: acquiring monitoring image data of a kernel virtual machine; performing image segmentation on the monitoring image data to generate text image data; performing scale invariant feature transformation on the text image data to determine fault features; and when the fault characteristics are matched with the preset fault keyword image data, determining fault diagnosis result data according to the fault characteristics. According to the embodiment of the invention, when the kernel virtual machine is used for monitoring the server, errors can be automatically identified, so that the fault diagnosis time is greatly shortened, and fault diagnosis is performed through graphical data, so that non-professional personnel can easily perform fault diagnosis, and the method has high practicability.
Description
Technical Field
The present invention relates to the field of computer systems and fault diagnosis technologies, and in particular, to a method for diagnosing faults based on graphics, a device for diagnosing faults based on graphics, an electronic apparatus, and a storage medium.
Background
With the continuous development of emerging technologies such as cloud computing, big data, internet of things and the like, the number of data centers and server devices is increased, and management and monitoring become more complex. Currently, a KVM (Kernel-virtual machine) is adopted to perform mainstream fault diagnosis in the fields of cloud computing, virtualization, servers and the like through a BMC (baseboard management controller ). However, the analysis and fault diagnosis of the server according to the KVM virtual machine when the server is down and in error is always a difficult point, and since the operating system of the KVM is virtualized, the fault diagnosis of the hardware level cannot be directly performed like a physical machine. The fault cause can not be rapidly positioned through log analysis and downtime pictures, so that the fault diagnosis time is long, and professional technicians are required to operate the fault diagnosis time.
Disclosure of Invention
In view of the above problems, embodiments of the present invention have been made to provide a pattern-based fault diagnosis method, a pattern-based fault diagnosis apparatus, an electronic device, and a storage medium that overcome or at least partially solve the above problems.
In a first aspect of the present invention, an embodiment of the present invention discloses a graphic-based fault diagnosis method, including:
Acquiring monitoring image data of a kernel virtual machine;
performing image segmentation on the monitoring image data to generate text image data;
performing scale invariant feature transformation on the text image data to determine character features;
and filtering the character features to determine fault pre-diagnosis data.
Further, after the step of filtering the character features to determine fault pre-diagnosis data, the method further includes:
and generating a management log by the fault pre-diagnosis data and the character features.
Further, after the step of generating the management log from the failure pre-diagnosis data and the character feature, the method further includes:
and sending the management log to preset operation and maintenance equipment.
Further, after the step of acquiring the monitoring image data of the kernel virtual machine, the method further includes:
and storing the monitoring image data into a baseboard management controller database.
Further, after the step of storing the monitoring image data to a baseboard management controller database, the method further includes:
correlating the fault diagnosis result data with the monitoring image data to generate a key value relationship;
And storing the key value relation to the baseboard management controller database.
Further, the step of storing the monitoring image data in a baseboard management controller database includes:
determining the front frame image data of the monitoring image data and the rear frame image data of the monitoring image data;
determining the monitoring image data, the previous frame image data and the subsequent frame image data as a group map;
and storing the group graph to the baseboard management controller database.
Further, after the step of filtering the character features to determine fault pre-diagnosis data, the method further includes:
and sending the fault pre-diagnosis data and the monitoring image data to a preset display page.
Further, the step of performing image segmentation on the monitored image data to generate text image data includes:
image segmentation is carried out on the monitoring image data based on a preset threshold value, and a text area and a background area are generated;
and determining the text area as the text image data.
Further, the step of performing image segmentation on the monitored image data based on a preset threshold value to generate a text region and a background region includes:
Comparing the pixel points of the monitoring image data with the preset threshold value one by one;
determining that the pixel points of the monitoring image data are the text areas in response to the pixel points of the monitoring image data being greater than the preset threshold;
and determining the pixel point of the monitoring image data as the background area in response to the pixel point of the monitoring image data not being larger than the preset threshold value.
Further, the step of performing scale-invariant feature transformation on the text image data to determine character features includes:
detecting key pixel points in text image data;
determining a fault keyword according to the key pixel points;
and determining the character characteristics according to the fault keywords.
Further, the character features include no faults and substantial faults, and after the step of performing scale-invariant feature transformation on the text image data to determine fault features, the method further includes:
marking the monitoring image data as a fault-free image in response to the character feature being the fault-free image;
and responding to the fault characteristic as the substantial fault, and executing the step of filtering the character characteristic to determine fault pre-diagnosis data.
Further, before the step of filtering the character features to determine fault pre-diagnosis data, the method further includes:
judging whether the character features are matched with preset fault keyword image data or not;
when the character features are not matched with the fault keyword image data, determining that the character features are fault-free;
and when the character features are not matched with the fault keyword image data, executing the step of filtering the character features to determine fault pre-diagnosis data.
Further, after the step of marking the monitoring image data as a failure-free image, the method further includes:
and deleting the fault-free image.
Further, the step of filtering the character features and determining fault pre-diagnosis data includes:
determining a fault type and positioning a fault position according to the character characteristics;
acquiring processing data matched with the fault type;
and combining the fault type and the processing data to generate the fault pre-diagnosis data.
Further, the step of determining the fault type according to the character features includes:
Identifying a fault identification character in the character features;
the fault type is determined based on the fault identification character.
Further, the step of obtaining the monitoring image data of the kernel virtual machine includes:
starting a preset kernel data grabbing process;
and capturing the monitoring image data by adopting the preset kernel data capturing process.
Further, after the step of acquiring the monitoring image data of the kernel virtual machine, the method further includes:
synchronizing the monitoring image data to a physical display device.
In a second aspect of the present invention, an embodiment of the present invention discloses a graphic-based fault diagnosis apparatus, including:
the acquisition module is used for acquiring the monitoring image data of the kernel virtual machine;
the segmentation module is used for carrying out image segmentation on the monitoring image data to generate text image data;
the feature extraction module is used for carrying out scale invariant feature transformation on the text image data and determining character features;
and the fault diagnosis module is used for filtering the character features and determining fault pre-diagnosis data.
Optionally, the apparatus further comprises:
and generating a management log, wherein the management log is used for generating the fault pre-diagnosis data and the character characteristics.
Optionally, the apparatus further comprises:
and the first sending module is used for sending the management log to a preset operation and maintenance device.
Optionally, the apparatus further comprises:
and the first storage module is used for storing the monitoring image data to a baseboard management controller database.
Optionally, the apparatus further comprises:
the association module is used for associating the fault diagnosis result data with the monitoring image data to generate a key value relation;
a second storage module for storing the key value relation to the baseboard management controller database
Optionally, the first storage module includes:
a front-back frame determining sub-module for determining front frame image data of the monitoring image data and back frame image data of the monitoring image data;
a group map determining sub-module configured to determine the monitoring image data, the preceding frame image data, and the following frame image data as a group map;
and the storage sub-module is used for storing the group graph to the baseboard management controller database.
