Disclosure of Invention
The application provides an operation and maintenance method based on a visual identification technology, which comprises the following steps:
The block chain master node acquires a network link hardware state diagram in real time, acquires the data execution rate of each block chain sub-node, groups the network link hardware state diagram according to the data execution rate of each block chain sub-node, and sends each group of network link hardware state diagram to each corresponding block chain sub-node;
Extracting fault characteristics from the received network link hardware state diagrams by each block chain sub-node according to a visual identification technology, inputting the fault characteristics into a pre-constructed link anomaly model to identify fault types, calculating the severity of each identified fault type, and returning the fault types and the fault severity to the block chain main node;
The block chain master node gathers the fault type and the fault severity fed back by each block chain sub node and processes the fault.
The operation and maintenance method based on the visual identification technology, wherein the hardware in the network link comprises transmission and switching equipment, line interconnection equipment, a network adapter, a hub, a repeater, a network bridge, a router, a gateway and a transmission medium, and the blockchain master node acquires all hardware state diagrams in the network link in real time, distributes the acquired network link hardware state diagrams in a distributed mode every preset time and distributes the acquired network link hardware state diagrams to all blockchain child nodes.
The operation and maintenance method based on the visual identification technology, as described above, wherein the network link hardware state diagram is grouped according to the data execution rate of each block chain sub-node, specifically includes:
Calculating the maximum data volume which can be processed by each block chain node;
Sequentially polling the byte numbers of the hardware state diagrams, and searching a plurality of hardware device state diagrams closest to the maximum data quantity;
All hardware state diagrams are grouped according to the maximum data quantity which can be processed by each block chain sub-node.
The operation and maintenance method based on the visual identification technology, which is described above, inputs fault characteristics into a pre-constructed link anomaly model to identify fault types, and specifically comprises the following sub-steps:
Acquiring historical hardware state diagrams of different fault types of different equipment from each blockchain node in advance, constructing a fault feature vector set, inputting the fault feature vector set into a fault classification model, training the fault classification model to obtain different sub-training models, classifying the fault feature vector set by using each sub-training model, and estimating the classification result to obtain a set of weights of each sub-training model;
Searching an optimal value corresponding to each weight in the weight set, and determining a fault type through the combination of each sub-training model and the optimal value of the corresponding weight to obtain a fault analysis model;
And comparing the received multiple state diagrams of the network link hardware, extracting a feature area with morphological change from the state diagrams as a fault feature, inputting the fault feature into a fault analysis model, and outputting the fault type.
The operation and maintenance method based on the visual recognition technology, as described above, sets weights E 1 and E 2 for the number of fault types and the severity of faults in advance, then calculates u=e 1*V+E2 ×y, V is the total number of fault types, Y is the severity of faults, and performs fault sorting processing according to the final calculation result U.
The application also provides an operation and maintenance system based on the visual identification technology, which comprises a block chain main node and a plurality of block chain sub nodes;
The block chain master node is used for acquiring the network link hardware state diagram in real time, acquiring the data execution rate of each block chain sub-node, grouping the network link hardware state diagram according to the data execution rate of each block chain sub-node, and transmitting each group of network link hardware state diagram to each corresponding block chain sub-node;
Each block chain sub node is used for extracting fault characteristics from the network link hardware state diagrams received by each block chain sub node according to a visual identification technology, inputting the fault characteristics into a pre-constructed link anomaly model to identify fault types, calculating the severity of each identified fault type, and returning the fault types and the fault severity to the block chain main node;
And the block chain master node is also used for summarizing the fault types and the severity of each fault fed back by each block chain child node and carrying out fault processing.
The operation and maintenance system based on the visual identification technology, wherein the hardware in the network link comprises transmission and switching equipment, line interconnection equipment, a network adapter, a hub, a repeater, a network bridge, a router, a gateway and a transmission medium, and the blockchain master node acquires all hardware state diagrams in the network link in real time, distributes the acquired network link hardware state diagrams in a distributed mode every preset time and distributes the acquired network link hardware state diagrams to all blockchain child nodes.
