KR102522634B1 - Methods, devices, and systems for automating maintenance operations of network equipment - Google Patents

Abstract

The present invention relates to a method, apparatus, and system for automating maintenance operation of network equipment. The system for automating maintenance operation of network equipment comprises: a processor; a memory; and an artificial intelligence learning model. According to the present invention, the operating state of network equipment can be automatically diagnosed or the remaining life of the network equipment can be predicted.

Description

Maintenance operation automation method, device and system of network equipment

This document is about a method, device, and system for automating maintenance and repair operation of network equipment. Specifically, it relates to a system that collects operation data of network equipment subject to maintenance and automatically diagnoses the operation status of network equipment using the collected operation data using an artificial neural network to help with maintenance and repair. .

Recently, as the use of mobile communication devices has greatly increased, each mobile communication network operator is installing network equipment including base stations or repeaters so that mobile communication services can be used anywhere in the country. As the number of base stations or repeaters increases significantly, each mobile communication network operator performs continuous maintenance and management for the normal operation of network equipment.

In addition, in providing management services for equipment that requires continuous maintenance and repair, such as corporate computer equipment such as corporate computer servers, storage, security and network equipment, the management company provides a cost estimate for maintenance at the request of the customer. Maintenance service is proposed through the company, and maintenance and repair services are provided through the engineer in charge if there is approval from the customer.

The task of performing maintenance by monitoring the existing network equipment is in the form of simply displaying the power of the signal output by the network equipment, so maintenance personnel could not accurately analyze the output signal of the network equipment, and maintenance and repair There was a difficulty in determining whether or not there was a lack of basis for judgment.

In addition, since measurement equipment operators must be familiar with how to use each measurement equipment and have mobile communication network maintenance skills and experience, mobile communication network operators purchase a large number of measurement equipment and hire and maintain high-quality personnel. There was a problem of having to spend a lot of money for it.

The maintenance operation automation system of network equipment according to this document collects operation data of network equipment subject to maintenance and repair, and automatically diagnoses the operation status of network equipment using the collected operation data using artificial neural networks. It aims to predict the remaining life.

The network equipment maintenance operation automation system according to this document analyzes the cause of the error when an error is detected in the network equipment, extracts necessary parts for maintenance and price information on the necessary parts, and generates a maintenance estimate to perform maintenance. Its purpose is to provide notifications for

The maintenance operation automation system of network equipment may include a processor, memory, and artificial intelligence learning model. The processor obtains first device information including type, structure, operation method and operation data of the first device for a first device corresponding to a first company, and obtains the first device and type, structure and operation data from an external server. Obtain driving data of the second device, the third device, and the Nth device having the same operating method, and obtain the driving data of the first device, the driving data of the second device, the driving data of the third device, and the driving data of the Nth device. Driving data is provided as an input to the artificial intelligence learning model, a performance standard for network equipment of the same type as the first device is obtained, and when the performance standard for the network equipment is determined, the driving data of the first device It may be provided as an input to the artificial intelligence learning model, and information about the state and remaining lifespan of the first device may be obtained. The artificial intelligence learning model calculates an average of the driving data of the first device, the driving data of the second device, the driving data of the third device, and the driving data of the Nth device as inputs, and based on the average value, the driving data of the Nth device is calculated. A performance standard may be output for network equipment of the same type as the first device, and information on a state and remaining life of the first device may be output based on operation data of the first device and the performance standard. The performance standard of network equipment is firewall (FW), distributed denial of service attack (DDoS) response, web firewall (WebFW), virtual private network (VPN), network access control (NAC), intrusion prevention system (IPS), maximum connection creation rate per second (CPS), a maximum number of concurrent sessions (CC), a traffic throughput (BW), or a maximum transaction generation rate (TPS), and N may mean a natural number of 3 or more.

The maintenance operation automation system of network equipment according to this document collects operation data of network equipment subject to maintenance and repair, and automatically diagnoses the operation status of network equipment using the collected operation data using artificial neural networks. Remaining life can be predicted.

The maintenance operation automation system of network equipment according to this document collects operation data of network equipment, accurately analyzes the output signal of network equipment using an artificial neural network, and can help determine maintenance and repair. .

The network equipment maintenance operation automation system according to this document analyzes the cause of the error when an error is detected in the network equipment, extracts necessary parts for maintenance and price information on the necessary parts, and generates a maintenance estimate to perform maintenance. notifications can be provided.

