Method, device and computer readable medium for detecting performance of network element equipment

By building a risk assessment index system and using genetic algorithms to optimize weights and thresholds, the subjectivity and inefficiency of traditional network element equipment performance evaluation methods are solved, accurate assessment of network element equipment performance and risk warning are achieved, and fault prevention is improved ability.

CN114302418BActive Publication Date: 2024-11-05CHINA TELECOM CORP LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202111637846.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-29
Publication Date
2024-11-05
Estimated Expiration
2041-12-29

AI Technical Summary

Technical Problem

Traditional network element equipment performance and risk assessment methods are subjective and inefficient, affecting the accuracy and credibility of the assessment results, and lacking timely abnormal warnings and effective failure prevention measures.

Method used

By obtaining the historical communication data of network element devices, a risk assessment index system is built, and a genetic algorithm is used to optimize weights and thresholds to build a risk assessment model, thereby determining the risk level and achieving automation and accuracy of risk assessment.

Benefits of technology

It improves the accuracy and reliability of risk assessment, reduces the frequency of failures, improves the efficiency of operation and maintenance work, and provides a timely warning mechanism.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114302418B_ABST
    Figure CN114302418B_ABST
Patent Text Reader

Abstract

The present application belongs to the field of communication technology, and specifically relates to a method, device and computer-readable medium for detecting the performance of network element equipment. The method includes: obtaining historical communication data of the network element equipment, and determining the risk source based on the historical communication data, wherein the risk source is a factor that affects the performance of the network element equipment; constructing a risk assessment index system based on the risk source; optimizing the weights and thresholds in the risk assessment index system to obtain a risk assessment model; inputting the risk assessment index of the network element equipment into the risk assessment model to obtain a risk assessment value; and determining the risk level of the network element equipment based on the risk assessment value. In this way, constructing a risk assessment index system through risk sources and optimizing the weights and thresholds in the risk assessment index system is conducive to constructing a risk assessment model that is more in line with the actual situation, thereby making the predicted risk assessment value more accurate and the risk assessment result more reliable.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application belongs to the field of communication technology, and specifically relates to a method, device and computer-readable medium for detecting performance of network element equipment. Background Art

[0002] There are a large number of network element devices in the 5G core network (5GC). In actual application scenarios, to ensure that different types of network element devices are in normal operation, it is necessary to test the performance of the network element devices and evaluate the possible failure risks, determine the risk level and take necessary countermeasures.

[0003] Traditional risk assessment methods are all subjective analysis methods, which require artificial setting of values ​​​​of some key risk sources during the analysis process, which greatly affects the accuracy and credibility of the assessment results.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present application, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of this application is to provide a method, device and computer-readable medium for detecting the performance of network element equipment, which to a certain extent achieves more accurate performance evaluation results, thereby making the risk assessment results more reliable.

[0006] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0007] According to one aspect of an embodiment of the present application, a method for detecting performance of a network element device is provided, the method comprising:

[0008] Acquire historical communication data of the network element device, and determine the risk source according to the historical communication data, wherein the risk source is a factor that affects the performance of the network element device;

[0009] Based on the risk sources, a risk assessment indicator system is constructed;

[0010] Optimizing the weights and thresholds in the risk assessment indicator system to obtain a risk assessment model;

[0011] Inputting the risk assessment index of the network element device into the risk assessment model to obtain a risk assessment value;

[0012] The risk level of the network element device is determined according to the risk assessment value.

[0013] According to one aspect of an embodiment of the present application, a device for detecting performance of a network element device is provided, the device comprising:

[0014] An acquisition module, used to acquire historical communication data of a network element device, and determine a risk source according to the historical communication data, wherein the risk source is a factor that affects the performance of the network element device;

[0015] A construction module, used to construct a risk assessment indicator system based on the risk source;

[0016] An optimization module, used to optimize the weights and thresholds in the risk assessment indicator system to obtain a risk assessment model;

[0017] An evaluation module, used for inputting the risk evaluation index of the network element device into the risk evaluation model to obtain a risk evaluation value;

[0018] A determination module is used to determine the risk level of the network element device according to the risk assessment value.

[0019] In some embodiments of the present application, based on the above technical solution, the construction module is also used to construct an objective function according to the actual number of risk sources of the network element device during operation to obtain the risk assessment indicator system.

[0020] In some embodiments of the present application, based on the above technical solution, the optimization module is also used to construct an initial weight and threshold population; calculate the fitness of the initial weight and threshold population; select, cross, and mutate the initial weight and threshold population according to the fitness of the initial weight and threshold population until the termination condition is met to obtain the optimal weight and the optimal threshold; substitute the optimal weight and the optimal threshold into the risk assessment indicator system to obtain the risk assessment model.

