Abnormal network equipment identification method and device

Abstract

The invention discloses an abnormal network equipment identification method and device. The method comprises the following steps: obtaining performance index parameter sets of a first network device newly accessed to a network and a plurality of second network devices accessed to the network in a passive optical network in a preset time period; determining at least one second target network device with the same model and / or the same version as the first network device according to the performance index parameter set of the first network device and each second network device; determining a specification boundary value according to the performance index parameter set of the first network device, and determining a process capability index of each second target network device according to the specification boundary value and the performance index parameter set of each second target network device; and for each second target network device, determining whether the second target network device has quality abnormality according to the process capability index of the second target network device. The technical problem that the related technology cannot accurately identify the abnormal network device whose performance index parameter is degraded but does not reach the poor-quality standard is solved.

Description

Technical Field

[0001] The present application relates to the field of network security technology, and in particular to a method and apparatus for identifying abnormal network equipment. Background Art

[0002] In the current PON (Passive Optical Network) operation and maintenance process, operators mainly rely on monitoring whether the performance indicator parameters of network equipment are lower than the preset threshold value to determine whether the network equipment has poor quality problems. However, this method can only identify situations where the performance of the equipment has significantly declined. For those network devices that have not yet reached the poor quality standard but whose performance indicator stability is gradually deteriorating, existing technologies often make it difficult to provide early warning. This technical problem leads to hidden faults in the network, which affect the user experience but are not easy to be discovered and handled in time. Especially in networks with diverse equipment models and complex operating environments, it is difficult to effectively predict and manage equipment aging and performance fluctuations, thereby increasing the difficulty and cost of network maintenance.

[0003] In response to the above problems, an intelligent algorithm is proposed that can perform early identification and evaluation of network equipment performance indicators, so as to accurately identify network equipment that is about to experience performance degradation and reduce the occurrence of poor network quality problems. Summary of the invention

[0004] The embodiments of the present application provide a method and apparatus for identifying abnormal network equipment, so as to at least solve the technical problem that the related art cannot accurately identify abnormal network equipment whose performance indicator parameters are degraded but do not meet the quality standard.

[0005] According to one aspect of an embodiment of the present application, a method for identifying abnormal network equipment is provided, including: obtaining a performance indicator parameter set of a newly connected first network equipment and multiple second network equipment that have been connected to a passive optical network within a preset time period, wherein the performance indicator parameter set is a parameter set of preset performance indicators of the network equipment within a preset time period; determining at least one second target network equipment of the same model and / or version as the first network equipment based on the performance indicator parameter set of the first network equipment and each second network equipment; determining a specification boundary value based on the performance indicator parameter set of the first network equipment, and determining a process capability index of each second target network equipment based on the specification boundary value and the performance indicator parameter set of each second target network equipment; for each second target network equipment, determining whether the second target network equipment has a quality abnormality based on the process capability index of the second target network equipment.

[0006] Optionally, a performance indicator parameter set of a newly connected first network device and multiple second network devices already connected to the passive optical network within a preset time period is obtained, including: a performance indicator parameter set of preset performance indicators collected within a preset time period by monitoring probes deployed on the first network device and each second network device in the passive optical network, wherein the types of preset performance indicators include: transmission power, received power, or received power signal-to-noise ratio.

[0007] Optionally, based on the performance indicator parameter sets of the first network device and each second network device, at least one second target network device of the same model and / or version as the first network device is determined, including: determining a first mean square deviation of the first network device on a preset performance indicator based on the performance indicator parameter set of the first network device, and determining a second mean square deviation of each second network device on the preset performance indicator based on the performance indicator parameter set of each second network device; using a hypothesis testing method to compare the first mean square deviation of the first network device on the preset performance indicator with the second mean square deviation of each second network device on the preset performance indicator, to determine at least one second target network device of the same model and / or version as the first network device.

[0008] Optionally, a hypothesis testing method is used to compare a first mean square error of the first network device on a preset performance indicator with a second mean square error of each second network device on a preset performance indicator to determine at least one second target network device of the same model and / or version as the first network device, including: for each second network device, calculating a quotient of the first mean square error of the first network device on the preset performance indicator and the second mean square error of the second network device on the preset performance indicator to obtain a corresponding verification statistic; when the verification statistic is not greater than a preset verification threshold, determining that the second network device is a second target network device of the same model and / or version as the first network device.