1 is a diagram for explaining a maintenance operation automation system for artificial intelligence-based network equipment according to an embodiment.
2 is a diagram for explaining learning of a neural network according to an exemplary embodiment.
3 is a diagram showing the configuration of an artificial intelligence model according to an embodiment.
4 is an exemplary diagram of a configuration of a system according to an embodiment.
5 is a flowchart of a method for automating maintenance operation of network equipment according to an embodiment.
6 is a flowchart illustrating a method for automating maintenance operation of network equipment according to an embodiment.
7 is a configuration diagram of a system for automating maintenance and operation of network equipment according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. However, since various changes can be made to the embodiments, the scope of the patent application is not limited or limited by these embodiments. It should be understood that all changes, equivalents or substitutes to the embodiments are included within the scope of rights.

Specific structural or functional descriptions of the embodiments are disclosed for illustrative purposes only, and may be modified and implemented in various forms. Therefore, the embodiments are not limited to the specific disclosed form, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit.

Although terms such as first or second may be used to describe various components, such terms should only be construed for the purpose of distinguishing one component from another. For example, a first element may be termed a second element, and similarly, a second element may be termed a first element.

It should be understood that when an element is referred to as being “connected” to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle.

Terms used in the examples are used only for descriptive purposes and should not be construed as limiting. Singular expressions include plural expressions unless the context clearly dictates otherwise. In this specification, terms such as "include" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the embodiment belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and unless explicitly defined in the present application, they should not be interpreted in an ideal or excessively formal meaning. don't

In addition, in the description with reference to the accompanying drawings, the same reference numerals are given to the same components regardless of reference numerals, and overlapping descriptions thereof will be omitted. In describing the embodiment, if it is determined that a detailed description of a related known technology may unnecessarily obscure the gist of the embodiment, the detailed description will be omitted.

The embodiments may be implemented in various types of products such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent vehicles, kiosks, and wearable devices.

The embodiments may be implemented in various types of products such as personal computers, laptop computers, tablet computers, smart phones, televisions, smart home appliances, intelligent vehicles, kiosks, and wearable devices.

An artificial intelligence (AI) system is a computer system that implements human-level intelligence, and unlike existing rule-based smart systems, machines learn and judge on their own. The more AI systems are used, the higher the recognition rate and the more accurate understanding of user preferences. Conventional rule-based smart systems are gradually being replaced by deep learning-based AI systems.

Artificial intelligence technology consists of machine learning and element technologies using machine learning. Machine learning is an algorithm technology that classifies/learns the characteristics of input data by itself, and element technology is a technology that uses machine learning algorithms such as deep learning to mimic functions such as recognition and judgment of the human brain. It consists of technical fields such as understanding, inference/prediction, knowledge expression, and motion control.

The various fields where artificial intelligence technology is applied are as follows. Linguistic understanding is a technology for recognizing and applying/processing human language/characters, including natural language processing, machine translation, dialogue systems, question and answering, voice recognition/synthesis, and the like. Visual understanding is a technology for recognizing and processing objects like human vision, and includes object recognition, object tracking, image search, person recognition, scene understanding, space understanding, image improvement, and the like. Inference prediction is a technique of reasoning and predicting logically by judging information, and includes knowledge/probability-based reasoning, optimization prediction, preference-based planning, and recommendation. Knowledge expression is a technology that automatically processes human experience information into knowledge data, and includes knowledge construction (data creation/classification) and knowledge management (data utilization). Motion control is a technology for controlling the autonomous driving of vehicles and the movement of robots, and includes motion control (navigation, collision, driving), manipulation control (behavior control), and the like.

In general, in order to apply machine learning algorithms to real life, learning is performed in a trial and error method due to the nature of the basic methodology of machine learning. In particular, deep learning requires hundreds of thousands of iterations. It is impossible to execute this in an actual physical external environment, so instead, the actual physical external environment is virtually implemented on a computer and learning is performed through simulation.

In the present invention, artificial intelligence (AI) means a technology that imitates human learning ability, reasoning ability, perception ability, etc., and implements it with a computer, and concepts such as machine learning and symbolic logic can include Machine learning (ML) is an algorithm technology that classifies or learns the characteristics of input data by itself. Artificial intelligence technology is a machine learning algorithm that analyzes input data, learns the result of the analysis, and can make judgments or predictions based on the result of the learning. In addition, technologies that mimic the functions of the human brain, such as cognition and judgment, using machine learning algorithms, can also be understood as the category of artificial intelligence. For example, technical fields such as linguistic understanding, visual understanding, inference/prediction, knowledge expression, and motion control may be included.

Machine learning may refer to processing that trains a neural network model using experience of processing data. Through machine learning, computer software could mean improving its own data processing capabilities. A neural network model is constructed by modeling a correlation between data, and the correlation may be expressed by a plurality of parameters. The neural network model extracts and analyzes features from given data to derive a correlation between the data. Machine learning is to optimize the parameters of the neural network model by repeating this process. For example, a neural network model may learn a mapping (correlation) between an input and an output with respect to data given as an input/output pair. Alternatively, even when only input data is given, the neural network model may learn the relationship by deriving regularities between given data.