[0021] In some embodiments of the present application, based on the above technical solution, the optimization module is also used to encode the weights and thresholds in the risk assessment index system; each set of the weights and the thresholds is formed into a chromosome, and multiple chromosomes are selected according to different combinations of the weights and the thresholds to obtain the initial weight and threshold population.

[0022] In some embodiments of the present application, based on the above technical solution, the optimization module is also used to calculate the objective function value of each chromosome in the initial weight and threshold population according to the objective function; and to obtain the fitness of the initial weight and threshold population according to the objective function value and preset constraints.

[0023] In some embodiments of the present application, based on the above technical solution, the optimization module is also used to select the initial weight and threshold population according to the fitness of the initial population to form a new weight and threshold genetic population; pair the generated new weight and threshold genetic population to generate a genetic pairing risk assessment population; cross the genetic pairing risk assessment population to obtain a genetic crossover risk assessment population; mutate the genetic crossover risk assessment population to form a secondary genetic risk assessment population.

[0024] In some embodiments of the present application, based on the above technical solution, the optimization module is also used to calculate the objective function value of each chromosome in the secondary genetic risk assessment population, and use the secondary genetic risk assessment population as the initial risk assessment population for the next round; repeatedly iteratively calculate the fitness of the initial risk assessment population for the next round, and obtain the objective function value based on the fitness calculation; until the corresponding weight and threshold combination population when the objective function value is the lowest is calculated to obtain the optimal weight and optimal threshold.

[0025] According to one aspect of an embodiment of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for detecting the performance of a network element device in the above technical solution is implemented.

[0026] According to one aspect of an embodiment of the present application, an electronic device is provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute a method for detecting performance of a network element device as in the above technical solution by executing the executable instructions.

[0027] According to one aspect of the embodiments of the present application, a computer program product or a computer program is provided, the computer program product or the computer program including computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method for detecting the performance of a network element device as in the above technical solution.

[0028] In the technical solution provided in the embodiments of the present application, a risk assessment index system is constructed through risk sources, and the weights and thresholds in the risk assessment index system are optimized, which is conducive to constructing a risk assessment model that is more in line with the actual situation, thereby making the predicted risk assessment value more accurate and the risk assessment result more reliable.

[0029] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0031] Figure 1 The following schematically illustrates the steps of a method for detecting performance of a network element device provided in an embodiment of the present application.

[0032] Figure 2 The schematic diagram shows the steps of optimizing the weights and thresholds in the risk assessment indicator system in one embodiment of the present application to obtain a risk assessment model.

[0033] Figure 3 The step flow of constructing the initial weight and threshold population in one embodiment of the present application is schematically shown.

[0034] Figure 4 The flowchart schematically shows the steps for calculating the initial weight and the fitness of the threshold population in one embodiment of the present application.

[0035] Figure 5 The flowchart schematically shows the steps of selecting, crossing over and mutating the initial weight and threshold population according to the fitness of the initial weight and threshold population in one embodiment of the present application.

[0036] Figure 6 The following schematically illustrates the steps of a method for detecting the performance of a network element device provided in another embodiment of the present application.

[0037] Figure 7 The overall flow chart of the system of an embodiment of the present application is schematically shown.

[0038] Figure 8 The structural block diagram of the network element equipment performance detection device provided in an embodiment of the present application is schematically shown.

[0039] Fig. 9 The structure block diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0040] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0041] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0042] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0043] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0044] 5G core network (5GC) is an important part of 5G construction. With the rapid expansion of the operation scale and business carrying capacity of the communication network, the complexity of the communication network is also increasing, and at the same time, it inevitably brings certain security risks. The communication network contains a complex network structure. There are also a large number of network element devices in the 5GC core network. Its operation status will be affected by many factors such as the environment. Due to the influence of complex factors, once a failure occurs in actual operation, it will have a serious impact on communication. However, according to the actual experience of operation and maintenance personnel, these failures in the operation process are not accidental or sudden. The process of failure is often a qualitative change caused by quantitative change. That is, before the failure occurs, some performance indicators of the network element device have already had certain problems, such as exceeding the predetermined normal range or an error. Therefore, it is necessary to perform performance detection and risk assessment on the real-time operation status of the communication network, judge the health status of the network element device, and discover potential risks in a timely manner. This is of great significance for reducing the frequency of sudden failures in the communication network and ensuring the stable operation of the network element device.