Optionally, the apparatus further comprises:
and the second sending module is used for sending the fault pre-diagnosis data and the monitoring image data to a preset display page.
Optionally, the segmentation module includes:
the segmentation sub-module is used for carrying out image segmentation on the monitoring image data based on a preset threshold value to generate a text region and a background region;
and the text image data determining submodule is used for determining the text area as the text image data.
Optionally, the segmentation submodule includes:
the comparison unit is used for comparing the pixel points of the monitoring image data with the preset threshold value one by one;
the first determining unit is used for determining that the pixel points of the monitoring image data are the text areas in response to the fact that the pixel points of the monitoring image data are larger than the preset threshold value;
and the second determining unit is used for determining the pixel point of the monitoring image data as the background area in response to the pixel point of the monitoring image data not being larger than the preset threshold value.
Optionally, the feature extraction module includes:
the detection sub-module is used for detecting key pixel points in the text image data;
the fault keyword determination submodule is used for determining a fault keyword according to the key pixel points;
and the character characteristic determining submodule is used for determining the character characteristic according to the fault keyword.
Optionally, the fault signature includes no fault and substantial fault, and the apparatus further includes:
a first response module for marking the monitoring image data as a fault-free image in response to the character feature being the fault-free image;
and the second response module is used for responding to the fault characteristic as the substantial fault and executing the step of filtering the character characteristic to determine fault pre-diagnosis data.
Optionally, the apparatus further comprises:
the judging module is used for judging whether the character features are matched with the preset fault keyword image data or not;
a mismatch module, configured to determine that the character feature is the fault-free when the character feature does not match the fault keyword image data;
and the matching module is used for executing the step of filtering the character features and determining fault pre-diagnosis data when the character features are not matched with the fault keyword image data. .
Optionally, the apparatus further comprises:
and the deleting sub-module is used for deleting the fault-free image.
Optionally, the fault diagnosis module includes:
the positioning sub-module is used for determining the fault type and positioning the fault position according to the character characteristics;
The matching sub-module is used for acquiring processing data matched with the fault type;
and the combining sub-module is used for combining the fault type and the processing data to generate the fault pre-diagnosis data.
Optionally, the positioning sub-module includes:
the identification unit is used for identifying the fault identification character in the character characteristics;
and the fault type determining unit is used for determining the fault type based on the fault identification character.
Optionally, the acquiring module includes:
the starting module is used for starting a preset kernel data grabbing process;
and the grabbing module is used for grabbing the monitoring image data by adopting the preset kernel data grabbing process.
Optionally, the apparatus further comprises:
and the synchronization module is used for synchronizing the monitoring image data to the physical display device.
In a third aspect of the present invention, an embodiment of the present invention also discloses an electronic device, including a processor, a memory, and a computer program stored on the memory and capable of running on the processor, the computer program implementing the steps of the graphics-based fault diagnosis method as described above when executed by the processor.
In a fourth aspect of the present invention, embodiments of the present invention also disclose a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a graphics-based fault diagnosis method as described above.
Embodiments of the invention may include at least one of the following advantages:
according to the embodiment of the invention, the monitoring image data of the kernel virtual machine are obtained; performing image segmentation on the monitoring image data to generate text image data; performing scale invariant feature transformation on the text image data to determine character features; and filtering the character features to determine fault pre-diagnosis data. By performing fault diagnosis based on the monitoring image data, the technical threshold of operation and maintenance personnel performing fault diagnosis is reduced, so that the fault diagnosis can be performed more quickly and simply, and the practicability is improved; the image is segmented, so that the data volume of data processing is reduced, and the fault diagnosis efficiency is improved; by carrying out scale invariant feature transformation on the text image data, fault features can be accurately and stably identified, and the accuracy of fault diagnosis is improved; when the kernel virtual machine is used for monitoring the server, fault errors can be automatically identified, so that fault diagnosis time is greatly shortened, faults can be timely found and solved, influences and losses of the faults on the service can be avoided, and the reliability of the server is improved.
Drawings
FIG. 1 is a flow chart of steps of an embodiment of a graphics-based fault diagnosis method of the present invention;
FIG. 2 is a flow chart of steps of another embodiment of a graphics-based fault diagnosis method of the present invention;
FIG. 3 is a schematic diagram of a data flow based on an example of a graphical fault diagnosis method of the present invention;
FIG. 4 is a flow chart of steps of an example of a graphical-based fault diagnosis method of the present invention;
FIG. 5 is a schematic view of image processing based on an example of a graphical fault diagnosis method of the present invention;
FIG. 6 is a schematic diagram of fault identification based on an example of a graphical fault diagnosis method of the present invention;
FIG. 7 is a block diagram of an embodiment of a graphic-based fault diagnosis apparatus according to the present invention;
fig. 8 is a block diagram of an electronic device according to an embodiment of the present invention;
fig. 9 is a block diagram of a storage medium according to an embodiment of the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.
Referring to fig. 1, a flowchart illustrating steps of an embodiment of a graph-based fault diagnosis method according to the present invention may specifically include the steps of:
Step 101, obtaining monitoring image data of a kernel virtual machine;
in the embodiment of the invention, the monitoring image data of the kernel virtual machine for monitoring the server can be obtained in real time. Wherein the kernel virtual machine may refer to a device employing KVM.
102, performing image segmentation on the monitoring image data to generate text image data;
after the monitored image data is obtained, image segmentation may be performed on the monitored image data, and the monitored image data is divided into a plurality of areas or objects by using the image segmentation, so as to generate text image data for subsequent processing on the text image data. The image segmentation method may include: the image segmentation methods such as threshold segmentation, region growing, edge detection, clustering-based segmentation and the like are not limited by the embodiment of the invention. In one example of the present invention, the monitoring image data is image-segmented by threshold segmentation.
Step 103, performing scale invariant feature transformation on the text image data to determine character features;
the Scale-invariant feature transformation has the advantages of rotation invariance, scale invariance and the like, the contrast control coefficient in SIFT (Scale-invariant feature transform, scale-invariant feature transformation) is automatically adjusted, and the balance of key point extraction is improved.
In the embodiment of the invention, the text image data is subjected to scale invariant feature transformation, key points in the text image data are identified, and character features are determined.
And 104, filtering the character features to determine fault pre-diagnosis data.
The character features can be filtered, fault information in the character features can be extracted, and fault pre-diagnosis data can be determined. And reflecting faults caused by a certain time in the future in the running process of the current server through the fault pre-diagnosis data so as to facilitate the fault repair by operation and maintenance personnel in advance.