[0009] Optionally, determining a specification boundary value based on a performance indicator parameter set of the first network device, and determining a process capability index of each second target network device based on the specification boundary value and the performance indicator parameter set of each second target network device, including: determining a first mean and a first mean square deviation of the first network device on a preset performance indicator based on the performance indicator parameter set of the first network device, and determining a specification boundary value based on the first mean and the first mean square deviation, wherein the specification boundary value includes: an upper specification limit value and a lower specification limit value; determining a second mean and a second mean square deviation of the second target network device on a corresponding performance indicator based on the performance indicator parameter set of the second target network device; determining the process capability index of the second target network device based on the specification boundary value, the second mean and the second mean square deviation of the second target network device, and according to the following formula: Where μ represents the first mean, σ represents the first mean square deviation, μ+4σ represents the upper specification limit, μ-4σ represents the lower specification limit, and μ f,i represents the second mean of the i-th second target network device, σ f,i represents the second mean square error of the i-th second target network device.

[0010] Optionally, determining whether the second target network device has a quality abnormality based on a process capability index of the second target network device includes: when the process capability index of the second target network device is less than a preset threshold value, determining that the second target network device has a quality abnormality; when the process capability index of the second target network device is not less than a preset threshold value, determining that the second target network device does not have a quality abnormality.

[0011] Optionally, after determining that the second target network device has a quality abnormality, the method also includes: determining the size of the gap between the process capability index of the second target network device with the quality abnormality and a threshold value; determining the quality abnormality level of the second target network device with the quality abnormality based on the size of the gap; determining the management priority of the second target network device with the quality abnormality according to the quality abnormality level, and maintaining the second target network device with the quality abnormality in sequence according to the management priority.

[0012] According to another aspect of an embodiment of the present application, there is also provided an abnormal network device identification device, including: an acquisition module, used to obtain a performance indicator parameter set of a newly connected first network device and multiple second network devices that have been connected to the passive optical network within a preset time period, wherein the performance indicator parameter set is a parameter set of a preset performance indicator of the network device within a preset time period; a first determination module, used to determine at least one second target network device of the same model and / or version as the first network device based on the performance indicator parameter set of the first network device and each second network device; a second determination module, used to determine a specification boundary value based on the performance indicator parameter set of the first network device, and determine a process capability index of each second target network device based on the specification boundary value and the performance indicator parameter set of each second target network device; an abnormality discrimination module, used to determine, for each second target network device, whether the second target network device has a quality abnormality based on the process capability index of the second target network device.

[0013] According to another aspect of an embodiment of the present application, a computer program product is further provided, the computer program product comprising: a computer program, wherein when the computer program is executed by a processor, the above-mentioned abnormal network device identification method is implemented.

[0014] According to another aspect of an embodiment of the present application, an electronic device is further provided, comprising: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above-mentioned abnormal network device identification method through the computer program.

[0015] In an embodiment of the present application, a performance indicator parameter set of a newly connected first network device and a plurality of connected second network devices in a passive optical network within a preset time period is obtained, wherein the performance indicator parameter set is a parameter set of a preset performance indicator of a network device within a preset time period; at least one second target network device of the same model and / or version as the first network device is determined based on the performance indicator parameter set of the first network device and each second network device; the specification boundary value is determined based on the performance indicator parameter set of the first network device, and the process capability index of each second target network device is determined based on the specification boundary value and the performance indicator parameter set of each second target network device; for each second target network device, whether the second target network device has quality abnormalities is determined based on the process capability index of the second target network device. In other words, by combining big data analysis with statistical methods, the technical effect of intelligent identification and evaluation of quality abnormalities of network devices in the network is achieved, and the purpose of early warning and accurate positioning of network devices with performance problems is achieved, thereby optimizing the quality of network services, thereby solving the technical problem that the related technology cannot accurately identify abnormal network devices whose performance indicator parameters have degraded but have not reached the quality difference standard. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 It is a flowchart of an optional abnormal network device identification method according to an embodiment of the present application;

[0018] Figure 2 is a schematic structural diagram of an optional abnormal network device identification device according to an embodiment of the present application;

[0019] Figure 3 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0021] It should be noted that the terms "first", "second", etc. in the specification, claims and drawings of the present application are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0022] In order to better understand the embodiments of the present application, some nouns or terms that appear in the description of the embodiments of the present application are first translated and explained as follows:

[0023] PON (Passive Optical Network) is a pure medium network that uses point-to-multipoint optical fiber transmission and access technology, broadcasting for downlink and time division multiple access for uplink to flexibly form tree, star, bus and other topological structures, and only a simple optical splitter needs to be installed at the optical branching point. Therefore, it has the advantages of saving optical cable resources, sharing bandwidth resources, saving equipment room investment, fast network construction speed and low comprehensive network construction cost.