[0045] However, when conducting risk assessment, the traditional risk judgment methods used by operation and maintenance personnel are somewhat subjective and inefficient. For example, the traditional method requires manual setting of the values ​​of some key risk factors during the analysis process, which greatly affects the accuracy and credibility of the assessment results; secondly, the inefficient manual troubleshooting method also consumes a lot of human resources, and still cannot meet the risk troubleshooting requirements in the complex communication process of network element equipment. In addition, there is a lack of timely warning of abnormal information, and there is a lack of timeliness.

[0046] Specifically, there are two main methods for diagnosing faults of network element devices in current communication networks:

[0047] The first method is to simply compare the performance indicators of network element equipment, relying on manual judgment by operation and maintenance personnel. When a performance indicator parameter of a network element equipment exceeds the predetermined normal range or is in an error state, it is directly judged as abnormal data and corresponding measures are taken.

[0048] The second method is: traditional intelligent operation and maintenance methods are combined with data analysis methods to establish some theoretical models of machine learning and deep learning, obtain the original time series information of certain network performance indicators within a certain period, and then use normalization, denoising and other data processing methods to use the processed data as algorithm input, use K-nearest neighbor algorithm, support vector machine and other classification algorithms to classify the input data, and judge whether it is abnormal based on the classification results combined with certain judgment criteria to achieve performance detection and search and location of abnormal information.

[0049] The above two methods have certain shortcomings in many aspects such as the timeliness of early warning, scope of application, reliability and stability of prediction results, which brings many inconveniences in the actual operation and maintenance process.

[0050] In order to solve the above technical problems, this application proposes a method for detecting the performance of network element equipment. This method utilizes a large amount of sample data in the actual communication process of 5GC network element equipment and various performance indicators that reflect the operating status of network element equipment to construct a risk assessment indicator system. On the basis of the existing traditional risk assessment method that relies on manual analysis by operation and maintenance personnel, it combines the genetic algorithm in the field of artificial intelligence, and improves its genetic operations such as selection retention and crossover mutation, optimizes and solves the weights of multiple performance indicators in the network element equipment performance detection system, so as to obtain the optimal weight and the optimal threshold, thereby constructing a risk assessment model that is more in line with the actual situation, so that the predicted risk assessment value is more accurate, and the risk assessment result is more reliable. In this way, the subjectivity brought by the traditional 5GC network element equipment performance and risk assessment method is avoided, and the risk assessment result is more accurate and reliable. In addition, the efficiency of operation and maintenance work is also improved.

[0051] The following is a detailed description of a method, device and computer-readable medium for detecting performance of a network element device provided by the present application in conjunction with specific implementation methods.

[0052] See also Figure 1 , Figure 1 The method for detecting the performance of a network element device provided in an embodiment of the present application is schematically shown. The execution subject of the method may be a server, and the method may mainly include the following steps S101 to S105.

[0053] Step S101: acquiring historical communication data of a network element device, and determining a risk source according to the historical communication data, wherein the risk source is a factor that affects the performance of the network element device.

[0054] Obtaining the historical communication records of network element equipment and determining the risk source is conducive to obtaining the performance and risk assessment indicators of historical network element equipment, thereby facilitating the subsequent construction of a risk assessment indicator system. In this way, by utilizing a large amount of sample data in the actual communication process of 5GC network element equipment and various performance indicators reflecting the operating status of network element equipment, the characteristic data used is comprehensive and representative, which is conducive to the construction of a risk assessment indicator system.

[0055] By utilizing a large amount of sample data from the actual communication process of 5GC network elements and various performance indicators that reflect the operating status of network element equipment, we can intelligently detect the performance of network element equipment at a certain moment for different types of network element equipment, calculate the performance evaluation value, and determine the risk level, so as to take timely response measures to possible risks and reduce the frequency of network element equipment failures.

[0056] Step S102: construct a risk assessment indicator system based on risk sources.

[0057] Among them, the risk assessment index system is used to express the relationship between the risk source and the performance of the network element equipment. The risk assessment index system includes weights and thresholds. The values ​​of weights and thresholds have an impact on the performance of the network element equipment. By determining the optimal weights and optimal thresholds, it is helpful to determine the risk assessment value of the network element equipment, thereby obtaining a more accurate risk assessment value.

[0058] Step S103, optimizing the weights and thresholds in the risk assessment indicator system to obtain a risk assessment model.

[0059] Genetic algorithms are used to optimize the weights and thresholds in the risk assessment index system to obtain the optimal weights and thresholds. After obtaining the optimal weights and thresholds, they are substituted into the risk assessment index system to obtain the optimal risk assessment model. In this way, the optimal risk assessment model is constructed to facilitate the subsequent prediction of network element equipment risks, making the prediction results more accurate.