An artificial intelligence learning model or a neural network model may be designed to implement a human brain structure on a computer, and may include a plurality of network nodes having weights while simulating neurons of a human neural network. A plurality of network nodes may have a connection relationship between them by simulating synaptic activities of neurons in which neurons exchange signals through synapses. In the artificial intelligence learning model, a plurality of network nodes can exchange data according to the convolution connection relationship while being located in layers of different depths. The artificial intelligence learning model may be, for example, an artificial neural network model, a convolutional neural network model (CNN), and the like. As an embodiment, the artificial intelligence learning model may be machine-learned according to methods such as supervised learning, unsupervised learning, and reinforcement learning. Machine learning algorithms for performing machine learning include Decision Tree, Bayesian Network, Support Vector Machine, Artificial Neural Network, and Ada-boost. ), perceptron, genetic programming, clustering, etc. can be used.

Of these, CNNs are a type of multilayer perceptrons designed to use minimal preprocessing. CNN consists of one or several convolutional layers and general artificial neural network layers placed on top of them, and additionally utilizes weights and pooling layers. Thanks to this structure, CNN can fully utilize the two-dimensional structure of the input data. Compared to other deep learning structures, CNN shows good performance in both video and audio fields. CNNs can also be trained via standard back-propagation. CNNs are easier to train than other feedforward artificial neural network techniques and have the advantage of using fewer parameters.

Convolutional networks are neural networks that contain sets of nodes with bound parameters. The increasing size of available training data and the availability of computing power, combined with algorithmic advances such as piecewise linear units and dropout training, have greatly improved many computer vision tasks. With huge data sets, such as those available for many tasks today, overfitting is not critical, and increasing the size of the network improves test accuracy. Optimal use of computing resources becomes a limiting factor. To this end, a distributed, scalable implementation of deep neural networks can be used.

1 is a diagram for explaining a maintenance operation automation system for artificial intelligence-based network equipment according to an embodiment.

As shown in FIG. 1, the artificial intelligence-based network equipment maintenance operation automation system 100 may include a plurality of user terminals 110-1, ??, a server 120, and a database 130. there is. According to one embodiment, the database 130 is shown as configured separately from the server 120, but is not limited thereto, and the database 130 may be provided in the server 120. For example, the server 120 may include multiple artificial intelligence for performing machine learning algorithms. According to one embodiment, a plurality of user terminals (110-1, ?? server 120 and database 130) can be connected to communicate with each other through a network (N).

The network N may perform wireless or wired communication between a plurality of user terminals 110-1, ??, a server 120, a database 130, etc. For example, the network may be LTE (long- term evolution), LTE-A (LTE Advanced), CDMA (code division multiple access), WCDMA (wideband CDMA), WiBro (Wireless BroadBand), WiFi (wireless fidelity), Bluetooth, NFC (near field communication), It is possible to perform wireless communication according to a method such as GPS (Global Positioning System) or GNSS (global navigation satellite system), etc. For example, the network (N) is USB (universal serial bus), HDMI (high definition multimedia interface) ), RS-232 (recommended standard 232), or POTS (plain old telephone service), etc. may be used to perform wired communication.

The database 130 may store various data. The data stored in the database 130 is obtained, processed, or used by at least one component of the plurality of user terminals 110-1, ?? : program) The database 130 may include volatile and/or non-volatile memory.

In the present invention, artificial intelligence (AI) means a technology that imitates human learning ability, reasoning ability, perception ability, etc., and implements it with a computer, and concepts such as machine learning and symbolic logic can include Machine learning (ML) is an algorithm technology that classifies or learns the characteristics of input data by itself. Artificial intelligence technology is a machine learning algorithm that analyzes input data, learns the result of the analysis, and can make judgments or predictions based on the result of the learning. In addition, technologies that mimic the functions of the human brain, such as cognition and judgment, using machine learning algorithms, can also be understood as the category of artificial intelligence. For example, technical fields such as linguistic understanding, visual understanding, inference/prediction, knowledge expression, and motion control may be included.

Machine learning may refer to processing that trains a neural network model using experience of processing data. Through machine learning, computer software could mean improving its own data processing capabilities. A neural network model is constructed by modeling a correlation between data, and the correlation may be expressed by a plurality of parameters. The neural network model extracts and analyzes features from given data to derive a correlation between the data. Machine learning is to optimize the parameters of the neural network model by repeating this process. For example, a neural network model may learn a mapping (correlation) between an input and an output with respect to data given as an input/output pair. Alternatively, even when only input data is given, the neural network model may learn the relationship by deriving regularities between given data.