[0024] Mean: Also known as average value, it is the average value of a set of data, which is obtained by adding the data and then dividing it by the number of data. Its calculation formula is as follows:

[0025]

[0026] Where x i represents the i-th data, and n represents the total number of data.

[0027] Mean Squared Error (MSE): It is the average of the sum of squares of the distances of each data from the true value, that is, the average of the sum of squared errors. The calculation formula is as follows:

[0028]

[0029] Where x GT represents the true value, x i represents the i-th data, and n represents the total number of data.

[0030] Hypothesis Testing: Also known as statistical hypothesis testing, it is a statistical inference method used to determine whether the differences between samples and samples, or between samples and the population, are caused by sampling errors or essential differences. Significance testing is the most commonly used method in hypothesis testing and is also the most basic form of statistical inference. Its basic principle is to first make a certain hypothesis about the characteristics of the population, and then make an inference on whether the hypothesis should be rejected or accepted through statistical reasoning of sampling research. Commonly used hypothesis testing methods include: Z test, T test, F test, chi-square test, etc.

[0031] F-Test: also known as Joint Hypotheses Test, Variance Ratio Test, Variance Homogeneity Test. It is a test that the statistical value follows F-distribution under the Null Hypotheses (H0). It is usually used to analyze statistical models with more than one parameter to determine whether all or part of the parameters in the model are suitable for statistical population.

[0032] Process Capability Index: Also known as process capability index, it refers to the actual processing capability of a process in a controlled state (stable state) within a certain period of time. It is the inherent capability of the process, or it is the ability of the process to guarantee instructions. The process here refers to the process of the comprehensive effect of five basic quality factors such as operators, machines, raw materials, process methods and production environment, that is, the production process of product quality. Product quality is the comprehensive performance of the role of each quality factor in the process.

[0033] Example 1

[0034] According to an embodiment of the present application, a method for identifying abnormal network devices is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0035] Figure 1 is a flow chart of a method for identifying abnormal network devices provided according to an embodiment of the present application, such as Figure 1 As shown, the method includes the following steps S102-S108, wherein:

[0036] Step S102: acquiring a performance indicator parameter set of a newly connected first network device and a plurality of connected second network devices in the passive optical network within a preset time period.

[0037] In the technical solution provided in the above step S102, the above-mentioned first network device newly connected to the network can be understood as: a user terminal device that has been connected to and registered to the PON network for the first time in a recent period of time, such as an optical modem or a router, where the time period for newly connected to the network can be defined by the operator according to actual conditions, such as "within the past month", "within the past three months", etc. The multiple second network devices that have been connected to the network can be understood as: network devices that have been running in the network for a period of time, and their network access time is earlier than the defined new network access time period. Usually, the number of second network devices that have been connected to the network is usually much larger than that of newly connected network devices, and their performance indicator parameters can reflect the long-term performance of network devices in actual operating environments.

[0038] In addition, the performance indicator parameter set of the above-mentioned first network device and multiple second network devices that have entered the network within the preset time period can be a parameter set of the preset performance indicator of the network device within the preset time period, wherein the preset performance indicator can be one of multiple performance indicators.

[0039] Step S104: determining at least one second target network device of the same model and / or same version as the first network device according to the performance indicator parameter sets of the first network device and each second network device.

[0040] In the technical solution provided in the above step S104, since network devices of the same model usually use the same hardware configuration, and network devices of the same version run the same version of software or firmware. This means that network devices of the same model and / or the same version should have similar performance characteristics and parameter ranges in design, such as transmit power, receive power, signal-to-noise ratio, etc. Therefore, by analyzing the distribution between the performance indicator parameter sets of the first network device and each second network device, at least one second target network device with a similar distribution of the performance indicator parameter set to the first network device is identified, and it is inferred that the identified second target network device and the first network device belong to the same model or version.