The operation and maintenance system based on the visual recognition technology, wherein the block chain master node comprises a hardware state diagram grouping module, and the hardware state diagram grouping module is specifically used for calculating the maximum data volume which can be processed by each block chain child node; sequentially polling the byte numbers of the hardware state diagrams, and searching a plurality of hardware device state diagrams closest to the maximum data quantity; all hardware state diagrams are grouped according to the maximum data quantity which can be processed by each block chain sub-node.
The operation and maintenance system based on the visual recognition technology, wherein each blockchain node comprises a fault type recognition module, and the module is specifically used for acquiring historical hardware state diagrams of different fault types of different devices from each blockchain node in advance, constructing a fault feature vector set, inputting the fault feature vector set into a fault classification model, training the fault classification model to obtain different sub-training models, classifying the fault feature vector set by using each sub-training model, and estimating the classification result to obtain a set of weights of each sub-training model; searching an optimal value corresponding to each weight in the weight set, and determining a fault type through the combination of each sub-training model and the optimal value of the corresponding weight to obtain a fault analysis model; and comparing the received multiple state diagrams of the network link hardware, extracting a feature area with morphological change from the state diagrams as a fault feature, inputting the fault feature into a fault analysis model, and outputting the fault type.
The present application also provides a computer-readable storage medium including: at least one memory and at least one processor; a memory for storing one or more program instructions; a processor for executing one or more program instructions for performing an operation and maintenance method based on a visual recognition technique as described in any one of the above.
The beneficial effects achieved by the application are as follows: by adopting the technical scheme of the application, a large number of hardware state diagrams are subjected to distributed identification processing by the block chain technology, so that the processing speed of the hardware state diagrams is improved, hardware faults in the hardware state diagrams are identified by the visual identification technology, and the accuracy of hardware fault identification is improved.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1
An embodiment of the present application provides an operation and maintenance method based on a visual identification technology, which is used for performing operation and maintenance processing on hardware faults existing in a network link through the visual identification technology, as shown in fig. 1, and includes:
step 110, the block chain master node collects the network link hardware state diagram in real time, acquires the data execution rate of each block chain sub-node, groups the network link hardware state diagram according to the data execution rate of each block chain sub-node, and sends each group of network link hardware state diagram to each corresponding block chain sub-node;
In a data communications network, a telecommunications facility, called a network link, that connects two or more data stations according to the specifications of a link protocol, hardware in the network link including, but not limited to, transmission and switching equipment, line interconnect equipment, network adapters, hubs, repeaters, bridges, routers, gateways, transmission mediums, etc.;
In the embodiment of the application, the block chain master node acquires all hardware state diagrams in the network link in real time, distributes the acquired network link hardware state diagrams to all the block chain child nodes at intervals of preset time in a distributed mode, and processes a large number of hardware state diagrams by all the block chain child nodes, so that the data processing capacity of the block chain master node can be balanced.
Specifically, when the block chain master node distributes data, the data execution rate of each block chain sub-node needs to be acquired first, and the data execution rate of each block chain sub-node is calculated according to the following formula:
wherein M is the data execution rate of each block chain sub-node, L i is the residual storage length of the ith storage area in the block chain sub-node, n is the total number of storage areas, M is the security level of the hardware state diagram, and the value of i is the slave value L is the total byte number of a network link hardware state diagram, L j' is the total length of a j-th storage area, and the value of j is 1-n; lambda 1 is the block chain child node energy storage capability weight, lambda 2 is the block chain child node computation capability weight, and v is the current CPU utilization of the block chain child node.