[0060] Step S104: input the risk assessment index of the network element device into the risk assessment model to obtain a risk assessment value.

[0061] After the risk assessment model is constructed, the risk assessment index of the network element device is input into the risk assessment model as an independent variable, so as to obtain the output as a risk assessment value. The risk assessment value is used to predict the possibility of risk occurring in the element device during the communication process.

[0062] Step S105: determining the risk level of the network element device according to the risk assessment value.

[0063] After obtaining the risk assessment value, the possible risks of network element equipment during the communication process can be obtained, and then feedback and warning of possible risks can be given, such as abnormal network element equipment name, IP address, location and other indicator information, for early warning. Then, the operation and maintenance personnel take timely response measures based on the feedback results to reduce the frequency of network element failures.

[0064] In the technical solution provided in the embodiment of the present application, a risk assessment index system is constructed through risk sources, and the weights and thresholds in the risk assessment index system are optimized, which is conducive to constructing a risk assessment model that is more consistent with the actual situation, thereby making the predicted risk assessment value more accurate and the risk assessment result more reliable. In addition, the risk assessment value is calculated, the risk level is determined, and the abnormalities that may occur during the network element communication process are fed back to the operation and maintenance personnel to take necessary countermeasures in a timely manner, thereby reducing the frequency of network element equipment failures.

[0065] In one embodiment of the present application, a risk assessment indicator system is constructed based on the risk source, including:

[0066] The objective function is constructed according to the actual number of risk sources of network element equipment during operation to obtain a risk assessment index system.

[0067] According to the daily experience of operation and maintenance personnel, the risk sources are searched and a risk assessment index system is preliminarily constructed. The objective function can be, for example, a linear function, Y = WX + b, where Y refers to the performance of the network element device, W refers to the weight, X refers to the risk assessment index, and b refers to the threshold. Of course, the setting of the objective function can also be other functions, which are not limited here.

[0068] In this way, by constructing a risk assessment indicator system, it is helpful to determine the correspondence between risk sources and network element equipment performance, which is beneficial to the subsequent evaluation and prediction of network element equipment performance.

[0069] In one embodiment of the present application, see Figure 2 , Figure 2The schematic diagram shows the steps of optimizing the weights and thresholds in the risk assessment index system to obtain the risk assessment model in one embodiment of the present application. The optimization of the weights and thresholds in the risk assessment index system to obtain the risk assessment model can mainly include the following steps S201 to S204.

[0070] Step S201, constructing an initial weight and threshold population.

[0071] Since the genetic algorithm is used to optimize the weights and thresholds, generally, before constructing the initial population, the genetic algorithm needs to set the initialization factor of the genetic algorithm. Specifically, the parameters in the genetic algorithm operation process are set, such as the population size Nind, the individual encoding method, the algorithm termination condition, and the subsequent crossover operator α, mutation operator β, selection operator γ, as well as the crossover probability Pc, mutation probability Pm, etc., and the initial population is established based on these parameters.

[0072] When constructing the initial weight and threshold population, randomly select values ​​within the range of the indicator weight W and the threshold b to form genes, and combine the genes corresponding to all decision variables to form individuals Pi. A random function is used to generate the initial population throughout the feasible domain: P = (P1; P2; ...; Pn) T .

[0073] Specifically, in one embodiment of the present application, see Figure 3 , Figure 3 The steps of constructing the initial weight and threshold population in one embodiment of the present application are schematically shown. Constructing the initial weight and threshold population may mainly include the following steps S301 to S302.

[0074] Step S301, encoding the weights and thresholds in the risk assessment indicator system.

[0075] The weights and thresholds in the risk assessment index system are encoded, and the encoding can be binary encoding or Gray code encoding.

[0076] Step S302, each set of weights and thresholds is grouped into a chromosome, and multiple chromosomes are selected according to different combinations of weights and thresholds to obtain an initial weight and threshold population.

[0077] The set of each weight and each threshold is determined as a group and combined into a chromosome. Different weights and different thresholds are combined to form multiple chromosomes, thereby constructing an initial weight and threshold population.

[0078] In this way, by encoding the weights and thresholds in the risk assessment index system, and then forming multiple chromosomes with different combinations of weights and thresholds, it is beneficial to construct the initial weight and threshold population, so as to facilitate the subsequent risk assessment model.

[0079] Step S202, calculating the initial weight and the fitness of the threshold population.