According to the embodiment of the invention, the monitoring image data of the kernel virtual machine are obtained; performing image segmentation on the monitoring image data to generate text image data; performing scale invariant feature transformation on the text image data to determine character features; and filtering the character features to determine fault pre-diagnosis data. By performing fault diagnosis based on the monitoring image data, the technical threshold of operation and maintenance personnel performing fault diagnosis is reduced, so that the fault diagnosis can be performed more quickly and simply, and the practicability is improved; the image is segmented, so that the data volume of data processing is reduced, and the fault diagnosis efficiency is improved; by carrying out scale invariant feature transformation on the text image data, fault features can be accurately and stably identified, and the accuracy of fault diagnosis is improved; when the kernel virtual machine is used for monitoring the server, fault errors can be automatically identified, so that fault diagnosis time is greatly shortened, faults can be timely found and solved, influences and losses of the faults on the service can be avoided, and the reliability of the server is improved.
Referring to fig. 2, there is shown a flowchart of steps of another embodiment of a graph-based fault diagnosis method of the present invention, which may specifically include the steps of:
step 201, obtaining monitoring image data of a kernel virtual machine.
After the server is powered on and started, the monitoring image data of the kernel virtual machine can be obtained in real time.
Specifically, the step of acquiring the monitoring image data of the kernel virtual machine includes: starting a preset kernel data grabbing process; and capturing the monitoring image data by adopting the preset kernel data capturing process.
After the server is powered on and started, a corresponding preset kernel data grabbing process can be started, and the preset kernel data grabbing process is adopted to grab the monitoring image data of the kernel virtual machine so as to obtain the monitoring image data of the kernel virtual machine. In an example of the present invention, the preset kernel data crawling process may be a CatVideoPic (process name) process.
Step 202, synchronizing the monitoring image data to a physical display device.
In the embodiment of the invention, BMCH 5 (HTML 5, hypertext 5.0) or JAVA (program) can be used for viewing the monitoring image data in real time, and the monitoring image data is synchronized to the physical display device, so that an operator can see the monitoring image data through the physical display device in real time.
And step 203, storing the monitoring image data into a baseboard management controller database.
The resulting monitoring image data may be stored to a baseboard management controller database so that processing and archiving of faults may follow from the monitoring image data. The baseboard management controller database may be a Redis (database name) database of the baseboard management controller.
Specifically, the step of storing the monitoring image data in a baseboard management controller database includes: determining the front frame image data of the monitoring image data and the rear frame image data of the monitoring image data; determining the monitoring image data, the previous frame image data and the subsequent frame image data as a group map; and storing the group graph to the baseboard management controller database.
When the monitoring image data is stored, the previous frame image of the current monitoring image data, namely the previous frame image data of the monitoring image data, can be stored; and the next frame of image of the current monitoring image data, namely the next frame of image data of the monitoring image data, and obtaining three frames of image data at the moment: current monitoring image data, front frame image data and rear frame image data. The previous monitoring image data, the previous frame image data and the subsequent frame image data can be combined to determine a group map, and then stored in the form of the group map in the baseboard management controller database. Ensuring that the two pictures before and after the error can trace back whether the diagnosis process is wrong.
And 204, performing image segmentation on the monitoring image data to generate text image data.
When the monitoring image data is processed, the monitoring image data can be firstly subjected to image segmentation, invalid parts are screened out, and text image data is generated, so that the subsequent data processing amount is reduced, and the diagnosis efficiency is improved.
In an optional embodiment of the invention, the step of performing image segmentation on the monitored image data to generate text image data includes:
step S2041, performing image segmentation on the monitoring image data based on a preset threshold value to generate a text region and a background region;
the monitoring image data may be image-segmented based on a preset threshold value, thereby dividing the monitoring image data into two parts, a text region and a background region. The magnitude of the preset threshold may be determined according to practical situations, which is not limited in the embodiment of the present invention.
Specifically, the step of performing image segmentation on the monitored image data based on a preset threshold value to generate a text region and a background region includes: comparing the pixel points of the monitoring image data with the preset threshold value one by one; determining that the pixel points of the monitoring image data are the text areas in response to the pixel points of the monitoring image data being greater than the preset threshold; and determining the pixel point of the monitoring image data as the background area in response to the pixel point of the monitoring image data not being larger than the preset threshold value.
Each pixel of the monitoring image data may be compared one by one, and the pixels of the monitoring image data may be compared one by one with a preset threshold. When the pixel point of the monitoring image data is larger than the preset threshold value, the pixel point of the monitoring image data can be determined to be a text area in response to the pixel point of the monitoring image data being larger than the preset threshold value. Accordingly, when the pixel point of the monitoring image data is not greater than the preset threshold value, the pixel point of the monitoring image data may be determined as the background area in response to the pixel point of the monitoring image data being not greater than the preset threshold value.
Substep S2042 determines the text region as the text image data.
The text region may be determined as text image data for subsequent processing. The background area can be filtered, so that the subsequent processing for the background area is reduced.
And 205, performing scale-invariant feature transformation on the text image data to determine character features.
After the text image data is generated, only the text image data is subjected to scale invariant feature transformation, and pixels corresponding to key points in the text image data are identified, so that character features describing faults are determined.
In an optional embodiment of the invention, the step of performing scale invariant feature transform on the text image data, and determining character features comprises:
sub-step S2051, detecting key pixel points in the text image data;
the key pixel points in the text image data can be determined by detecting the key pixel points in the text image data based on matching alignment.
Step S2052, determining a fault keyword according to the key pixel points;
and combining the key pixel points according to the relation among the key pixel points, and determining fault keywords such as warning, error, kernel error and the like.
And a substep S2053, determining the character features according to the fault keywords.
And determining character features corresponding to the current faults based on the fault keywords.
In an alternative embodiment of the present invention, the fault signature includes no fault and substantial fault, the method further comprising:
step S1, marking the monitoring image data as a fault-free image in response to the character features being the fault-free image;
when the character features are fault-free, namely the server is not monitored to have faults in the current monitoring image data, the monitoring image data can be marked as a fault-free image in response to the fault features being fault-free; to characterize that no fault has been detected with the current monitored image data.
And step S2, responding to the character features as the substantial faults, and executing the step of filtering the character features to determine fault pre-diagnosis data.
When the character feature is a substantial failure, i.e., the server is monitored to be in failure in the current monitored image data, step 206 may be performed in response to the character feature being a substantial failure. And further, the fault types can be classified in advance.
Further, the substantial fault includes an alarm pre-fault, an error fault. The warning pre-fault is a warning fault. The error fault is error fault, kernel panic fault.
And step 206, judging whether the character features are matched with the preset fault keyword image data.
The character features can be matched with the preset fault keyword image data, and whether the character features are matched with the preset fault keyword image data or not is checked, so that the accuracy of fault diagnosis is further ensured.
And step 207, when the character features are not matched with the fault keyword image data, executing the step of filtering the character features to determine fault pre-diagnosis data.
When the character features match with the preset fault keyword image data, the fault pre-diagnosis data may be determined according to the character features.