An artificial intelligence learning model or a neural network model may be designed to implement a human brain structure on a computer, and may include a plurality of network nodes having weights while simulating neurons of a human neural network. A plurality of network nodes may have a connection relationship between them by simulating synaptic activities of neurons in which neurons exchange signals through synapses. In the artificial intelligence learning model, a plurality of network nodes can exchange data according to the convolution connection relationship while being located in layers of different depths. The artificial intelligence learning model may be, for example, an artificial neural network model, a convolutional neural network model (CNN), and the like. As an embodiment, the artificial intelligence learning model may be machine-learned according to methods such as supervised learning, unsupervised learning, and reinforcement learning. Machine learning algorithms for performing machine learning include Decision Tree, Bayesian Network, Support Vector Machine, Artificial Neural Network, and Ada-boost. ), perceptron, genetic programming, clustering, etc. can be used.

Of these, CNNs are a type of multilayer perceptrons designed to use minimal preprocessing. CNN consists of one or several convolutional layers and general artificial neural network layers placed on top of them, and additionally utilizes weights and pooling layers. Thanks to this structure, CNN can fully utilize the two-dimensional structure of the input data. Compared to other deep learning structures, CNN shows good performance in both video and audio fields. CNNs can also be trained via standard back-propagation. CNNs are easier to train than other feedforward artificial neural network techniques and have the advantage of using fewer parameters.

Convolutional networks are neural networks that contain sets of nodes with bound parameters. The increasing size of available training data and the availability of computing power, combined with algorithmic advances such as piecewise linear units and dropout training, have greatly improved many computer vision tasks. With huge data sets, such as those available for many tasks today, overfitting is not critical, and increasing the size of the network improves test accuracy. Optimal use of computing resources becomes a limiting factor. To this end, a distributed, scalable implementation of deep neural networks can be used.

2 is a diagram for explaining learning of a neural network according to an exemplary embodiment.

As shown in FIG. 2 , the learning device may train the neural network 123 in order to itemize the review responses received from the plurality of user terminals 110-1 (??). In addition, the learning device may train the neural network 123 to extract the user's stay details from the user's movement path information. According to one embodiment, the learning device may be a separate entity different from the server 120, but is not limited thereto.

The neural network 123 includes an input layer 121 into which training samples are input and an output layer 125 into which training outputs are output, and may be learned based on differences between the training outputs and labels. Here, the labels may be defined based on items corresponding to review responses and based on user stay details corresponding to movement path information. The neural network 123 is connected to a group of a plurality of nodes, and is defined by weights between the connected nodes and an activation function that activates the nodes.

The learning device may train the neural network 123 using a gradient descent (GD) technique or a stochastic gradient descent (SGD) technique. The learning device may use a loss function designed by outputs and labels of the neural network.

The learning device may calculate a training error using a predefined loss function. The loss function may be predefined with labels, outputs and parameters as input variables, where the parameters may be set by weights in the neural network 123. For example, the loss function may be designed in a mean square error (MSE) form, an entropy form, and the like, and various techniques or methods may be employed in an embodiment in which the loss function is designed.

The learning device may find weights affecting the training error using a backpropagation technique. Here, weights are relationships between nodes in the neural network 123 . The learning device may use the SGD technique using labels and outputs to optimize the weights found through the backpropagation technique. For example, the learning device may update weights of a loss function defined based on labels, outputs, and weights using the SGD technique.

According to an embodiment, the learning device extracts first objects from the review response, obtains first labels corresponding to the first objects, applies the first objects to a first neural network, and First training outputs corresponding to the first training outputs may be generated, and the first neural network may be trained based on the first training outputs and the first labels.

The learning device extracts second objects from movement path information, obtains second labels corresponding to the second objects, which are details of a user's stay, and applies the second objects to a second neural network to obtain information on the second objects. Corresponding second training outputs may be generated, and the second neural network may be trained based on the second training outputs and the second labels.

According to an embodiment, the learning device may generate first training feature vectors based on configuration features, location features, and pattern features of the review response. Various methods may be employed to extract features.

According to an embodiment, the learning device may generate second training feature vectors based on configuration features, length features, and pattern features of the movement path information. Various methods may be employed to extract features.

According to an embodiment, the learning device may obtain training outputs by applying the first training feature vectors to the neural network 123. The learning device may train the review item extraction algorithm of the neural network 123 based on the training outputs and the first labels. The learning device calculates training errors corresponding to the training outputs, and optimizes a connection relationship between nodes in the neural network 123 to minimize the training errors, thereby training the review item extraction algorithm of the neural network 123. . The server 120 may extract items from the review response using the first neural network for which learning has been completed. For example, the extracted items may include friendliness, store cleanliness, service satisfaction, etc., but are not limited thereto.