[0080] In the genetic algorithm, after constructing the initial population, the fitness of the initial population is then determined. Specifically, when calculating the fitness of the initial population, for the individual Pi of the initial population, its objective function value ObjV and fitness value FitnV are calculated according to the objective function (i.e., the evaluation method).

[0081] In one embodiment of the present application, see Figure 4 , Figure 4 The step flow of calculating the fitness of the initial weight and the threshold population in one embodiment of the present application is schematically shown. Calculating the fitness of the initial weight and the threshold population may mainly include the following steps S401 to S402.

[0082] Step S401, calculating the objective function value of each chromosome in the initial weight and threshold population according to the objective function;

[0083] Step S402, according to the objective function value and the preset constraints, to obtain the fitness of the initial weight and threshold population.

[0084] Among them, the preset constraints are agreed upon through weights, thresholds, and acceptable risk assessment ranges that meet stable operation requirements.

[0085] In this way, by calculating the fitness of the initial weight and threshold population, it is helpful to obtain the optimal weight and optimal threshold.

[0086] Step S203, according to the fitness of the initial weight and threshold population, the initial weight and threshold population are selected, crossed, and mutated until the termination condition is met to obtain the optimal weight and the optimal threshold.

[0087] In the genetic algorithm, after determining the fitness of the initial population, the population is selected, crossed, and mutated according to the fitness value of the individual. Aiming at the shortcomings of the traditional simple genetic algorithm, this application is based on the elite selection genetic algorithm (e-GA), which combines the tournament selection method with the elite retention strategy, and improves the selection method and genetic operation of the population P.

[0088] Among them, the improved selection and retention operation is that, during the evolution process, the parent population P is first subjected to conventional genetic operations, and after it produces offspring, the parent and offspring matrices are combined to generate a new population P', and then the new population P' is screened, and 50% of the elite individuals are selected from them using the tournament selection method to enter the next generation, and the offspring repeat in this way. This selection mechanism combining elite retention and tournament method ensures that the algorithm has sufficient elite retention ability, which plays a great role in the algorithm's rapid convergence to the optimal solution.

[0089] For the improved crossover and mutation operations, the improved algorithm adopts an adaptive design method to dynamically adjust the crossover probability Pc and mutation probability Pm according to the fitness value of the individual, thereby taking into account the convergence speed of the algorithm solution and the diversity of the population. The adjustment formulas for the crossover probability Pc and the mutation probability Pm are as follows:

[0090]

[0091]

[0092] Among them, f max is the maximum fitness value of individuals in the population, f avg is the average fitness value of the individuals in the population, f is the larger fitness value of the two individuals performing the crossover operation, is the fitness value of the mutant individual, k1, k2, k3 and k4 are all constants, and in the selection of parameters, k1<k2, k3<k4 are satisfied.

[0093] From the perspective of overall evolution, when the evolving population has a single gene, the diversity of individuals in the population is poor, and it lingers near the local optimal solution for several consecutive generations, the Pc and Pm values ​​tend to increase; conversely, when the individual gene diversity in the population is good and the fitness value has a large discreteness, the Pc and Pm values ​​tend to decrease. Therefore, for a specific generation of the population, the purpose of retaining elite individuals and timely eliminating individuals with poor fitness can be achieved.

[0094] Specifically, in one embodiment of the present application, see Figure 5 , Figure 5 The schematic diagram shows the steps of selecting, crossing, and mutating the initial weight and threshold population according to the fitness of the initial weight and threshold population in one embodiment of the present application. Selecting, crossing, and mutating the initial weight and threshold population according to the fitness of the initial weight and threshold population can mainly include the following steps S501 to S504.

[0095] Step S501, selecting the initial weight and threshold population according to the fitness of the initial population to form a new weight and threshold genetic population;

[0096] Step S502, pairing the newly generated weighted and threshold genetic populations to generate a genetic pairing risk assessment population;

[0097] Step S503, crossover the genetic pairing risk assessment population to obtain a genetic crossover risk assessment population;

[0098] Step S504, mutating the genetic crossover risk assessment population to form a secondary genetic risk assessment population.

[0099] In this way, the initial weight and threshold populations are selected, crossed, and mutated according to the fitness of the initial weight and threshold populations to obtain evolved offspring.

[0100] In one embodiment of the present application, see Figure 6 , Figure 6 The method for detecting the performance of a network element device provided in another embodiment of the present application is schematically shown. After the step of mutating the genetic crossover risk assessment group to form a secondary genetic risk assessment group, the method may mainly include the following steps S601 to S603.