[0041] Step S106, determining a specification boundary value according to the performance indicator parameter set of the first network device, and determining a process capability index of each second target network device according to the specification boundary value and the performance indicator parameter set of each second target network device.

[0042] In the technical solution provided in the above step S106, since the newly connected first network device is usually still in the early stage of performance testing and stability, its performance indicator parameter set can be used to establish a "healthy" benchmark performance indicator, that is, the specification boundary value of the second target network device of the same model and / or the same version, as the normal range of the device performance parameter. As the second target network devices that have been connected to the network, their performance may change due to aging, damage, software problems, etc. Therefore, by combining the specification boundary value and the performance indicator parameter set of each second target network device, the process capability index of each second target network device can be determined, and the process capability index can measure the degree to which the device process capability meets the specification range.

[0043] Step S108: for each second target network device, determine whether the second target network device has a quality abnormality according to the process capability index of the second target network device.

[0044] In the technical solution provided in the above step S108, the process capability index, as a quantitative indicator, can measure the degree of compliance between the performance parameters of the equipment and the predetermined specification boundary values, which reflects the stability and consistency of the network equipment during the manufacturing and operation process. Therefore, based on the process capability index of the second target network equipment, it can be judged whether its performance parameters do not meet the expected stability and consistency standards, so as to analyze whether the quality abnormality is caused by equipment aging, failure, software problems or other related factors.

[0045] Based on the technical solutions provided by the above steps S102 to S108, it can be known that in the embodiment of the present application, a combination of big data analysis and statistical methods is adopted to achieve the technical effect of intelligent identification and evaluation of abnormal quality of network equipment in the network, so as to achieve early warning and precise positioning of network equipment with performance problems, thereby optimizing the purpose of network service quality.

[0046] The following describes the various steps of the abnormal network device identification method in conjunction with a specific implementation process.

[0047] As an optional implementation, in the technical solution provided in the above step S102, the performance indicator parameter set of the network device can be obtained through the following steps, including: a performance indicator parameter set of preset performance indicators collected by monitoring probes deployed on the first network device and each second network device in the passive optical network within a preset time period.

[0048] Specifically, the embodiment of the present application detects a performance indicator parameter set of a preset performance indicator of the network device within a preset time period through a probe deployed on the network device. The types of the preset performance indicators include: transmit power, received power or received power signal-to-noise ratio.

[0049] Since the transmission power determines the strength of the signal sent by the network device, if the transmission power is too low, it may cause signal attenuation, affect the data transmission rate and quality, and further affect the user's network experience; at the same time, abnormal changes in transmission power are often early signs of equipment aging, hardware damage or software problems. Therefore, when identifying abnormal network devices, the embodiments of the present application can mainly identify potential faulty devices in advance by continuously monitoring and analyzing the performance indicator of transmission power, provide early warning for network maintenance, and help take timely measures to prevent faults and reduce the risk of network interruption.

[0050] After collecting the performance indicator parameter sets of each network device, it is necessary to determine whether the performance indicator parameter distribution is a normal distribution (also called a Gaussian distribution). This is because the premise of the hypothesis test method is that the data distribution is a normal distribution. If the data deviates from the normal distribution, the effectiveness of these test methods will be reduced, and the conclusions drawn may be unreliable. Generally, there are several methods to determine whether the data distribution is a normal distribution: graphical test (i.e., drawing a histogram or QQ graph of the data to observe whether it presents a typical bell-shaped curve of a normal distribution), statistical test (i.e., using the statistical method of normality test to test whether the data meets the assumption of a normal distribution), empirical rules (i.e., observing whether the skewness and kurtosis of the data are close to the skewness 0 and kurtosis 3 of the normal distribution), etc.

[0051] In addition, if the data distribution is not normal, it can be made close to normal distribution through data transformation (such as logarithmic transformation, square root transformation, etc.), or non-parametric statistical methods can be used for analysis, such as Mann-Whitney U test, Kruskal-Wallis test, etc.