According to an embodiment, the learning device may obtain training outputs by applying the second training feature vectors to the neural network 123. The learning device may learn an algorithm for obtaining user stay details of the neural network 123 based on the training outputs and the second labels. The learning device calculates training errors corresponding to the training outputs, optimizes the connection relationship of nodes in the neural network 123 to minimize the training errors, and trains the algorithm for obtaining user stay details of the neural network 123. can The server 120 may obtain the details of the user's stay from the moving path information by using the second neural network for which learning has been completed.

3 is a diagram showing the configuration of an artificial intelligence model according to an embodiment.

An artificial intelligence model according to an embodiment may include an input layer, a hidden layer, and an output layer.

An input layer is a layer related to input values input to an artificial intelligence model.

In the hidden layer, a feature map may be output by performing a multiply-accumulate (MAC) operation and an activation operation on an input value.

The MAC operation may be an operation of multiplying an input value by a corresponding weight and summing the multiplied values.

The activation operation may be an operation of inputting a result of the MAC operation to an activation function and outputting a resultant value. Activation functions can be of various types. For example, the activation function may include, but is not limited to, a sigmoid function, a tangent function, a relu function, a ricky relu function, a maxout function, and/or an elu function.

The hidden layer may consist of at least one layer. For example, when the hidden layer is composed of a first hidden layer and a second hidden layer, the first hidden layer outputs a feature map by performing a MAC operation and an activation operation based on the input value of the input system, and A feature map, which is a result value of the layer, may be an input value of the second hidden layer. The second hidden layer may perform a MAC operation and an activation operation based on the feature map resulting from the first hidden layer.

An output layer may be a layer related to a result value of an operation performed in a hidden layer.

In one embodiment, the learning model automatically learns the boundaries of compound words and object names by learning syllable (letter) patterns that are frequently combined and used in a given corpus, and object information of the first UI source and object information rendered by the browser Integrating to create an object information file for learning, generating learning data for learning a deep learning network using the object information file for learning, receiving data from various domains of the support system, and corresponding to each of the various domains Based on at least one standardization method, standardizes the data of the various domains in an integrated format, learns and infers data of a specific domain, determines information to be transmitted for the standardization in the data of the specific domain, Post processing may be performed on data from the various domains. The first UI source includes an XML file, and the object information file for learning includes an input JSON file for learning features and an output JSON file that is label data during learning, and the output JSON file is a web standard. and the various domains include at least one of RAN (radio access network), transport, or core, and the post-processing is (correlation) function can be included.

4 is an exemplary diagram of a configuration of a system according to an embodiment.

The system 400 according to an embodiment may include an artificial intelligence learning model 410, a processor 420, and a memory 430, and some of the illustrated components may be omitted or replaced. System 400 according to an embodiment may be a server or a terminal. According to an embodiment, the processor 420 is a component capable of performing calculations or data processing related to control and/or communication of each component of the electronic device 400, and may include one or more processors. The memory 430 may store information related to the above-described method or a program in which the above-described method is implemented. Memory 430 may be volatile memory or non-volatile memory. The memory 430 may store various file data, and the stored file data may be updated according to the operation of the processor 120 .

According to an embodiment, the artificial intelligence learning model 410 may be designed to implement the structure of the human brain on a computer, and may include a plurality of network nodes having weights while simulating neurons of a human neural network. there is. A plurality of network nodes may have a connection relationship between them by simulating synaptic activities of neurons that transmit and receive signals through synapses. In the artificial intelligence learning model, a plurality of network nodes can exchange data according to the convolution connection relationship while being located in layers of different depths. The artificial intelligence learning model may be, for example, an artificial neural network model or a convolutional neural network (CNN) model. As an embodiment, the artificial intelligence learning model may be machine-learned according to methods such as supervised learning, unsupervised learning, and reinforcement learning.

According to one embodiment, the processor 420 may execute a program and control the device 400 . Program codes executed by the processor 120 may be stored in the memory 430 . Operations of the processor 420 may be performed by loading instructions stored in the memory 430 . The system 400 may be connected to an external device (eg, a personal computer or network) through an input/output device (not shown) and exchange data.

According to an embodiment, the processor 420 obtains first device information including the type, structure, operation method, and operation data of the first device corresponding to the first company, from an external server. Obtain operation data of a second device, a third device, and an Nth device having the same type, structure, and operation method as the first device; Provides the driving data of and the driving data of the Nth device as inputs to the artificial intelligence learning model, obtains a performance standard for network equipment of the same type as the first device, and determines the performance standard for the network equipment , Driving data of the first device may be provided as an input to the artificial intelligence learning model, and information on the state and remaining life of the first device may be obtained.