Specifically, the step of determining fault diagnosis result data according to the fault characteristics includes: determining a fault type and positioning a fault position according to the character characteristics; acquiring processing data matched with the fault type; and combining the fault type and the processing data to generate the fault pre-diagnosis data.
In determining the failure pre-diagnosis result data for the character feature, the form of the failure, i.e., the failure type, may be determined based on the character feature, and the corresponding failure location may also be located based on the payment feature. Fault locations include, but are not limited to, CPU (central processing unit), memory, hard disk, power supply, temperature, drive, etc. Processing data matching the fault type is also acquired for the character feature. The processing data is generated based on the processing method corresponding to the same fault in the past history, and can be stored in a database. Process data is obtained from the database. And finally, combining the fault type and the processing data to generate fault pre-diagnosis result data. So that the corresponding processing mode of the fault position can be clear for operation and maintenance personnel through the fault pre-diagnosis result data.
Furthermore, the method comprises the following steps:
and S3, when the character features are not matched with the fault keyword image data, determining that the fault features are the faults.
In the embodiment of the invention, the condition that the character features are not matched with the fault keyword image data also occurs, and when the fault features are not matched with the fault keyword image data, the recognized fault features are not accurate, and the fault features can be determined to be fault-free at first. In the subsequent image processing, a new detection of the fault is performed.
In addition, the graph-based fault diagnosis method further comprises the following steps:
and S4, deleting the fault-free image.
The monitored image data corresponding to the fault-free image can be deleted from the baseboard management controller database to empty the corresponding group diagram in the baseboard management controller database, so as to release the memory space of the baseboard management controller and avoid the memory error of the baseboard management controller.
And step 208, generating a management log by the fault pre-diagnosis data and the character features.
After the fault pre-diagnosis result data is obtained, determining the fault type corresponding to the fault pre-diagnosis result data, and carrying out different processing on the fault diagnosis result data of different types. Such as pre-detection for a warning type fault, so that the occurrence of an erroneous fault can be detected earlier. And the fault diagnosis result data of different fault types can be stored in the database of the baseboard management controller according to the category, so that operation and maintenance personnel can extract all faults of the same type at one time, and the faults can be uniformly processed, and the fault processing efficiency is improved. The obtained fault pre-diagnosis data and character features can be recorded into the same file to generate a management log. The management log may be a fault management log of the server. The operation and maintenance personnel can know the current and historical faults of the server based on the management log.
And step 209, associating the fault pre-diagnosis result data with the monitoring image data to generate a key value relation.
The correlation can be performed with respect to the failure pre-diagnosis result data and the monitoring image data, so that the failure pre-diagnosis result data and the monitoring image data have a corresponding relationship, namely a key-value relationship is generated.
Step 210, storing the key value relation to the baseboard management controller database.
The key-value relationships are stored in a baseboard management controller database. The corresponding monitoring image data can be queried through the fault pre-diagnosis result data in the bottom plate management controller database, so that operation and maintenance personnel can quickly look up the monitoring image data corresponding to the fault pre-diagnosis result data, and the fault diagnosis efficiency is improved.
In an optional embodiment of the invention, the graphic-based fault diagnosis method further comprises:
and S5, sending the fault pre-diagnosis result data and the monitoring image data to a preset display page.
In the embodiment of the invention, the fault pre-diagnosis result data and the monitoring image data can be sent to the preset display page, and the current fault diagnosis result data and the current monitoring image data are displayed by the preset display page. Wherein the preset presentation page may be a WEB (global wide area network) page of the baseboard management controller. Those skilled in the art may set different pages according to the requirements for display, which is not limited in the embodiment of the present invention.
In an optional embodiment of the invention, the graphic-based fault diagnosis method further comprises:
and S6, sending the management log to preset operation and maintenance equipment.
In the embodiment of the invention, after the management log is generated, the management log can be sent to the preset operation and maintenance equipment in a mail or short message mode through a communication network. The preset operation and maintenance equipment is held by operation and maintenance personnel, and after the operation and maintenance personnel check the management log through the preset operation and maintenance equipment, the operation and maintenance personnel can easily judge the fault reason, and the fault problem is solved by operation and maintenance methods such as direct replacement of components or component driving.
According to the embodiment of the invention, the monitoring image data of the kernel virtual machine are obtained; synchronizing the monitoring image data to a physical display device; storing the monitoring image data to a baseboard management controller database; performing image segmentation on the monitoring image data to generate text image data; performing scale invariant feature transformation on the text image data to determine fault features; when the fault characteristics are matched with preset fault keyword image data, determining fault diagnosis result data according to the fault characteristics; classifying the fault diagnosis result data to obtain a fault type; generating a management log according to the fault type and the fault diagnosis result data; correlating the fault diagnosis result data with the monitoring image data to generate a key value relationship; and storing the key value relation to the baseboard management controller database.
The starting error can be automatically identified and positioned through graphic fault diagnosis, so that the fault diagnosis time is greatly shortened. After the fault occurs, the fault group diagram can be directly displayed in the page. Based on the fault prediction of the group graph analysis, a warning type of fault is extracted, and the fault is predicted and diagnosed in advance. The graphic fault diagnosis displays fault information through a graphic interface, so that non-professional staff can easily perform fault diagnosis. By timely finding and solving the faults, the influence and loss of the faults on the service can be avoided, and the reliability and stability of the equipment are improved. The fault diagnosis can intuitively display fault information, help a user to better know and solve faults, and improve user experience.
In order to make the implementation of the present invention more apparent to those skilled in the art, the following description is given by way of example:
referring to fig. 3, a schematic data flow diagram based on an example of a graphical fault diagnosis method according to the present invention is shown.
The graphic interface information (monitoring image data) of the KVM is captured in real time, the graphic interface information is stored in a database of the BMC, the graphic interface is analyzed by each frame of data, the image information is divided into a plurality of areas or objects by image segmentation, and the data quantity required to be analyzed can be reduced. Useful information is then extracted from the image using feature extraction methods for classification, identification, or other processing. Key points in the image are detected, descriptors of the key points are calculated, matching and recognition of the image are achieved, the key points are compared with the key word image, key starting errors are recognized, such as warning, error key features and key features, corresponding fault diagnosis result analysis is conducted according to error types, fault can be detected in advance through warning, and then fault diagnosis results are stored in a BMC log mode and sent to operation and maintenance personnel.
In particular, referring to fig. 4, a flowchart of steps of an example of a graph-based fault diagnosis method of the present invention is shown;
1. after the server is powered on and started, the KVM monitoring picture can be checked through BMC H5 or JAVA to be synchronous with the display content of the physical display.
2. And after the BMC normally operates, starting the CatVideoPic process to capture KVM real-time picture data in real time, storing the KVM real-time picture data in a mode of key-value by taking a group of pictures as a unit every three frames, and storing the KVM real-time picture data in a Redis database of the BMC.