[0052] As an optional implementation, in the technical solution provided in the above step S104, the method may include:

[0053] Step S1041, determining a first mean square error of the first network device on a preset performance indicator according to a performance indicator parameter set of the first network device, and determining a second mean square error of each second network device on a preset performance indicator according to a performance indicator parameter set of each second network device;

[0054] Step S1042, using a hypothesis testing method to compare the first mean square error of the first network device on the preset performance indicator with the second mean square error of each second network device on the preset performance indicator, and determine at least one second target network device of the same model and / or version as the first network device.

[0055] Specifically, the above hypothesis verification methods include but are not limited to: F test (used to compare whether the variances of two groups of data are equal), T test (used to compare whether the means of two groups of data are significantly different, applicable to small sample data with normal distribution), chi-square test (used to test whether there is a significant association between two or more categorical variables, applicable to count data), Mann-Whitney U test (used to compare whether the medians of two independent samples are the same, applicable to cases where the data are not normally distributed) or Kruskal-Wallis test (used to compare whether the medians of three or more independent samples are the same, which can be used when the data are not normally distributed or the variances are uneven), etc.

[0056] Taking F check as an example, the technical solution provided in the above step S1042 can be implemented according to the following steps:

[0057] First, for each second network device, a quotient of a first mean square error of the first network device on a preset performance indicator and a second mean square error of the second network device on a preset performance indicator is calculated to obtain a corresponding verification statistic;

[0058] When the verification statistic is not greater than the preset verification threshold, it is determined that the second network device is a second target network device of the same model and / or the same version as the first network device.

[0059] When the verification statistic is greater than the preset verification threshold, it is determined that the second network device is a second target network device of the same model and / or the same version as the first network device.

[0060] That is, the first mean square error of the first network device on the preset performance indicator is recorded as The second mean square error of the second network device on the preset performance indicator is recorded as Then its statistics can be expressed as:

[0061]

[0062] In addition, the general significance level (i.e., the probability of making an error when estimating the population parameter falling within a certain interval) is 0.05, and the degree of freedom is the sampling point of the acquisition network device within the preset time period minus one. Therefore, by consulting the corresponding F test adjacent value table, the corresponding verification critical value can be obtained. If the F statistic is greater than the F critical value, it means that the verification result has a significant difference; conversely, if the F statistic is not greater than the F critical value, it means that the verification result has no significant difference.

[0063] In addition to the several implementation schemes listed above, based on the basic concept of the embodiments of the present application in identifying other devices of the same model and / or the same version as the newly-connected device, those skilled in the art may also implement other technical schemes to identify a second target network device of the same model and / or the same version as the first network device. For example, those skilled in the art may make changes to the above implementation schemes, which should also be within the scope of protection of the present invention.

[0064] As an optional implementation, in the technical solution provided in the above step S106, the method may include:

[0065] Step S1061, determining a first mean and a first mean square deviation of the first network device on a preset performance indicator based on a performance indicator parameter set of the first network device, and determining a specification boundary value based on the first mean and the first mean square deviation, wherein the specification boundary value includes: a specification upper limit value and a specification lower limit value.

[0066] Among them, the first mean value of the first network device on the preset performance indicator is denoted as μ, and the first mean square deviation is denoted as σ. Then the specification boundary values ​​of other network devices of the same model and / or version as the first network device can be denoted as: the upper specification limit (Upper Spec Limit, USL) is μ+4σ, and the lower specification limit (Lower Spec Limit, USL) is μ-4σ.

[0067] Step S1062: Determine a second mean and a second mean square error of the second target network device on the corresponding performance indicator according to the performance indicator parameter set of the second target network device.

[0068] The second mean value of the corresponding performance index of the i-th second target network device can be recorded as μ f,i , the second mean square error can be recorded as σ f,i .

[0069] Step S1063, determining the process capability index of the second target network device according to the specification boundary value, the second mean and the second mean square deviation of the second target network device and according to the following formula:

[0070]

[0071] Where μ represents the first mean, σ represents the first mean square deviation, μ+4σ represents the upper specification limit, μ-4σ represents the lower specification limit, and μ f,i represents the second mean of the i-th second target network device, σ f,i represents the second mean square error of the i-th second target network device.