The artificial intelligence learning model 410 takes the driving data of the first device, the driving data of the second device, the driving data of the third device, and the driving data of the Nth device as inputs, calculates an average, and based on the average value Thus, a performance standard for network equipment of the same type as the first device may be output, and information on the status and remaining life of the first device may be output based on operation data of the first device and the performance standard. The performance standard of network equipment is firewall (FW), distributed denial of service attack (DDoS) response, web firewall (WebFW), virtual private network (VPN), network access control (NAC), intrusion prevention system (IPS), maximum connection creation rate per second (CPS), a maximum number of concurrent sessions (CC), a traffic throughput (BW), or a maximum transaction generation rate (TPS), and N may mean a natural number of 3 or more.

According to an embodiment, the processor 420 determines the degree of difference between the performance of the first device (eg, 90 points) and the performance standard (eg, 100 points) when the performance of the first device falls short of the performance standard. Display in numerical form (for example, a difference of 10%), and measure the performance of the first device again at a second time point after a certain time has elapsed based on the fact that the performance of the first device measured at the first time point is lower than the performance standard and the performance of the first device at the first time point (eg, present) (eg, 90 points) and the performance of the first device at the second time point (eg, 3 months from now) (eg, 70 points) , calculates a slope at which the performance decreases, and based on the calculated slope (eg, a decrease of 20 points in 3 months), the first device compares the performance standard to a first level (eg, 40%) (e.g., a 20-point decrease in 3 months, so 6 months later, a difference of 40 points determines that the event will occur) The remaining life of the first device (eg 5 months) may be calculated.

According to an embodiment, the processor 420 determines that there is an error in the first device when the performance of the first device falls below a specified level compared to the performance standard, and responds to the occurrence of the error by the user terminal. To provide a notification, determine at least one part in which an error has occurred, receive price information of the part in which an error has occurred from at least one shopping mall server, and maintain based on the price information received from at least one shopping mall server. A maintenance estimate may be calculated, and information on the calculated maintenance estimate may be transmitted to the user terminal.

According to an embodiment, the processor 420 determines that the period remaining until the expected event occurrence time is the first period (eg, 1 month), the first period is included within a preset reference range (eg, 3 months). When the first period (eg, 1 month) is out of a predetermined reference range (eg, 15 days), the expected event occurrence rate may be displayed as normal. The reference range (eg, 3 months to 15 days) may be determined based on the period during which the first device was installed, the year of the first device, and the error occurrence history of the first device. For example, when the first device is installed for more than one year, the reference range may be relatively low compared to when the first device is installed for one month. In this case, even if the period remaining until the event is expected to occur is the same as the first period (eg, 1 month), if the period in which the first device is installed exceeds one year, the expected event occurrence rate may be displayed as high, and the first device If the installed period is 1 month, the expected event rate may be displayed as normal.

According to an embodiment, the processor 420 subtracts the performance index (eg, 50 points) of the first device at the second time point from the performance index (eg, 80 points) of the first device at the first time point. is determined as a first value (eg, 30 points), and when the replacement cycle of the same network equipment as the first equipment is identified as the first period (eg, 3 years), the first value (eg, 30 points) If included within the set reference range (eg 50 points), the replacement cycle of the first equipment is determined as the first period, and when the first value exceeds the preset reference range (eg 20 points), the first device It is determined that the aging rate is faster than expected, and a replacement cycle of the first equipment may be determined as a second period shorter than the first period (eg, 1 year). The second period is determined based on the first period and the rate at which the first value exceeds a preset reference range, and the second period is shortened as the rate at which the first value exceeds the preset reference range increases, The second period may be set closer to the first period as the ratio of the first value exceeding the predetermined reference range is smaller.

For example, in the first case, the standard range is 20 points, and if the first value is 30 points, it exceeds 10 points. In the second case, the standard range is 20 points, but if the first value is 40 points, 20 points. exceeds the amount In this case, the excess ratio of the first case is relatively smaller than that of the second case. In the first case, the replacement cycle of the first equipment can be formed close to the first period (eg, 3 years) (eg, 2 years), and in the case of the second case, the excess rate is higher, so the replacement of the first equipment The cycle may be formed relatively far from the first period (eg 3 years) (eg 1 year). That is, in the case of the first case, replacement may be required after 2 years, and in the case of the 2nd case Replacement may be required after one year.

According to one embodiment, calculation and data processing functions that the processor 420 can implement on the system 400 will not be limited, but hereinafter, functions for automating maintenance and repair of network equipment will be described.

5 is a flowchart of a method for automating maintenance operation of network equipment according to an embodiment.