[0101] Step S601, calculating the objective function value of each chromosome in the secondary genetic risk assessment population, and using the secondary genetic risk assessment population as the initial risk assessment population for the next round;

[0102] Step S602, repeatedly iteratively calculating the fitness of the initial risk assessment group for the next round, and obtaining the objective function value according to the fitness calculation;

[0103] Step S603, until the weight and threshold combination group corresponding to the lowest objective function value is calculated to obtain the optimal weight and optimal threshold.

[0104] After a complete round of evolution, the population produces offspring and determines whether the termination condition is met. If the termination condition is met, the evolution terminates and the optimal individual is output. After chromosome decoding, the optimal weight W and threshold b are obtained; if not, a new round of evolution is re-entered, and the cycle repeats. In this way, the individual with the highest fitness can be found at a relatively high computing speed, that is, the optimal solution to the actual problem is obtained.

[0105] In this way, by combining the genetic algorithm in the field of artificial intelligence and improving its genetic operation, the indicator weights and thresholds are optimized to obtain the optimal weights and thresholds. Compared with the traditional genetic algorithm, it has better performance in finding the global optimal solution and algorithm convergence, making the risk assessment results more accurate and reliable.

[0106] In one embodiment of the present application, in order to avoid the "premature phenomenon" (local convergence of the optimal solution), a global optimal solution is sought. During the evolution of a population, when the performance evaluation model contains a large number of local optimal solutions in the entire solution space, it causes a certain interference to the evolution process, causing the evolution process of the population to fall into the local optimum prematurely, and finally converge to the local optimal solution rather than the global optimal solution. To address this problem, this method selects multiple population genetic strategies, each population selects different crossover and mutation probabilities, and changes the operator, appropriately adjusts the probability of increasing mutation, and uses two-point crossover or multi-point crossover for the mutation process, thereby avoiding the occurrence of premature phenomenon while improving the optimization effect.

[0107] Step S204: Substitute the optimal weight and the optimal threshold into the risk assessment indicator system to obtain a risk assessment model.

[0108] In this way, by obtaining the risk assessment model, the risk assessment index of the network element device is input into the risk assessment model as an independent variable, and the risk assessment value is output.

[0109] In order to facilitate the understanding of the technical solution of the present application, the overall process of the solution is described as follows: Figure 7 , Figure 7 The overall flow chart of the system of an embodiment of the present application is schematically shown. A method for detecting the performance of a network element device is as follows: first, the risk factors in the actual communication of the network element are searched, the performance and risk assessment indicators are determined, and a risk assessment indicator system is constructed; then, the indicator weights and thresholds are optimized in combination with a genetic algorithm that improves genetic operations to obtain the optimal weights and optimal thresholds. Among them, a genetic algorithm is used to obtain the optimal weights and optimal thresholds, which mainly includes the steps of initializing individuals in the population and performing chromosome encoding, evaluating the fitness of individuals in the population, performing operations such as selection, crossover and mutation of the population, and judging the termination conditions of the algorithm; finally, the risk assessment value is calculated, the risk level is determined, and the anomalies that may occur during the communication of the network element device are fed back to the operation and maintenance personnel to take necessary countermeasures in a timely manner to reduce the frequency of network element failures.

[0110] Among them, the specific method for obtaining the optimal weight and the optimal threshold is as follows:

[0111] Step A: construct an objective function model, such as a linear model, according to the number of actual risk sources during the operation of the network element equipment, and construct constraint conditions based on the indicator weights, thresholds, and acceptable risk assessment ranges that meet stable operation requirements in the assessment model;

[0112] Step B, binary encoding or Gray code encoding is performed on the indicator weights and thresholds. A set of weights and thresholds constitutes a chromosome individual. Multiple chromosomes are selected according to different combinations of indicator weights and thresholds to form an initial weight and threshold population.

[0113] Step C, calculating the risk assessment value of each dyed individual in the initial weight and threshold population, that is, the objective function value, and calculating the fitness of the initial weight and threshold population according to the risk assessment objective function value and the constraints of the weight and threshold;

[0114] Step D, selecting the initial population according to the fitness of the initial population, and forming a new weighted and threshold genetic population;

[0115] Step E, pairing the genetic population generated in the previous step to generate a genetic pairing risk assessment population, crossing the genetic pairing risk assessment population to obtain a genetic crossover risk assessment population, and mutating the genetic crossover risk assessment population to form a secondary genetic risk assessment population;

[0116] Step F, calculate the risk assessment objective function value of each stained individual in the secondary genetic risk assessment group, and use the secondary genetic risk assessment group as the initial risk assessment group for the next round, repeat steps C to E, until the weighted threshold combination group with the lowest actual risk assessment value that meets the requirements of stable operation is calculated, at which time the optimal calculation result can be output.