The block chain master node then performs data grouping according to the data execution rate of each block chain sub-node, specifically, calculates the maximum data amount that each block chain sub-node can process, namelyFloor is a downward rounding function, M i is the data execution rate of the ith blockchain child node,/>For the sum of the data execution rates of all the block chain sub-nodes, T is the total number of the block chain sub-nodes, after the maximum data quantity L imax which can be processed by each block chain sub-node is calculated, sequentially polling the byte number of the hardware state diagram, searching a plurality of hardware equipment state diagrams closest to the maximum data quantity L imax, grouping all the hardware state diagrams according to the maximum data quantity which can be processed by each block chain sub-node, and transmitting each group of network link hardware state diagrams to each corresponding block chain sub-node; for example, the hardware state diagrams of hubs, repeaters, bridges are distributed to a first blockchain sub-node, the hardware state diagrams of transmission and switching devices, line interconnection devices are distributed to a second blockchain sub-node, and the hardware state diagrams of network adapters, routers, gateways, transmission mediums are distributed to a third blockchain sub-node.
Step 120, each block chain node extracts fault characteristics from the network link hardware state diagram received by each block chain node according to a visual recognition technology, and inputs the fault characteristics into a pre-constructed link anomaly model to recognize fault types;
In the embodiment of the present application, as shown in fig. 2, fault characteristics are input into a pre-constructed link anomaly model to identify fault types, and specifically the method includes the following sub-steps:
Step 210, collecting historical hardware state diagrams of different fault types of different devices from each blockchain node in advance, constructing a fault feature vector set, inputting the fault feature vector set into a fault classification model, training the fault classification model to obtain different sub-training models, classifying the fault feature vector set by using each sub-training model, and estimating the classification result to obtain a set of weights of each sub-training model;
Specifically, inputting a fault feature vector set into a classification model, and training a sub-training model by using the feature vector set; classifying the feature vector set by using the sub-training model to obtain a classification result, estimating a weight set of the sub-training model by the classification result, and specifically adopting a formula Estimating a set of weights { mu 1,μ2,μ3……μT } for the sub-training model, wherein argmin is/>A set of μ with a minimum value.
Step 220, searching the optimal value corresponding to each weight in the weight set, and determining the fault type through the combination of each sub-training model and the optimal value of the corresponding weight to obtain a fault analysis model;
Specifically, calculating an optimal value corresponding to each weight in the set of weights of each sub-training model through a particle swarm optimization algorithm; and determining the fault type through the optimal value combination of each sub-training model and the corresponding weight to obtain a fault analysis model.
And 230, comparing the received multiple state diagrams of the network link hardware, extracting a feature area with morphological change from the state diagrams as a fault feature, inputting the fault feature into a fault analysis model, and outputting a fault type.
Referring back to fig. 1, step 130, each blockchain child node calculates the severity of each identified failure type, and returns the failure type and the severity of the failure to the blockchain master node;
specifically, the severity of each fault type is calculated using the following formula:
wherein Y represents the severity of the fault type; represents the j-th total number of fault types,/> Representing the total number of all fault types for all devices, R ij represents the limit threshold for the jth fault type in the ith hardware device.
Step 140, the block chain master node performs fault processing according to the fed-back fault type and each fault severity;
Specifically, after receiving the fault types and the severity of the feedback of all the blockchain sub-nodes, the blockchain master node considers that the number of faults and the severity of the faults have an effect on the sequence of fault processing, so weights E 1 and E 2,E1+E2 =1 are preset for the number of the fault types and the severity of the faults, then, U=e 1*V+E2 ×y is calculated, V is the total number of the fault types, Y is the severity of the faults, and the fault sequencing processing is performed according to the final calculation result U.
Example two
The second embodiment of the application provides an operation and maintenance system based on a visual recognition technology, as shown in fig. 3, which comprises a blockchain master node and a plurality of blockchain child nodes, and in order to improve the processing capacity of the blockchain master node for a plurality of network link hardware state diagrams, the network link hardware state diagrams are distributed to each blockchain child node for data distributed processing.