3. Preprocessing the graphic interface data of each frame stored in the database by using an image processing technology. Referring to fig. 5, specifically, the image information is divided into two parts by using a threshold segmentation algorithm, one part is a text region, the other part is a background picture, and key points in the text region of the image are detected by using a SIFT feature extraction method, descriptors of the key points are calculated, and matching and recognition are performed with a keyword image (Warning, error, panic). And the method is carried out by taking the group diagram as a unit, so that the traceability of two pictures before and after an error is ensured.
4. Intelligent classification is carried out according to the feature extraction result, wherein Waring is an alarm and pre-fault class; error, kernel Panic is Error, fault class, with KEY: the Warning-flag, the Error-flag and the Panic-flag are stored in a Redis database.
5. Filtering the images without corresponding keywords after the images are processed through SIFT feature extraction by an image processing technology, adding a No-Error mark in a Redis database entry, and clearing the images in the database after judging that the No-Error is needed to be cleared so as to release the memory space of the BMC.
6. And grabbing a group diagram in a Redis database according to the keywords, performing fault diagnosis processing, judging the fault type according to the picture information, and diagnosing faults such as CPU, memory, hard disk, power supply, temperature, drive mismatch and the like according to the error positioning information according to FIG. 6. The machine learning algorithm is utilized to analyze and learn a large amount of fault data, the rules and the characteristics of faults are found out from the fault data, further, the rapid and accurate diagnosis of the faults is realized, the accurate fault positioning algorithm is integrated into the BMC, the root cause and the possible solution of the faults are determined through deep analysis and research of the faults, the accurate fault positioning algorithm is directly called for fault processing, and the fault diagnosis result is output. And synchronously outputting the fault group graph and the fault analysis result to the BMC WEB page for display.
7. And generating a corresponding log according to the fault analysis result, and triggering a mail or a short message to inform operation and maintenance personnel to perform fault processing.
It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.
Referring to fig. 7, there is shown a block diagram of an embodiment of a graphic-based fault diagnosis apparatus of the present invention, which may include the following modules:
an acquisition module 701, configured to acquire monitoring image data of a kernel virtual machine;
a segmentation module 702, configured to perform image segmentation on the monitored image data to generate text image data;
a feature extraction module 703, configured to perform scale-invariant feature transformation on the text image data, and determine character features;
and the fault diagnosis module 704 is configured to filter the character features and determine fault pre-diagnosis data.
Optionally, the apparatus further comprises:
and generating a management log, wherein the management log is used for generating the fault pre-diagnosis data and the character characteristics.
Optionally, the apparatus further comprises:
and the first sending module is used for sending the management log to a preset operation and maintenance device.
Optionally, the apparatus further comprises:
and the first storage module is used for storing the monitoring image data to a baseboard management controller database.
Optionally, the apparatus further comprises:
the association module is used for associating the fault diagnosis result data with the monitoring image data to generate a key value relation;
a second storage module for storing the key value relation to the baseboard management controller database
Optionally, the first storage module includes:
a front-back frame determining sub-module for determining front frame image data of the monitoring image data and back frame image data of the monitoring image data;
a group map determining sub-module configured to determine the monitoring image data, the preceding frame image data, and the following frame image data as a group map;
and the storage sub-module is used for storing the group graph to the baseboard management controller database.
Optionally, the apparatus further comprises:
and the second sending module is used for sending the fault pre-diagnosis data and the monitoring image data to a preset display page.
Optionally, the segmentation module includes:
the segmentation sub-module is used for carrying out image segmentation on the monitoring image data based on a preset threshold value to generate a text region and a background region;
and the text image data determining submodule is used for determining the text area as the text image data.
Optionally, the segmentation submodule includes:
the comparison unit is used for comparing the pixel points of the monitoring image data with the preset threshold value one by one;
the first determining unit is used for determining that the pixel points of the monitoring image data are the text areas in response to the fact that the pixel points of the monitoring image data are larger than the preset threshold value;
and the second determining unit is used for determining the pixel point of the monitoring image data as the background area in response to the pixel point of the monitoring image data not being larger than the preset threshold value.
Optionally, the feature extraction module includes:
the detection sub-module is used for detecting key pixel points in the text image data;
the fault keyword determination submodule is used for determining a fault keyword according to the key pixel points;
And the character characteristic determining submodule is used for determining the character characteristic according to the fault keyword.
Optionally, the fault signature includes no fault and substantial fault, and the apparatus further includes:
a first response module for marking the monitoring image data as a fault-free image in response to the character feature being the fault-free image;
and the second response module is used for responding to the fault characteristic as the substantial fault and executing the step of filtering the character characteristic to determine fault pre-diagnosis data.
Optionally, the apparatus further comprises:
the judging module is used for judging whether the character features are matched with the preset fault keyword image data or not;
a mismatch module, configured to determine that the character feature is the fault-free when the character feature does not match the fault keyword image data;
and the matching module is used for executing the step of filtering the character features and determining fault pre-diagnosis data when the character features are not matched with the fault keyword image data. .
Optionally, the apparatus further comprises:
and the deleting sub-module is used for deleting the fault-free image.
Optionally, the fault diagnosis module includes:
the positioning sub-module is used for determining the fault type and positioning the fault position according to the character characteristics;
the matching sub-module is used for acquiring processing data matched with the fault type;
and the combining sub-module is used for combining the fault type and the processing data to generate the fault pre-diagnosis data.
Optionally, the positioning sub-module includes:
the identification unit is used for identifying the fault identification character in the character characteristics;
and the fault type determining unit is used for determining the fault type based on the fault identification character.
Optionally, the acquiring module includes:
the starting module is used for starting a preset kernel data grabbing process;
and the grabbing module is used for grabbing the monitoring image data by adopting the preset kernel data grabbing process.
Optionally, the apparatus further comprises:
and the synchronization module is used for synchronizing the monitoring image data to the physical display device.
According to the embodiment of the invention, the monitoring image data of the kernel virtual machine are obtained; performing image segmentation on the monitoring image data to generate text image data; performing scale invariant feature transformation on the text image data to determine fault features; and when the fault characteristics are matched with the preset fault keyword image data, determining fault diagnosis result data according to the fault characteristics. By performing fault diagnosis based on the monitoring image data, the technical threshold of operation and maintenance personnel performing fault diagnosis is reduced, so that the fault diagnosis can be performed more quickly and simply, and the practicability is improved; the image is segmented, so that the data volume of data processing is reduced, and the fault diagnosis efficiency is improved; by carrying out scale invariant feature transformation on the text image data, fault features can be accurately and stably identified, and the accuracy of fault diagnosis is improved; when the kernel virtual machine is used for monitoring the server, fault errors can be automatically identified, so that fault diagnosis time is greatly shortened, faults can be timely found and solved, and influences and losses of the faults on services can be avoided.