Although process steps, method steps, algorithms, etc. are described in a sequential order in the flowchart of FIG. 5, such processes, methods and algorithms may be configured to operate in any suitable order. In other words, the steps of the processes, methods and algorithms described in the various embodiments of the invention need not be performed in the order described herein. Also, although some steps are described as being performed asynchronously, in other embodiments, some of these steps may be performed concurrently. Further, illustration of a process by depiction in the drawings does not mean that the illustrated process is exclusive of other changes and modifications thereto, and that any of the illustrated process or steps thereof may be one of various embodiments of the present invention. It is not meant to be essential to one or more, and it does not imply that the illustrated process is preferred.

In operation 510, a processor (eg, the processor 420 of FIG. 4 ) may obtain first device information including type, structure, operating method, and operation data of the first device. The processor 420 may obtain driving data of the second device, the third device, and the Nth device having the same type, structure, and operation method as the first device from an external server. N means a natural number of 3 or more.

In operation 520, the processor 420 may input driving data of a plurality of devices to an artificial intelligence learning model (eg, the artificial intelligence learning model 410 of FIG. 4). The processor 420 may provide driving data of the first device, driving data of the second device, driving data of the third device, and driving data of the Nth device to the artificial intelligence learning model 410 as inputs. .

In operation 530, the processor 420 may determine a performance standard through the artificial intelligence learning model 410. The artificial intelligence learning model 410 takes the driving data of the first device, the driving data of the second device, the driving data of the third device, and the driving data of the Nth device as inputs, calculates an average, and based on the average value Thus, a performance standard for network equipment of the same type as the first device may be output. The performance standard of network equipment is firewall (FW), distributed denial of service attack (DDoS) response, web firewall (WebFW), virtual private network (VPN), network access control (NAC), intrusion prevention system (IPS), maximum connection creation rate per second (CPS), a maximum number of concurrent sessions (CC), a traffic throughput (BW), or a maximum transaction generation rate (TPS).

In operation 540, the processor 420 may input the driving data of the first device to the artificial intelligence learning model 410 and obtain information about the state and remaining life of the first device.

According to an embodiment, the processor 420 determines the degree of difference between the performance of the first device (eg, 90 points) and the performance standard (eg, 100 points) when the performance of the first device falls short of the performance standard. Display in numerical form (for example, a difference of 10%), and measure the performance of the first device again at a second time point after a certain time has elapsed based on the fact that the performance of the first device measured at the first time point is lower than the performance standard and the performance of the first device at the first time point (eg, present) (eg, 90 points) and the performance of the first device at the second time point (eg, 3 months from now) (eg, 70 points) , calculates a slope at which the performance decreases, and based on the calculated slope (eg, a decrease of 20 points in 3 months), the first device compares the performance standard to a first level (eg, 40%) (e.g., a 20-point decrease in 3 months, so 6 months later, a difference of 40 points determines that the event will occur) The remaining life of the first device (eg 5 months) may be calculated. The process of determining the remaining life will be described in more detail in FIG. 6 .

6 is a flowchart illustrating a method for automating maintenance operation of network equipment according to an embodiment.

At operation 610, a processor (eg, processor 420 of FIG. 4) may determine whether the performance of the first device is less than standard performance.

In operation 620, the processor 420 quantifies the difference from the standard performance (eg, a difference of 20 points) based on the fact that the performance (eg, 80 points) of the first device is less than the standard performance (eg, 100 points) and displays the difference. can do.

In operation 630, the processor 420 determines the performance (eg, 90 points) of the first device at a first time point (eg, present) and the performance of the first device at a second time point (eg, 3 months from now). Performance (e.g. 70 points) can be compared.

In operation 640, the processor 420 determines the performance (eg, 90 points) of the first device at a first time point (eg, present) and the performance of the first device at a second time point (eg, 3 months from now). By comparing performance (e.g. 70 points), we can calculate the slope of decreasing performance (e.g. 20 points decrease over 3 months).

In operation 650, the processor 420 may determine when an event is expected to occur. For example, since the processor 420 decreased by 20 points for 3 months, it may be determined that an event (eg, an error or a device replacement cycle arrives) occurs after a difference of 40 points after 6 months.

In operation 660, the processor 420 may determine the remaining lifespan of the first device based on an expected event occurrence time. The processor 420 may calculate the remaining lifespan (eg, 5 months) of the first device based on the expected event occurrence time (eg, 6 months).

According to an embodiment, the processor 420 determines that there is an error in the first device when the performance of the first device falls below a specified level compared to the performance standard, and responds to the occurrence of the error by the user terminal. To provide a notification, determine at least one part in which an error has occurred, receive price information of the part in which an error has occurred from at least one shopping mall server, and maintain based on the price information received from at least one shopping mall server. A maintenance estimate may be calculated, and information on the calculated maintenance estimate may be transmitted to the user terminal.