The block chain master node is used for acquiring the network link hardware state diagram in real time, acquiring the data execution rate of each block chain sub-node, grouping the network link hardware state diagram according to the data execution rate of each block chain sub-node, and transmitting each group of network link hardware state diagram to each corresponding block chain sub-node;
Extracting fault characteristics from the received network link hardware state diagrams by each block chain sub-node according to a visual identification technology, inputting the fault characteristics into a pre-constructed link anomaly model to identify fault types, calculating the severity of each identified fault type, and returning the fault types and each fault severity to the block chain main node;
And the block chain master node performs fault merging processing according to the fed-back fault type and each fault severity.
The hardware in the network link comprises transmission and switching equipment, line interconnection equipment, a network adapter, a hub, a repeater, a network bridge, a router, a gateway and a transmission medium, wherein a block chain main node acquires all hardware state diagrams in the network link in real time, and then distributes the acquired network link hardware state diagrams in a distributed mode at preset time intervals to all block chain sub-nodes.
The block chain master node comprises a hardware state diagram grouping module which is specifically used for calculating the maximum data volume which can be processed by each block chain child node; sequentially polling the byte numbers of the hardware state diagrams, and searching a plurality of hardware device state diagrams closest to the maximum data quantity; all hardware state diagrams are grouped according to the maximum data quantity which can be processed by each block chain sub-node.
Each block chain sub-node comprises a fault type identification module, and is specifically configured to collect historical hardware state diagrams of different fault types of different devices from each block chain node in advance, construct a fault feature vector set, input the fault feature vector set into a fault classification model, train the fault classification model to obtain different sub-training models, respectively classify the fault feature vector set by using each sub-training model, and estimate the classification result to obtain a set of weights of each sub-training model; searching an optimal value corresponding to each weight in the weight set, and determining a fault type through the combination of each sub-training model and the optimal value of the corresponding weight to obtain a fault analysis model; and comparing the received multiple state diagrams of the network link hardware, extracting a feature area with morphological change from the state diagrams as a fault feature, inputting the fault feature into a fault analysis model, and outputting the fault type.
Corresponding to the above embodiments, an embodiment of the present invention provides a computer storage medium, including: at least one memory and at least one processor;
the memory is used for storing one or more program instructions;
And a processor for executing one or more program instructions for performing an operation and maintenance method based on visual recognition technology.
In accordance with the foregoing embodiments, the embodiments of the present invention provide a computer readable storage medium, where the computer readable storage medium contains one or more program instructions for execution by a processor of an operation and maintenance method based on a visual recognition technology.
The disclosed embodiments provide a computer readable storage medium having stored therein computer program instructions which, when run on a computer, cause the computer to perform the above-described method.
In the embodiment of the invention, the processor may be an integrated circuit chip with signal processing capability. The Processor may be a general purpose Processor, a digital signal Processor (DIGITAL SIGNAL Processor, DSP for short), an application specific integrated circuit (Application Specific Processor NTEGRATED CIRCUIT ASIC for short), a field programmable gate array (FieldProgrammable GATE ARRAY FPGA for short), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The processor reads the information in the storage medium and, in combination with its hardware, performs the steps of the above method.
The storage medium may be memory, for example, may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory.
The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable ROM (ELECTRICALLY EPROM, EEPROM), or a flash Memory.
The volatile memory may be a random access memory (Random Access Memory, RAM for short) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as static random access memory (STATIC RAM, SRAM), dynamic random access memory (DYNAMIC RAM, DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate Synchronous dynamic random access memory (Double DATA RATESDRAM, ddr SDRAM), enhanced Synchronous dynamic random access memory (ENHANCEDSDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCHLINK DRAM, SLDRAM), and direct memory bus random access memory (DirectRambus RAM, DRRAM).
The storage media described in embodiments of the present invention are intended to comprise, without being limited to, these and any other suitable types of memory.
Those skilled in the art will appreciate that in one or more of the examples described above, the functions described in the present invention may be implemented in a combination of hardware and software. When the software is applied, the corresponding functions may be stored in a computer-readable medium or transmitted as one or more instructions or code on the computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present invention in further detail, and are not to be construed as limiting the scope of the invention, but are merely intended to cover any modifications, equivalents, improvements, etc. based on the teachings of the invention.