[0072] It should be noted that the above method of setting the specification boundary value takes into account that in the normal distribution, Theoretically, it can cover data points closer to 100% in the normal distribution to strictly screen out network devices with abnormal performance, ensure network stability and service quality, and further reduce the impact of outliers. However, if the network environment has very high performance requirements for the equipment, or the cost allows for a higher maintenance frequency, you can consider using a larger standard deviation multiple (such as ) to further reduce potential abnormal devices. Therefore, the setting method of determining the specification boundary value based on the first mean and the first mean square error can be dynamically adjusted according to the actual operation of the device, changes in the network environment or the operator's strategy.

[0073] As an optional implementation, in the technical solution provided in the above step S108, the method may include:

[0074] When the process capability index of the second target network device is less than a preset threshold value, determining that the second target network device has a quality abnormality;

[0075] When the process capability index of the second target network device is not less than a preset threshold value, it is determined that the second target network device has no quality abnormality.

[0076] Specifically, the threshold value can usually be set to 1.33 or the like. Generally, the higher the threshold value, the smaller the deviation between the mean and mean square error of the transmission power of other devices and the reference value is required, and the higher the number of unqualified products will be. The second target network device with a process capability index lower than the threshold value is regarded as a device with unstable or abnormal performance. This is because a low process capability index indicates that the performance parameters of the device deviate greatly from the specification boundary value, that is, the performance indicators of the device are not stable enough or do not meet the expected performance standards.

[0077] Furthermore, after determining that the second target network device with abnormal quality exists, the second target network device with abnormal quality may be managed according to the following method, including:

[0078] Step 1: Determine the gap between the process capability index of the second target network device with quality anomalies and the threshold value. The gap reflects the degree of deviation between the stability of the device's transmission power and the network standard, which is an important basis for judging the quality status of the device.

[0079] Step 2: Determine the quality abnormality level of the second target network device with quality abnormality according to the size of the gap, that is, classify the second target network device with quality abnormality into different quality abnormality levels, and the level classification can be based on a fixed interval.

[0080] For example, a device with a difference of less than 0.3 may be marked as slightly abnormal, a device with a difference between 0.3 and 0.6 may be marked as moderately abnormal, and a device with a difference greater than 0.6 may be marked as severely abnormal. It should be noted that the classification of abnormality levels may be determined based on network performance requirements and equipment maintenance costs.

[0081] Step 3: Determine the management priority of the second target network device with quality abnormality according to the quality abnormality level, and perform maintenance on the second target network device with quality abnormality in sequence according to the management priority.

[0082] Among them, the second target network device with a higher quality anomaly level has a higher corresponding management priority; conversely, the second target network device with a lower quality anomaly level has a lower corresponding management priority. Therefore, by sequentially maintaining the second target network devices with quality anomalies according to the management priority, it can be ensured that the devices with higher priority receive maintenance services before the devices with lower priority, thereby ensuring that the network stability and user experience are not significantly affected. The maintenance content includes but is not limited to: adjustment of device parameters, software upgrades, hardware replacement or on-site inspections, etc.

[0083] Through the above abnormal network device identification method, not only can the devices whose performance indicators are lower than the poor quality threshold be identified, but also the devices whose performance indicators begin to decline but have not yet reached the poor quality standard can be discovered in advance, thereby effectively preventing network problems and improving the initiative and accuracy of network maintenance. At the same time, targeted and refined management is carried out according to the abnormal level of different abnormal devices to ensure that the key problems of different abnormal devices are solved in a timely manner, while optimizing resource allocation, avoiding unnecessary intervention in devices with normal performance, and achieving efficient and targeted network maintenance.

[0084] Example 2

[0085] According to an embodiment of the present application, there is also provided an abnormal network device identification device for implementing the abnormal network device identification method in embodiment 1, such as Figure 2 As shown, the abnormal network device identification device at least includes: an acquisition module 22, a first determination module 24, a second determination module 26 and an abnormality determination module 28, wherein:

[0086] An acquisition module 22 is used to acquire a performance indicator parameter set of a newly connected first network device and a plurality of connected second network devices in a passive optical network within a preset time period, wherein the performance indicator parameter set is a parameter set of a preset performance indicator of a network device within a preset time period;

[0087] A first determination module 24, configured to determine at least one second target network device of the same model and / or same version as the first network device based on the performance indicator parameter set of the first network device and each second network device;

[0088] A second determination module 26, configured to determine a specification boundary value according to the performance indicator parameter set of the first network device, and determine a process capability index of each second target network device according to the specification boundary value and the performance indicator parameter set of each second target network device;

[0089] The abnormality determination module 28 is used to determine, for each second target network device, whether the second target network device has a quality abnormality according to the process capability index of the second target network device.