7 is a configuration diagram of a system for automating maintenance and operation of network equipment according to an embodiment.

According to FIG. 7 , a maintenance operation automation system for network equipment may include a customer equipment 710 , a management server 720 , and a plurality of online shopping mall servers 730 and 732 . Equipment subject to maintenance and repair services in the network equipment maintenance operation automation system may include at least one of corporate computer servers, storage, security and network equipment, or corporate computer equipment.

The customer equipment 710 is a terminal used by a customer who receives maintenance service, and may include any one of a PC, PDA, or smart phone equipped with a communication function with the management server 720 .

The online shopping mall servers 730 and 732 are servers that sell various parts required for equipment maintenance online, and can provide the management server 720 with price information of various parts in real time.

The management server 720 is a server that provides maintenance services for network equipment and can determine whether network equipment has a problem. The management server 720 may detect an abnormality in the network equipment and determine a component in which the abnormality occurs. The management server 720 calculates a base price for each part based on the price information of various parts provided from the online shopping mall servers 730 and 732, generates a maintenance cost estimate based on the calculated base price, and generates a repair cost estimate based on the calculated base price. (710).

Claims (3)

In the maintenance operation automation system of network equipment,
processor;
memory; and
Including an artificial intelligence learning model,
The processor
obtaining first device information about a first device corresponding to a first enterprise, including the type, structure, operation method and operation data of the first device;
Obtain driving data of a second device, a third device, and an Nth device having the same type, structure, and operation method as the first device from an external server;
Driving data of the first device, driving data of the second device, driving data of the third device, and driving data of the Nth device are provided as inputs to the artificial intelligence learning model, and the same type as the first device is provided. Acquire performance standards for network equipment of
When a performance standard for the network equipment is determined, driving data of the first device is provided as an input to the artificial intelligence learning model, information on a state and remaining life of the first device is obtained,
The artificial intelligence learning model is
The driving data of the first device, the driving data of the second device, the driving data of the third device, and the driving data of the Nth device are used as inputs to calculate an average, and based on the average value, the same value as that of the first device is calculated. Output performance standards for types of network equipment,
outputting information about a state and remaining life of the first device based on the operating data and the performance standard of the first device;
The performance standard is
Network equipment firewall (FW), distributed denial of service attack (DDoS) response, web firewall (WebFW), virtual private network (VPN), network access control (NAC), intrusion prevention system (IPS), maximum connection creation rate per second (CPS) , includes at least one element of the maximum number of concurrent sessions (CC), traffic throughput (Throughput (BW)), or maximum transaction generation rate (TPS) per second;
Wherein N means a natural number of 3 or more,
The processor
If the performance of the first device does not meet the performance standard, the degree of difference is digitized and displayed;
Measure the performance of the first device again at a second time point after a predetermined time based on the performance of the first device measured at the first time point being lower than the performance standard;
Comparing the performance of the first device at the first time point with the performance of the first device at the second time point, calculating a slope at which the performance decreases;
Based on the calculated slope, the first device compares the performance standard to determine an expected time of occurrence of an event in which a difference exceeds a first level;
Calculate the remaining lifespan of the first device based on an expected event occurrence time;
If the period remaining until the event is expected to occur is confirmed as the first period,
When the first period is included within a preset reference range, the event occurrence rate is adjusted to high and displayed on the user terminal;
When the first period is out of a predetermined reference range, the event occurrence rate is adjusted to a relatively low average and displayed on the user terminal,
The above standard range is
Determined based on the period during which the first device was installed, the age of the first device, and a history of error occurrence of the first device;
The processor
determining a value obtained by subtracting a performance index of the first device at the second time point from a performance index of the first device at the first time point as a first value;
When the replacement cycle of the same network equipment as the first device is identified as the first period,
When the first value is within a preset reference range, determining a replacement cycle of the first equipment as a first period;
When the first value exceeds a preset reference range, it is determined that the aging rate of the first device is faster than expected, and a replacement cycle of the first device is determined as a second period shorter than the first period,
The second period is
The first period and the first value are determined based on a ratio exceeding a preset reference range,
The second period is shortened as the ratio of the first value exceeding the preset reference range increases,
The second period is set closer to the first period as the ratio of the first value exceeding the preset reference range is smaller.
delete According to claim 1,
The processor
determining that there is an error on the first device if the performance of the first device falls below a specified level compared to the performance standard;
Provides a notification corresponding to the occurrence of an error to the user terminal,
determining at least one faulty component;
Receiving price information of an error-occurring part from at least one shopping mall server;
Calculate a maintenance estimate based on price information received from at least one shopping mall server;
A system for transmitting information about the calculated maintenance estimate to the user terminal.

Images