[0117] It should be noted that although the steps of the method in the present application are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0118] The following introduces an apparatus embodiment of the present application, which can be used to execute the method for detecting the performance of network element equipment in the above-mentioned embodiment of the present application. Figure 8 The structure block diagram of the device for detecting the performance of a network element device provided in an embodiment of the present application is schematically shown. Figure 8 As shown, the network element device performance detection device 800 includes:

[0119] The acquisition module 801 is used to acquire historical communication data of the network element device and determine the risk source according to the historical communication data, wherein the risk source is a factor that affects the performance of the network element device;

[0120] A construction module 802 is used to construct a risk assessment indicator system based on risk sources;

[0121] The optimization module 803 is used to optimize the weights and thresholds in the risk assessment indicator system to obtain a risk assessment model;

[0122] An evaluation module 804 is used to input the risk evaluation index of the network element device into the risk evaluation model to obtain a risk evaluation value;

[0123] The determination module 805 is used to determine the risk level of the network element device according to the risk assessment value.

[0124] In some embodiments of the present application, based on the above technical solution, the construction module 802 is also used to construct an objective function according to the actual number of risk sources of the network element device during operation to obtain a risk assessment indicator system.

[0125] In some embodiments of the present application, based on the above technical solution, the optimization module 803 is also used to construct an initial weight and threshold population; calculate the fitness of the initial weight and threshold population; select, cross, and mutate the initial weight and threshold population according to the fitness of the initial weight and threshold population until the termination condition is met to obtain the optimal weight and the optimal threshold; substitute the optimal weight and the optimal threshold into the risk assessment indicator system to obtain a risk assessment model.

[0126] In some embodiments of the present application, based on the above technical solution, the optimization module 803 is also used to encode the weights and thresholds in the risk assessment index system; each set of weights and thresholds is formed into a chromosome, and multiple chromosomes are selected according to different combinations of weights and thresholds to obtain an initial weight and threshold population.

[0127] In some embodiments of the present application, based on the above technical solution, the optimization module 803 is also used to calculate the objective function value of each chromosome in the initial weight and threshold population according to the objective function; and to obtain the fitness of the initial weight and threshold population according to the objective function value and preset constraints.

[0128] In some embodiments of the present application, based on the above technical solution, the optimization module 803 is also used to select the initial weight and threshold populations according to the fitness of the initial population to form a new weight and threshold genetic population; pair the newly generated weight and threshold genetic populations to generate a genetic pairing risk assessment population; cross the genetic pairing risk assessment population to obtain a genetic crossover risk assessment population; mutate the genetic crossover risk assessment population to form a secondary genetic risk assessment population.

[0129] In some embodiments of the present application, based on the above technical solution, the optimization module 803 is also used to calculate the objective function value of each chromosome in the secondary genetic risk assessment population, and use the secondary genetic risk assessment population as the initial risk assessment population for the next round; repeatedly iteratively calculate the fitness of the initial risk assessment population for the next round, and obtain the objective function value based on the fitness calculation; until the corresponding weight and threshold combination population when the objective function value is the lowest is calculated to obtain the optimal weight and optimal threshold.

[0130] The specific details of the network element device performance detection device provided in each embodiment of the present application have been described in detail in the corresponding method embodiment and will not be repeated here.

[0131] Fig. 9 The structure block diagram of a computer system for implementing an electronic device according to an embodiment of the present application is schematically shown.

[0132] It should be noted that Fig. 9 The computer system 900 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0133] like Fig. 9 As shown, the computer system 900 includes a central processing unit 901 (CPU), which can perform various appropriate actions and processes according to the program stored in the read-only memory 902 (ROM) or the program loaded from the storage part 908 to the random access memory 903 (RAM). Various programs and data required for system operation are also stored in the random access memory 903. The central processing unit 901, the read-only memory 902 and the random access memory 903 are connected to each other through a bus 904. An input / output interface 905 (Input / Output interface, i.e., I / O interface) is also connected to the bus 904.

[0134] The following components are connected to the input / output interface 905: an input section 906 including a keyboard, a mouse, etc.; an output section 907 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 908 including a hard disk, etc.; and a communication section 909 including a network interface card such as a LAN card, a modem, etc. The communication section 909 performs communication processing via a network such as the Internet. A drive 910 is also connected to the input / output interface 905 as needed. A removable medium 911, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 910 as needed so that a computer program read therefrom is installed into the storage section 908 as needed.