[0090] In addition, the above-mentioned device may also include a management module, which is used to determine the gap between the process capability index of the second target network device with quality abnormality and the threshold value after determining that the second target network device has quality abnormality; determine the quality abnormality level of the second target network device with quality abnormality based on the gap; determine the management priority of the second target network device with quality abnormality according to the quality abnormality level, and maintain the second target network device with quality abnormality in sequence according to the management priority.

[0091] It should be noted that each module in the abnormal network device identification device in the embodiment of the present application corresponds one by one to each implementation step of the abnormal network device identification method in Example 1. Since a detailed description has been given in Example 1, some details not reflected in this embodiment can be referred to Example 1 and will not be repeated here.

[0092] Example 3

[0093] According to an embodiment of the present application, a computer program product is also provided, which includes a computer program, wherein when the computer program is executed by a processor, the abnormal network device identification method in Example 1 is implemented.

[0094] According to an embodiment of the present application, a non-volatile storage medium is also provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the abnormal network device identification method in Example 1 by running the computer program.

[0095] According to an embodiment of the present application, a processor is also provided, which is used to run a computer program, wherein the abnormal network device identification method in Example 1 is executed when the computer program is running.

[0096] According to an embodiment of the present application, an electronic device is also provided, which includes: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the abnormal network device identification method in Example 1 through the computer program.

[0097] Specifically, when the computer program is running, the following steps are executed: obtaining a performance indicator parameter set of a newly connected first network device and multiple second network devices that have been connected to the passive optical network within a preset time period, wherein the performance indicator parameter set is a parameter set of a preset performance indicator of the network device within a preset time period; determining at least one second target network device of the same model and / or version as the first network device based on the performance indicator parameter set of the first network device and each second network device; determining a specification boundary value based on the performance indicator parameter set of the first network device, and determining a process capability index of each second target network device based on the specification boundary value and the performance indicator parameter set of each second target network device; for each second target network device, determining whether the second target network device has a quality abnormality based on the process capability index of the second target network device.

[0098] As an optional implementation, the electronic device may be in the form of a mobile terminal, a computer terminal or a similar computing device. Figure 3 The hardware structure block diagram of an electronic device for implementing the abnormal network device identification method is shown. Figure 3 As shown, the electronic device 30 may include one or more (302a, 302b, ..., 302n are used to illustrate) processors 302 (the processor 302 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 304 for storing data, and a transmission device 306 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 3 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 3 More or fewer components as shown, or with Figure 3 Different configurations are shown.

[0099] It should be noted that the one or more processors 302 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the electronic device 30. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0100] The memory 304 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the abnormal network device identification method in the embodiment of the present application. The processor 302 executes various functional applications and data processing by running the software programs and modules stored in the memory 304, that is, realizing the vulnerability detection method of the above-mentioned application. The memory 304 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 304 may further include a memory remotely arranged relative to the processor 302, and these remote memories may be connected to the electronic device 30 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0101] The transmission device 306 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the electronic device 30. In one example, the transmission device 306 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 306 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0102] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the electronic device 30 .

[0103] The serial numbers of the above embodiments are only for description and do not represent the advantages or disadvantages of the embodiments.

[0104] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0105] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0106] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0107] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0108] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0109] The above are only preferred implementations of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for identifying abnormal network devices, characterized in that: include: Acquire a performance indicator parameter set of each of a first network device newly connected to the passive optical network and a plurality of second network devices already connected to the network within a preset time period, wherein the performance indicator parameter set is a parameter set of a preset performance indicator of the network device within the preset time period; Determine at least one second target network device of the same model and / or same version as the first network device according to the performance indicator parameter set of the first network device and each of the second network devices; Determine a specification boundary value according to a performance indicator parameter set of the first network device, and determine a process capability index of each of the second target network devices according to the specification boundary value and a performance indicator parameter set of each of the second target network devices; For each of the second target network devices, it is determined whether the second target network device has a quality abnormality according to the process capability index of the second target network device.