For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
Referring to fig. 8, an embodiment of the present invention further provides an electronic device, including:
a processor 801 and a storage medium 802, the storage medium 802 storing a computer program executable by the processor 801, the processor 801 executing the computer program when the electronic device is running to perform the graphics-based fault diagnosis method according to any one of the embodiments of the present invention. The graphic fault diagnosis-based method comprises the following steps:
acquiring monitoring image data of a kernel virtual machine;
performing image segmentation on the monitoring image data to generate text image data;
performing scale invariant feature transformation on the text image data to determine character features;
and filtering the character features to determine fault pre-diagnosis data.
Further, after the step of filtering the character features to determine fault pre-diagnosis data, the method further includes:
and generating a management log by the fault pre-diagnosis data and the character features.
Further, after the step of generating the management log from the failure pre-diagnosis data and the character feature, the method further includes:
And sending the management log to preset operation and maintenance equipment.
Further, after the step of acquiring the monitoring image data of the kernel virtual machine, the method further includes:
and storing the monitoring image data into a baseboard management controller database.
Further, after the step of storing the monitoring image data to a baseboard management controller database, the method further includes:
correlating the fault diagnosis result data with the monitoring image data to generate a key value relationship;
and storing the key value relation to the baseboard management controller database.
Further, the step of storing the monitoring image data in a baseboard management controller database includes:
determining the front frame image data of the monitoring image data and the rear frame image data of the monitoring image data;
determining the monitoring image data, the previous frame image data and the subsequent frame image data as a group map;
and storing the group graph to the baseboard management controller database.
Further, after the step of filtering the character features to determine fault pre-diagnosis data, the method further includes:
And sending the fault pre-diagnosis data and the monitoring image data to a preset display page.
Further, the step of performing image segmentation on the monitored image data to generate text image data includes:
image segmentation is carried out on the monitoring image data based on a preset threshold value, and a text area and a background area are generated;
and determining the text area as the text image data.
Further, the step of performing image segmentation on the monitored image data based on a preset threshold value to generate a text region and a background region includes:
comparing the pixel points of the monitoring image data with the preset threshold value one by one;
determining that the pixel points of the monitoring image data are the text areas in response to the pixel points of the monitoring image data being greater than the preset threshold;
and determining the pixel point of the monitoring image data as the background area in response to the pixel point of the monitoring image data not being larger than the preset threshold value.
Further, the step of performing scale-invariant feature transformation on the text image data to determine character features includes:
detecting key pixel points in text image data;
Determining a fault keyword according to the key pixel points;
and determining the character characteristics according to the fault keywords.
Further, the character features include no faults and substantial faults, and after the step of performing scale-invariant feature transformation on the text image data to determine fault features, the method further includes:
marking the monitoring image data as a fault-free image in response to the character feature being the fault-free image;
and responding to the fault characteristic as the substantial fault, and executing the step of filtering the character characteristic to determine fault pre-diagnosis data.
Further, before the step of filtering the character features to determine fault pre-diagnosis data, the method further includes:
judging whether the character features are matched with preset fault keyword image data or not;
when the character features are not matched with the fault keyword image data, determining that the character features are fault-free;
and when the character features are not matched with the fault keyword image data, executing the step of filtering the character features to determine fault pre-diagnosis data.
Further, after the step of marking the monitoring image data as a failure-free image, the method further includes:
and deleting the fault-free image.
Further, the step of filtering the character features and determining fault pre-diagnosis data includes:
determining a fault type and positioning a fault position according to the character characteristics;
acquiring processing data matched with the fault type;
and combining the fault type and the processing data to generate the fault pre-diagnosis data.
Further, the step of determining the fault type according to the character features includes:
identifying a fault identification character in the character features;
the fault type is determined based on the fault identification character.
Further, the step of obtaining the monitoring image data of the kernel virtual machine includes:
starting a preset kernel data grabbing process;
and capturing the monitoring image data by adopting the preset kernel data capturing process.
Further, after the step of acquiring the monitoring image data of the kernel virtual machine, the method further includes:
synchronizing the monitoring image data to a physical display device.
The starting error can be automatically identified and positioned through graphic fault diagnosis, so that the fault diagnosis time is greatly shortened. After the failure occurs, the failed group diagram can be directly displayed in the WEB page. Based on the fault prediction of the group graph analysis, the Warning classification is extracted to predict and diagnose faults in advance. The graphic fault diagnosis displays fault information through a graphic interface, so that non-professional staff can easily perform fault diagnosis. By timely finding and solving the faults, the influence and loss of the faults on the service can be avoided, and the reliability and stability of the equipment are improved. The fault diagnosis can intuitively display fault information, help a user to better know and solve faults, and improve user experience.
The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), etc.; but also digital signal processors (Digital Signal Processing, DSP for short), application specific integrated circuits (Application Specific Integrated Circuit, ASIC for short), field-programmable gate arrays (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
Referring to fig. 9, an embodiment of the present invention further provides a computer readable storage medium 901, the storage medium 901 having stored thereon a computer program which, when executed by a processor, performs a graph-based fault diagnosis method according to any one of the embodiments of the present invention. The graphic fault diagnosis-based method comprises the following steps:
acquiring monitoring image data of a kernel virtual machine;
performing image segmentation on the monitoring image data to generate text image data;
performing scale invariant feature transformation on the text image data to determine character features;
and filtering the character features to determine fault pre-diagnosis data.
Further, after the step of filtering the character features to determine fault pre-diagnosis data, the method further includes:
and generating a management log by the fault pre-diagnosis data and the character features.
Further, after the step of generating the management log from the failure pre-diagnosis data and the character feature, the method further includes:
and sending the management log to preset operation and maintenance equipment.
Further, after the step of acquiring the monitoring image data of the kernel virtual machine, the method further includes:
and storing the monitoring image data into a baseboard management controller database.
Further, after the step of storing the monitoring image data to a baseboard management controller database, the method further includes:
correlating the fault diagnosis result data with the monitoring image data to generate a key value relationship;
and storing the key value relation to the baseboard management controller database.
Further, the step of storing the monitoring image data in a baseboard management controller database includes:
determining the front frame image data of the monitoring image data and the rear frame image data of the monitoring image data;
Determining the monitoring image data, the previous frame image data and the subsequent frame image data as a group map;
and storing the group graph to the baseboard management controller database.
Further, after the step of filtering the character features to determine fault pre-diagnosis data, the method further includes:
and sending the fault pre-diagnosis data and the monitoring image data to a preset display page.
Further, the step of performing image segmentation on the monitored image data to generate text image data includes:
image segmentation is carried out on the monitoring image data based on a preset threshold value, and a text area and a background area are generated;
and determining the text area as the text image data.