[0135] In particular, according to an embodiment of the present application, the process described in each method flow chart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program contains a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 909, and / or installed from the removable medium 911. When the computer program is executed by the central processor 901, various functions defined in the system of the present application are executed.

[0136] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device or device or used in combination with it. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0137] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0138] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0139] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0140] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary technical means in the art that are not disclosed in the present application.

[0141] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A method for detecting performance of a network element device, characterized in that: The method comprises: Acquire historical communication data of the network element device, and determine the risk source according to the historical communication data, wherein the risk source is a factor that affects the performance of the network element device; Based on the risk sources, a risk assessment indicator system is constructed; Construct initial weight and threshold population; Calculating the fitness of the initial weight and threshold population; According to the fitness of the initial weight and threshold population, the initial weight and threshold population are selected, crossed, and mutated until the termination condition is met to obtain the optimal weight and optimal threshold; Substituting the optimal weight and the optimal threshold into the risk assessment indicator system to obtain a risk assessment model; Inputting the risk assessment index of the network element device into the risk assessment model to obtain a risk assessment value; The risk level of the network element device is determined according to the risk assessment value.

2. The method for detecting network element performance according to claim 1, characterized in that: Based on the risk source, a risk assessment indicator system is constructed, including: An objective function is constructed according to the actual number of risk sources of the network element equipment during operation to obtain the risk assessment index system.

3. The method for detecting network element device performance according to claim 1, characterized in that: The constructing of the initial weight and threshold population includes: Encoding weights and thresholds in the risk assessment indicator system; Each set of the weights and the thresholds is formed into a chromosome, and multiple chromosomes are selected according to different combinations of the weights and the thresholds to obtain the initial weight and threshold population.

4. The method for detecting network element performance according to claim 3, characterized in that: The calculating of the initial weight and the fitness of the threshold population includes: Calculate the objective function value of each chromosome in the initial weight and threshold population according to the objective function; According to the objective function value and the preset constraints, the fitness of the initial weight and threshold population is obtained.

5. The method for detecting network element performance according to claim 4, characterized in that: The selecting, crossing, and mutating the initial weight and threshold population according to the fitness of the initial weight and threshold population includes: Selecting the initial weight and threshold populations according to the fitness of the initial population to form new weight and threshold genetic populations; Pairing the newly generated weighted and threshold genetic populations to generate a genetic paired risk assessment population; Crossing the genetic paired risk assessment population to obtain a genetic crossover risk assessment population; The genetic crossover risk assessment population is mutated to form a secondary genetic risk assessment population.

6. The method for detecting network element device performance according to claim 5, characterized in that: After the step of mutating the genetic crossover risk assessment population to form a secondary genetic risk assessment population, the method further comprises: Calculating the objective function value of each chromosome in the secondary genetic risk assessment population, and using the secondary genetic risk assessment population as the initial risk assessment population for the next round; Repeat the iterative calculation of the fitness for the next round of initial risk assessment groups, and obtain the objective function value based on the fitness calculation; Until the corresponding weight and threshold combination group with the lowest objective function value is calculated, the optimal weight and optimal threshold are obtained.

7. A device for detecting performance of a network element device, characterized in that: The device comprises: An acquisition module, used to acquire historical communication data of a network element device, and determine a risk source according to the historical communication data, wherein the risk source is a factor that affects the performance of the network element device; A construction module, used to construct a risk assessment indicator system based on the risk source; An optimization module, used to optimize the weights and thresholds in the risk assessment indicator system to obtain a risk assessment model; An evaluation module is used to construct an initial weight and threshold population; calculate the fitness of the initial weight and threshold population; select, cross, and mutate the initial weight and threshold population according to the fitness of the initial weight and threshold population until the termination condition is met to obtain the optimal weight and the optimal threshold; substitute the optimal weight and the optimal threshold into the risk assessment indicator system to obtain the risk assessment value; A determination module is used to determine the risk level of the network element device according to the risk assessment value.

8. A computer-readable medium, characterized in that The computer-readable medium stores a computer program, which, when executed by a processor, implements the method for detecting the performance of a network element device as described in any one of claims 1 to 6.

9. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to execute the method for detecting the performance of a network element device as described in any one of claims 1 to 6 by executing the executable instructions.

Citation Information

Patent Citations

  • Risk assessment method, apparatus and device and computer readable storage medium

    CN111260243A

  • Communication network risk assessment method for optimizing deep neural network based on genetic algorithm

    CN111327462A

  • Electric power Internet-of-things information security risk assessment method and device

    CN111695754A

  • Risk quantitative evaluation method and device based on index management system and electronic equipment

    CN112668832A