2. The method according to claim 1, characterized in that Acquiring a performance indicator parameter set of a newly connected first network device and a plurality of connected second network devices in a passive optical network within a preset time period, including: A set of performance indicator parameters of preset performance indicators within a preset time period collected by monitoring probes deployed on the first network device and each second network device in the passive optical network, wherein the types of the preset performance indicators include: transmission power, received power or received power signal-to-noise ratio.

3. The method according to claim 1, characterized in that Determining at least one second target network device of the same model and / or same version as the first network device according to the performance indicator parameter set of the first network device and each of the second network devices includes: Determine a first mean square error of the performance of the first network device on a preset performance indicator according to the performance indicator parameter set of the first network device, and determine a second mean square error of the performance of each of the second network devices on the preset performance indicator according to the performance indicator parameter set of each of the second network devices; A hypothesis testing method is used to compare the first mean square error of the first network device on the preset performance indicator with the second mean square error of each of the second network devices on the preset performance indicator to determine at least one of the second target network devices of the same model and / or version as the first network device.

4. The method according to claim 3, characterized in that Using a hypothesis testing method to compare a first mean square error of the first network device on a preset performance indicator with a second mean square error of each of the second network devices on a preset performance indicator, and determining at least one second target network device of the same model and / or version as the first network device, includes: For each of the second network devices, calculating a quotient of a first mean square error of the first network device on a preset performance indicator and a second mean square error of the second network device on a preset performance indicator to obtain a corresponding verification statistic; When the verification statistic is not greater than a preset verification threshold, it is determined that the second network device is a second target network device of the same model and / or the same version as the first network device.

5. The method according to claim 1, characterized in that Determining a specification boundary value according to a performance indicator parameter set of the first network device, and determining a process capability index of each of the second target network devices according to the specification boundary value and a performance indicator parameter set of each of the second target network devices, including: Determine a first mean and a first mean square deviation of the performance of the first network device on a preset performance indicator according to the performance indicator parameter set of the first network device, and determine a specification boundary value according to the first mean and the first mean square deviation, wherein the specification boundary value includes: an upper specification limit value and a lower specification limit value; Determine a second mean and a second mean square error of the second target network device on the corresponding performance indicator according to the performance indicator parameter set of the second target network device; The process capability index of the second target network device is determined according to the specification boundary value, the second mean and the second mean square deviation of the second target network device and according to the following formula: Wherein μ represents the first mean, σ represents the first mean square deviation, μ+4σ represents the upper specification limit, μ-4σ represents the lower limit of the specification, μ f,i represents the second mean of the i-th second target network device, σ f,i represents the second mean square error of the i-th second target network device.

6. The method according to claim 1, characterized in that Determining whether the second target network device has quality abnormality according to the process capability index of the second target network device includes: When the process capability index of the second target network device is less than a preset threshold value, determining that the second target network device has a quality abnormality; When the process capability index of the second target network device is not less than a preset threshold value, it is determined that the second target network device has no quality abnormality.

7. The method according to claim 6, characterized in that After determining that the second target network device has a quality abnormality, the method further includes: Determine the difference between the process capability index of the second target network device with quality abnormality and the threshold value; Determine the quality abnormality level of the second target network device having quality abnormality according to the size of the gap; The management priority of the second target network device with quality abnormality is determined according to the quality abnormality level, and the second target network device with quality abnormality is maintained in sequence according to the management priority.

8. An abnormal network device identification device, characterized in that: include: An acquisition module, used to acquire a performance indicator parameter set of a newly connected first network device and a plurality of connected second network devices in a passive optical network within a preset time period, wherein the performance indicator parameter set is a parameter set of a preset performance indicator of a network device within the preset time period; A first determination module, configured to determine at least one second target network device of the same model and / or same version as the first network device based on the performance indicator parameter set of the first network device and each of the second network devices; A second determination module, configured to determine a specification boundary value according to a performance indicator parameter set of the first network device, and determine a process capability index of each of the second target network devices according to the specification boundary value and a performance indicator parameter set of each of the second target network devices; The abnormality identification module is used to determine, for each second target network device, whether the second target network device has a quality abnormality according to the process capability index of the second target network device.

9. A computer program product, characterized in that include: A computer program, wherein when the computer program is executed by a processor, the abnormal network device identification method according to any one of claims 1 to 7 is implemented.

10. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the abnormal network device identification method according to any one of claims 1 to 7 through the computer program.

Images