Further, the step of performing image segmentation on the monitored image data based on a preset threshold value to generate a text region and a background region includes:
comparing the pixel points of the monitoring image data with the preset threshold value one by one;
determining that the pixel points of the monitoring image data are the text areas in response to the pixel points of the monitoring image data being greater than the preset threshold;
and determining the pixel point of the monitoring image data as the background area in response to the pixel point of the monitoring image data not being larger than the preset threshold value.
Further, the step of performing scale-invariant feature transformation on the text image data to determine character features includes:
detecting key pixel points in text image data;
determining a fault keyword according to the key pixel points;
and determining the character characteristics according to the fault keywords.
Further, the character features include no faults and substantial faults, and after the step of performing scale-invariant feature transformation on the text image data to determine fault features, the method further includes:
marking the monitoring image data as a fault-free image in response to the character feature being the fault-free image;
and responding to the fault characteristic as the substantial fault, and executing the step of filtering the character characteristic to determine fault pre-diagnosis data.
Further, before the step of filtering the character features to determine fault pre-diagnosis data, the method further includes:
judging whether the character features are matched with preset fault keyword image data or not;
when the character features are not matched with the fault keyword image data, determining that the character features are fault-free;
And when the character features are not matched with the fault keyword image data, executing the step of filtering the character features to determine fault pre-diagnosis data.
Further, after the step of marking the monitoring image data as a failure-free image, the method further includes:
and deleting the fault-free image.
Further, the step of filtering the character features and determining fault pre-diagnosis data includes:
determining a fault type and positioning a fault position according to the character characteristics;
acquiring processing data matched with the fault type;
and combining the fault type and the processing data to generate the fault pre-diagnosis data.
Further, the step of determining the fault type according to the character features includes:
identifying a fault identification character in the character features;
the fault type is determined based on the fault identification character.
Further, the step of obtaining the monitoring image data of the kernel virtual machine includes:
starting a preset kernel data grabbing process;
and capturing the monitoring image data by adopting the preset kernel data capturing process.
Further, after the step of acquiring the monitoring image data of the kernel virtual machine, the method further includes:
Synchronizing the monitoring image data to a physical display device.
The starting error can be automatically identified and positioned through graphic fault diagnosis, so that the fault diagnosis time is greatly shortened. After the failure occurs, the failed group diagram can be directly displayed in the WEB page. Based on the fault prediction of the group graph analysis, the Warning classification is extracted to predict and diagnose faults in advance. The graphic fault diagnosis displays fault information through a graphic interface, so that non-professional staff can easily perform fault diagnosis. By timely finding and solving the faults, the influence and loss of the faults on the service can be avoided, and the reliability and stability of the equipment are improved. The fault diagnosis can intuitively display fault information, help a user to better know and solve faults, and improve user experience.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of 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, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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 terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The foregoing has described in detail a method, apparatus, electronic device and storage medium for diagnosing faults based on graphics, and specific examples are presented herein to illustrate the principles and embodiments of the present invention, and the above examples are only for aiding in understanding the method and core idea of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (17)
1. A graphic-based fault diagnosis method, comprising:
acquiring monitoring image data of a kernel virtual machine, wherein the monitoring image data comprises images of the kernel virtual machine for monitoring a server;
performing image segmentation on the monitoring image data to generate text image data;
performing scale invariant feature transformation on the text image data, and determining character features, wherein the character features comprise fault keywords;
filtering the character features to determine fault pre-diagnosis data, wherein the fault pre-diagnosis data is used for reflecting faults caused by the current server running in a certain time in the future;
The step of obtaining the monitoring image data of the kernel virtual machine comprises the following steps: starting a preset kernel data grabbing process; capturing the monitoring image data in real time by adopting the preset kernel data capturing process;
the step of filtering the character features and determining fault pre-diagnosis data comprises the following steps: determining a fault type and positioning a fault position according to the character characteristics; acquiring processing data matched with the fault type; combining the fault type and the processing data to generate the fault pre-diagnosis data;
the step of performing scale-invariant feature transformation on the text image data to determine character features includes: detecting key pixel points in text image data; combining the key pixel points according to the relation among the key pixel points to determine a fault keyword; and determining the character characteristics according to the fault keywords.
2. The method of claim 1, wherein after the step of filtering the character features to determine fault pre-diagnosis data, the method further comprises:
and generating a management log by the fault pre-diagnosis data and the character features.
3. The method of claim 2, wherein after the step of generating a management log of the fault pre-diagnosis data and the character feature, the method further comprises:
and sending the management log to preset operation and maintenance equipment.
4. The method of claim 1, wherein after the step of acquiring the monitor image data of the kernel virtual machine, the method further comprises:
and storing the monitoring image data into a baseboard management controller database.
5. The method of claim 4, wherein after the step of storing the monitoring image data to a baseboard management controller database, the method further comprises:
correlating the fault diagnosis result data with the monitoring image data to generate a key value relationship;
and storing the key value relation to the baseboard management controller database.
6. The method of claim 4, wherein the step of storing the monitoring image data to a baseboard management controller database comprises:
determining the front frame image data of the monitoring image data and the rear frame image data of the monitoring image data;
Determining the monitoring image data, the previous frame image data and the subsequent frame image data as a group map;
and storing the group graph to the baseboard management controller database.
7. The method of claim 1, wherein after the step of filtering the character features to determine fault pre-diagnosis data, the method further comprises:
and sending the fault pre-diagnosis data and the monitoring image data to a preset display page.
8. The method of claim 1, wherein the step of image segmentation of the monitored image data to generate text image data comprises:
image segmentation is carried out on the monitoring image data based on a preset threshold value, and a text area and a background area are generated;
and determining the text area as the text image data.
9. The method of claim 8, wherein the step of image segmentation of the monitored image data based on a preset threshold to generate text regions and background regions comprises:
comparing the pixel points of the monitoring image data with the preset threshold value one by one;
determining that the pixel points of the monitoring image data are the text areas in response to the pixel points of the monitoring image data being greater than the preset threshold;
And determining the pixel point of the monitoring image data as the background area in response to the pixel point of the monitoring image data not being larger than the preset threshold value.
10. The method of claim 1, wherein the character features include no faults and substantial faults, and wherein after the step of scale-invariant feature transforming the text image data to determine fault features, the method further comprises:
marking the monitoring image data as a fault-free image in response to the character feature being the fault-free image;
and responding to the fault characteristic as the substantial fault, and executing the step of filtering the character characteristic to determine fault pre-diagnosis data.
11. The method of claim 10, wherein prior to the step of filtering the character features to determine fault pre-diagnosis data, the method further comprises:
judging whether the character features are matched with preset fault keyword image data or not;
when the character features are not matched with the fault keyword image data, determining that the character features are fault-free;
and when the character features are matched with the fault keyword image data, executing the step of filtering the character features to determine fault pre-diagnosis data.
12. The method of claim 10, wherein after the step of marking the monitoring image data as a failure-free image, the method further comprises:
and deleting the fault-free image.
13. The method of claim 1, wherein the step of determining the fault type based on the character signature comprises:
identifying a fault identification character in the character features;
the fault type is determined based on the fault identification character.
14. The method of claim 1, wherein after the step of acquiring the monitor image data of the kernel virtual machine, the method further comprises:
synchronizing the monitoring image data to a physical display device.
15. A graphic-based fault diagnosis apparatus, comprising:
the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring monitoring image data of a kernel virtual machine, and the monitoring image data comprises images of the kernel virtual machine for monitoring a server;
the segmentation module is used for carrying out image segmentation on the monitoring image data to generate text image data;
the feature extraction module is used for carrying out scale invariant feature transformation on the text image data to determine character features, wherein the character features comprise fault keywords;
The fault diagnosis module is used for filtering the character features and determining fault pre-diagnosis data, wherein the fault pre-diagnosis data is used for reflecting faults caused by the current server running in a certain time in the future;
wherein, the acquisition module includes: the starting module is used for starting a preset kernel data grabbing process; the capturing module is used for capturing the monitoring image data in real time by adopting the preset kernel data capturing process;
the fault diagnosis module includes: the positioning sub-module is used for determining the fault type and positioning the fault position according to the character characteristics; the matching sub-module is used for acquiring processing data matched with the fault type; a combining sub-module for combining the fault type and the processing data to generate the fault pre-diagnosis data;
the feature extraction module includes: the detection sub-module is used for detecting key pixel points in the text image data; the fault keyword determination submodule is used for combining the key pixel points according to the relation among the key pixel points to determine a fault keyword; and the character characteristic determining submodule is used for determining the character characteristic according to the fault keyword.
16. An electronic device comprising a processor, a memory and a computer program stored on the memory and capable of running on the processor, which when executed by the processor implements the steps of the graphics-based fault diagnosis method of any one of claims 1 to 14.
17. A computer readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the steps of the graphics-based fault diagnosis method according to any of claims 1 to 14.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311100009.5A CN116824515B (en) | 2023-08-29 | 2023-08-29 | Graphic fault diagnosis method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311100009.5A CN116824515B (en) | 2023-08-29 | 2023-08-29 | Graphic fault diagnosis method and device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116824515A CN116824515A (en) | 2023-09-29 |
| CN116824515B true CN116824515B (en) | 2024-01-26 |
Family
ID=88139596
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311100009.5A Active CN116824515B (en) | 2023-08-29 | 2023-08-29 | Graphic fault diagnosis method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116824515B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567745A (en) * | 2011-12-29 | 2012-07-11 | 北京航天时代光电科技有限公司 | Automatic detection method of optical fiber fusion quality |
| CN102708378A (en) * | 2012-04-28 | 2012-10-03 | 浙江工业大学 | Method for diagnosing fault of intelligent traffic capturing equipment based on image abnormal characteristic |
| CN104698426A (en) * | 2015-04-01 | 2015-06-10 | 无锡桑尼安科技有限公司 | Automatic checking terminal for faults of outdoor electric energy meter |
| CN111126405A (en) * | 2019-12-13 | 2020-05-08 | 长沙理工大学 | Real-time scanning and updating pushing method for monitoring fault alarm information of converter station |
| CN111800294A (en) * | 2020-06-09 | 2020-10-20 | 中移（杭州）信息技术有限公司 | Gateway fault diagnosis method and device, network equipment and storage medium |
| CN114281628A (en) * | 2021-12-27 | 2022-04-05 | 北京天融信网络安全技术有限公司 | System fault detection method and device, electronic equipment and storage medium |
-
2023
- 2023-08-29 CN CN202311100009.5A patent/CN116824515B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102567745A (en) * | 2011-12-29 | 2012-07-11 | 北京航天时代光电科技有限公司 | Automatic detection method of optical fiber fusion quality |
| CN102708378A (en) * | 2012-04-28 | 2012-10-03 | 浙江工业大学 | Method for diagnosing fault of intelligent traffic capturing equipment based on image abnormal characteristic |
| CN104698426A (en) * | 2015-04-01 | 2015-06-10 | 无锡桑尼安科技有限公司 | Automatic checking terminal for faults of outdoor electric energy meter |
| CN111126405A (en) * | 2019-12-13 | 2020-05-08 | 长沙理工大学 | Real-time scanning and updating pushing method for monitoring fault alarm information of converter station |
| CN111800294A (en) * | 2020-06-09 | 2020-10-20 | 中移（杭州）信息技术有限公司 | Gateway fault diagnosis method and device, network equipment and storage medium |
| CN114281628A (en) * | 2021-12-27 | 2022-04-05 | 北京天融信网络安全技术有限公司 | System fault detection method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116824515A (en) | 2023-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2019275633B2 (en) | System and method of automated fault correction in a network environment | |
| CN111291096B (en) | Data set construction method, device, storage medium and abnormal index detection method | |
| CN112416705A (en) | Abnormal information processing method and device | |
| CN106909492B (en) | Method and device for tracking service data | |
| CN111767193A (en) | Server data anomaly detection method and device, storage medium and equipment | |
| CN116824515B (en) | Graphic fault diagnosis method and device, electronic equipment and storage medium | |
| CN112822440A (en) | Biological sample preparation monitoring method, application server, system and storage medium | |
| CN114327988B (en) | Visual network fault relation determination method and device | |
| JP2019164788A (en) | Information processing device, information processing method, program and image information display system | |
| CN115580528A (en) | Fault root cause positioning method, device, equipment and readable storage medium | |
| CN115098378A (en) | Method and device for classifying and aggregating log fragments based on abnormal breakpoints | |
| CN114416417A (en) | System abnormity monitoring method, device, equipment and storage medium | |
| CN114996080A (en) | Data processing method, device, equipment and storage medium | |
| CN113781068A (en) | Online problem solving method and device, electronic equipment and storage medium | |
| JP2010218267A (en) | Obstacle occurrence probability calculation system, obstacle occurrence probability calculation method and program | |
| CN111581044A (en) | Cluster optimization method, device, server and medium | |
| CN115333923B (en) | Fault point tracing analysis method, device, equipment and medium | |
| CN113037550B (en) | Service fault monitoring method, system and computer readable storage medium | |
| CN117555501B (en) | Cloud printer operation and data processing method based on edge calculation and related device | |
| CN113297026B (en) | Object detection method and device, electronic equipment and computer-readable storage medium | |
| US11086707B2 (en) | Image-based detection of errors in application state | |
| CN117130874A (en) | Page fault information processing method, device, computer equipment and storage medium | |
| CN114818968A (en) | Buried point data detection method and device, electronic equipment and storage medium | |
| CN116245854A (en) | Product detection result statistics method, device and storage medium | |
| CN110971446A (en) | Method and device for recording server restart reason log |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |