Network element equipment identification method, electronic equipment and readable storage medium

Abstract

The invention discloses a network element device identification method, an electronic device and a readable storage medium. The method comprises the steps of obtaining target data of a target index of each network element device at a current time point and historical data of a target index of each network element device at a historical time point; determining an actual extreme value ratio of the target index according to the target data, and determining a predicted extreme value ratio of the target index according to the historical data; and determining the network element equipment with the target data meeting a preset condition as target network element equipment under the condition that the target index is determined to be unbalanced based on the actual extreme value ratio and the predicted extreme value ratio.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the technical field of communication, in particular to a network element device identification method, an electronic device and a readable storage medium. BACKGROUND

[0002] With the popularization and application of 5G (5th Generation) technology, people's demand for high-speed, low-latency and high-reliability communication networks is increasing. In actual operation, various problems may occur in the communication network, but the network element device may not show abnormality until the related evaluation index data of the network element device has deteriorated for a period of time. At this time, if the network element device is positioned and identified and processed, the problem of failing to identify the abnormal network element device in time and affecting user services may occur. SUMMARY

[0003] Embodiments of the present application provide a network element device identification method, an electronic device and a readable storage medium, which can solve the problem of failing to identify the abnormal network element device in time and affecting user services.

[0004] To solve the above technical problems, the present application is implemented as follows:

[0005] In a first aspect, the embodiments of the present application provide a network element device identification method, which comprises: obtaining target data of a target index of each network element device at a current time point and historical data at a historical time point; determining an actual extreme value ratio of the target index according to the target data, and determining a predicted extreme value ratio of the target index according to the historical data; and determining a target network element device as the network element device whose target data meets a preset condition in a case where the target index is unbalanced based on the actual extreme value ratio and the predicted extreme value ratio.

[0006] In a second aspect, the embodiments of the present application provide an electronic device, which comprises a processor and a memory, wherein the memory stores programs or instructions executable on the processor, and the programs or instructions are executed by the processor to implement the steps of the network element device identification method according to the first aspect.

[0007] In a third aspect, the embodiments of the present application provide a readable storage medium, which stores programs or instructions, and the programs or instructions are executed by a processor to implement the steps of the network element device identification method according to the first aspect.

[0008] In a fourth aspect, the embodiments of the present application provide a chip, which comprises a processor and a communication interface, wherein the communication interface is coupled to the processor, the processor is configured to run programs or instructions, and implement the steps of the network element device identification method according to the first aspect.

[0009] Fifthly, embodiments of this application provide a computer program product, the computer program product including a computer program stored on a non-transitory computer-readable storage medium, the computer program including a program or instructions, which, when executed, implement the steps of the network element device identification method as described in the first aspect.

[0010] In this embodiment, target data and historical data of each network element device at the current time point are obtained. The actual extreme value ratio of the target indicator is determined based on the target data, and the predicted extreme value ratio of the target indicator is determined based on the historical data. The actual and predicted extreme value ratios of the target indicator are used to determine whether the target indicator is unbalanced. If the target indicator is determined to be unbalanced based on the actual and predicted extreme value ratios, network element devices whose target data meets preset conditions are identified as target network element devices. This achieves timely determination of an unbalanced target indicator based on the actual and predicted extreme value ratios of the target indicators of each network element device. Furthermore, based on the target data of the unbalanced target indicator and preset conditions, target network element devices that meet preset conditions can be identified in advance, such as identifying network element devices that are generating anomalies. This allows for proactive handling of abnormal network element devices, preventing impact on user services. Attached Figure Description

[0011] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0012] Figure 1 A flowchart illustrating an exemplary embodiment of this application for identifying a network element device is shown.

[0013] Figure 2 An analysis diagram of an imbalance of target indicators provided by an exemplary embodiment of this application is shown;

[0014] Figure 3 A flowchart illustrating another method for identifying network element devices provided in an exemplary embodiment of this application is shown.

[0015] Figure 4 A flowchart illustrating another method for identifying network element devices provided in an exemplary embodiment of this application is shown.

[0016] Figure 5 This illustration shows a schematic diagram of the structure of an electronic device provided in an exemplary embodiment of this application. Detailed Implementation

[0017] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0018] Figure 1 This illustration shows a flowchart of a method for identifying network element devices provided in an exemplary embodiment of this application. See also... Figure 1 The method includes the following steps.

[0019] Step 102: Obtain the target data of each network element device at the current time point and the historical data at historical time points.

[0020] The target metrics are indicators used to evaluate the operational quality of network element devices. These target metrics may include session activation success rate, session establishment success rate, and session reporting success rate. Table 1 shows the metrics supported by different network element device types provided in the embodiments of this application. The metrics in Table 1 are merely exemplary and are not limited to those in Table 1.

[0021]

[0022]

[0023]

[0024] Step 104: Determine the actual extreme value ratio of the target indicator based on the target data, and determine the predicted extreme value ratio of the target indicator based on the historical data.

[0025] The target data refers to the data of each network element device for the current point in time and the target indicator; the historical data refers to the data of each network element device for a specific historical point in time and the target indicator. The actual extreme value ratio of the target indicator can be determined based on the target data of each network element device at the current point in time. The predicted extreme value ratio of the target indicator can be determined based on the historical data of each network element device at multiple historical points in time. In essence, the actual extreme value ratio and the predicted extreme value ratio of the target indicator are compared between the data of each network element device on the same dimension, and the relationship between the actual extreme value ratio and the predicted extreme value ratio determines whether the target indicator is unbalanced.

[0026] Step 106: If the target index is determined to be unbalanced based on the actual extreme value ratio and the predicted extreme value ratio, the network element device whose target data meets the preset conditions is identified as the target network element device.

[0027] Specifically, the imbalance of the target indicator is judged based on the ratio of the actual extreme value to the predicted extreme value, and each network element is initially screened. By analyzing the imbalance of the target indicator, it is determined whether each network element has potential hidden dangers. Then, after confirming the imbalance of the target indicator, further identification of each network element is performed, thereby improving the efficiency of identifying abnormal network elements.

[0028] In this embodiment, target data of each network element device at the current time point and historical data at historical time points are obtained. The actual extreme value ratio of the target indicator is determined based on the target data, and the predicted extreme value ratio of the target indicator is determined based on the historical data. This allows for the determination of whether the target indicator is imbalanced based on the actual and predicted extreme value ratios, thus performing an initial screening of network element devices with potential risks. If the target indicator is determined to be imbalanced based on the actual and predicted extreme value ratios, the network element devices are further identified based on the target data of the imbalanced target indicator. Network element devices whose target data meets preset conditions are identified as target network element devices. This achieves timely determination of an imbalanced target indicator based on the actual and predicted extreme value ratios of the target indicators of each network element device. Furthermore, based on the target data of the imbalanced target indicator and preset conditions, target network element devices that meet preset conditions can be identified in advance, such as identifying network element devices that are generating anomalies. This allows for proactive handling of abnormal network element devices to avoid impacting user services.

[0029] In one implementation, step 104 above, which determines the actual extreme value ratio of the target indicator based on the target data and the predicted extreme value ratio of the target indicator based on the historical data, may include the following steps.

[0030] Step 1041: Determine the actual extreme value ratio of the target indicator based on the maximum and minimum values ​​of the target data.

[0031] The actual extreme value ratio of the target indicator can be determined by the following formula: Among them, X i / X j This represents the target data for the target metric of the i / j-th network element at the current time point.

[0032] Step 1042: Determine the predicted extreme value ratio of the target indicator based on the median fluctuation value of the target data and the historical data, and the average extreme value ratio of the historical data.

[0033] The median fluctuation value is used to characterize the degree of fluctuation between the target data and historical data. The mean extreme value ratio is determined by averaging the extreme value ratios of the target indicator determined from the historical data of the target indicator for each network element at multiple historical time points. The predicted extreme value ratio of the target indicator can be determined by the following formula: P 预 =P 均 *(1+W), where W is the median fluctuation between the target data and historical data, and P 均 The extreme values ​​are the ratio of the mean to the extreme values.

[0034] In this embodiment of the application, the actual extreme value ratio of the target indicator is determined by the target data of the target indicators of each network element device at the current time point, while the predicted extreme value ratio of the target indicator involves historical data from multiple historical time points. By using the historical data of the target indicators of each network element device at multiple historical time points, the average extreme value ratio is determined, so that the predicted extreme value ratio can uniformly represent the situation of the target indicator at historical time points, avoiding inaccurate prediction of the extreme value ratio due to the use of historical data from a single historical time point.

[0035] In one implementation, step 1042 above, which determines the predicted extreme value ratio of the indicator based on the median fluctuation value of the target data and the historical data, and the average extreme value ratio of the historical data, may include the following steps.

[0036] Step 1042a: Determine the median fluctuation value based on the actual median of the target data and the predicted median of the historical data.

[0037] The predicted median is determined using historical data of target metrics for each network element at multiple historical time points. The median fluctuation value can be determined using the following formula: That is, the median fluctuation value can be used to predict the median X. 预 Compared with the actual median X 实 The absolute value of the difference |X 预 -X 实 |Compared to the predicted median X 预 The ratio between them.

[0038] Step 1042b: Determine the average extreme value ratio of the target indicator within the preset time period based on the historical data of the historical time points within the preset time period.

[0039] The preset time period refers to the time period preceding the current time point. The extreme value ratios corresponding to historical data at multiple historical time points are determined, and then the average of these extreme value ratios is calculated to obtain the average extreme value ratio. For example, three historical time points T1, T2, and T3 are selected within the preset time period. The extreme value ratio P1 is obtained based on the historical data at T1, the extreme value ratio P2 is obtained based on the historical data at T2, and the extreme value ratio P3 is obtained based on the historical data at T3. The average of P1, P2, and P3 is then calculated to obtain the average extreme value ratio for the preset time period.

[0040] Step 1042c: Determine the predicted extreme value ratio of the target indicator based on the median fluctuation value and the average extreme value ratio.

[0041] In this embodiment, the predicted median is determined by using historical data of the target indicators of various network element devices at multiple historical time points. Then, the median fluctuation value is determined based on the actual median and the predicted median. This ensures that the predicted extreme value ratio, determined based on the median fluctuation value and the mean extreme value ratio, can better represent the historical data of the target indicator. Finally, it is compared with the actual extreme value ratio to determine whether the target indicator is unbalanced.

[0042] In one implementation, step 1042a above, which determines the median fluctuation value based on the actual median of the target data and the predicted median of the historical data, may include the following steps.

[0043] Step a1: Determine the actual median at the current time point based on the target data.

[0044] Step a2: Based on the median corresponding to the historical data of each network element device at multiple historical time points, predict the median corresponding to the current time point based on the prediction model, and determine the predicted median at the current time point.

[0045] The prediction model can be a least squares prediction model. For example, select n historical time points T1, T2, ..., Tn. Obtain the median X1 based on the historical data at T1, the median X2 based on the historical data at T2, ..., the median Xn based on the historical data at Tn. Using the historical time points T1, T2, ..., Tn as independent variables and the medians X1, X2, ..., Xn as dependent variables, fit the function between the median and the time points using the least squares method. Then, predict the median corresponding to the current time point based on this function. This median is the predicted median.

[0046] Step a3: Determine the median fluctuation value at the current time point based on the actual median and the predicted median.

[0047] In this embodiment, the actual median is directly determined by the target data of the target indicators of each network element device at the current time point. The predicted median is determined by first predicting the function between the time point and the median based on the historical data of the target indicators of each network element device at multiple historical time points, and then predicting the median corresponding to the current time point based on the function, thereby determining the predicted median. Based on the actual median and the predicted median at the current time point, the median fluctuation value at the current time point is determined to determine the predicted extreme value ratio.

[0048] In one implementation, step 106 above, when determining that the target indicator is unbalanced based on the actual extreme value ratio and the predicted extreme value ratio, may include the following steps:

[0049] Step 1061: If the actual extreme value ratio is greater than the predicted extreme value ratio, determine that the target index is unbalanced.

[0050] in, Figure 2 This application provides an embodiment of an analysis diagram of target indicator imbalance. See also: Figure 2 The predicted extreme value ratio is used as a threshold. By comparing this predicted extreme value ratio with the current actual extreme value ratio, it is possible to determine whether the target indicator is unbalanced.

[0051] Step 1062: Cluster the target data of the target indicators of each network element device to obtain multiple clusters;

[0052] This can be achieved by clustering target data based on the characteristics of target data for each network element and the current identification requirements. For example, if the identification requirement is to identify network elements that are generating anomalies, then based on the clustering parameters, the target data can be clustered into two categories: one corresponding to network elements generating anomalies and the other to network elements that are functioning normally. Then, based on preset conditions, the network elements generating anomalies can be identified. Another example is an identification requirement for the target indicator of session activation success rate: identifying network elements with low and medium session activation success rates. This involves processing network elements with low session activation success rates first, and then processing those with medium session activation success rates. Similarly, based on the clustering parameters, the target data can be clustered into three categories: one corresponding to network elements with low session activation success rates, another to network elements with medium session activation success rates, and a third to network elements with high session activation success rates. Then, based on preset conditions, the network elements with low and medium session activation success rates can be identified.

[0053] The target data used for clustering is the target data of each network element device for the current time point and the target indicator of the imbalance. This ensures that the historical data used for clustering is data representing different operating conditions of each network element device under the same time dimension and the same indicator dimension. This allows the network element devices corresponding to the target data to be clustered based on the target indicator of the imbalance, so as to obtain multiple clusters with different characteristics.

[0054] Step 1063: The network element devices corresponding to the clusters that meet the preset conditions among the multiple clusters are identified as target network element devices.

[0055] The preset condition is used to determine if a cluster is an abnormal cluster. This preset condition can be set according to the specific needs of identifying network element devices. For example, if it is necessary to identify network element devices that have generated abnormalities, the preset condition can be that the centroid data of the cluster (e.g., the target indicator is the success rate) is less than a preset threshold. In other words, if the centroid data of the cluster is less than the preset threshold, the success rate of the network element device corresponding to the cluster is low, and the network element device corresponding to the cluster has generated abnormalities, thus realizing the identification of network element devices that have generated abnormalities.

[0056] In one implementation, step 1062 above may include: clustering the target data of each network element device based on a binary clustering algorithm to obtain two clusters for the target indicator.

[0057] Different clustering algorithms or parameters result in different clustering outcomes. The binary K-means (K-Means) clustering algorithm works as follows: It selects two data points from the target data of each network element as the centroids of each cluster. Based on the distance between each target data point and its centroid, it assigns each target data point to the cluster containing the nearest centroid. Then, it recalculates the centroid of each cluster, iterating until the centroid no longer shows significant movement or the maximum set number of iterations is reached.

[0058] In this embodiment, when the actual extreme value ratio of a target indicator is greater than the predicted extreme value ratio, indicating an imbalance in the target indicator, a clustering algorithm is used to cluster the target data of each network element into multiple clusters, such as two clusters. It is understood that the two clusters have different characteristics, while the data within each cluster has the same or similar characteristics. This embodiment can be used to identify network elements that are malfunctioning. A binary clustering algorithm is used to cluster the data, resulting in one cluster corresponding to the malfunctioning network element and the other cluster corresponding to the normal network element. Then, based on preset conditions, the two clusters are judged, thereby identifying the malfunctioning network element.

[0059] In one implementation, step 1063 above, which determines the network element device corresponding to the cluster that meets the preset conditions among the multiple clusters, may include the following steps.

[0060] Step 1063a: Determine the preset conditions based on the type of the target indicator.

[0061] The preset conditions include: the centroid data in the cluster is greater than a preset threshold; or the centroid data in the cluster is less than the preset threshold.

[0062] For example, if the target indicator is success rate, and the network element device that generates an anomaly is identified, the preset condition is that the centroid data in the cluster is less than the preset threshold.

[0063] Step 1063b: The network element devices corresponding to the clusters that meet the preset conditions are identified as target network element devices.

[0064] In this embodiment, after clustering the target data of each network element device to obtain two clusters, preset conditions are determined based on the type of the target indicator. Then, the network element devices corresponding to the clusters that meet the preset conditions are identified as target network element devices. This enables the early identification of network element devices corresponding to clusters that meet the preset conditions based on historical data of the target indicator, such as network element devices exhibiting abnormalities. This allows for proactive handling of abnormal network element devices, preventing impact on user services.

[0065] In one implementation, the target network element device includes an abnormal network element device. After determining the network element devices corresponding to the clusters that meet the preset conditions among the multiple clusters as the target network element devices in step 108 above, the method further includes: reporting a network element device abnormality message; wherein, the network element device abnormality message is used to indicate that the abnormal network element device has generated an abnormality.

[0066] In this embodiment of the application, after identifying the target network element device corresponding to the cluster that meets the preset conditions, an abnormal network element device message is reported. The abnormal network element device message is used to indicate that the abnormal network element device has an anomaly, so that the operation and maintenance personnel or the intelligent network can know in advance that there is an abnormal network element device, thereby handling the abnormal network element device in a timely manner and avoiding affecting user services.

[0067] Figure 3 and Figure 4 This paper illustrates a flowchart of another method for identifying network element devices provided in an embodiment of this application. See also... Figure 3 and Figure 4 The method may include the following steps.

[0068] Step 301: Each network element reports the target indicator data. This indicator data includes both the current time point and historical time point data.

[0069] Step 302: The poor quality background analysis service module of the monitoring center analyzes the indicator data. The specific analysis steps are as follows.

[0070] Step 302a: Determine the actual extreme value ratio based on the index data at the current time point.

[0071] Specifically, it can be accessed through Determine the actual extreme value ratio, where X i / X j This represents the indicator data for the i / j-th network element at the current time point.

[0072] Step 302b: Determine the actual median based on the indicator data at the current time point, predict the predicted median at the current time point based on the indicator data at historical time points using the least squares method, and then determine the median fluctuation value at the current time point based on the actual median and the predicted median.

[0073] Specifically, it can be accessed through Determine the median fluctuation value, where X 预 To predict the median, X 实 This is the actual median.

[0074] Step 302c: Determine the predicted extreme value ratio based on the median fluctuation value and the average extreme value ratio. Specifically, determine the average extreme value ratio within the preset time period based on the extreme value ratios of multiple historical time points within the preset time period.

[0075] Specifically, it can be done via P 预 =P 均 *(1+W) determines the predicted extreme value ratio, where P 均 is the ratio of extreme values ​​to the mean, and W is the median fluctuation value.

[0076] Step 302d: If the actual extreme value ratio is greater than the predicted extreme value ratio, determine the target index imbalance.

[0077] Step 303: For the unbalanced target indicators, the target indicator data of each network element device at the current time point are clustered based on the binary K-Means clustering algorithm to obtain two clusters.

[0078] Step 304: Based on the type of indicator, select clusters whose centroid data are lower or higher than a preset threshold as abnormal clusters. The network element devices corresponding to these abnormal clusters are the abnormal network element devices.

[0079] For example, when the current indicator type is success rate, clusters with centroid data below a preset threshold are predicted and identified as abnormal clusters.

[0080] Step 305: After determining the abnormal network element device corresponding to the abnormal cluster, report the abnormal network element device message and notify the abnormal event management module of the monitoring center so that the abnormal event management module can trigger the operation and maintenance center to handle the abnormal network element device.

[0081] Step 306: The operation and maintenance center confirms that the identified abnormal network element device does indeed have a problem, and performs the corresponding one-click isolation on the abnormal network element device.

[0082] Through the embodiments of this application, abnormal network element devices that cause anomalies can be identified in a timely manner, and the abnormal network element devices can be isolated to avoid affecting user services.

[0083] This application also provides an electronic device. Figure 5 This application shows a schematic diagram of the structure of an electronic device provided in an exemplary embodiment. See also: Figure 5 This electronic device is used to perform the aforementioned network element identification method. Figure 5 This is a schematic diagram of the structure of an electronic device to implement the various embodiments of this application. The electronic device can vary significantly due to differences in configuration or performance, and may include a processor 501, a communications interface 502, a memory 503, and a communication bus 504. The processor 501, communications interface 502, and memory 503 communicate with each other via the communication bus 504. The processor 501 can call a computer program stored in the memory 503 and executable on the processor 501 to perform the various steps of the above-described network element device identification method embodiments, achieving the same technical effects. To avoid repetition, further details are omitted here.

[0084] The above electronic device structure does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or arrange them differently. For example, an input unit may include a Graphics Processing Unit (GPU) and a microphone, and a display unit may use a liquid crystal display (LCD), organic light-emitting diode (OLED), or other similar display panels. User input units include at least one of a touch panel and other input devices. A touch panel is also called a touchscreen. Other input devices may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, power buttons, etc.), trackballs, mice, and joysticks, which will not be elaborated further here.

[0085] Memory can be used to store software programs and various data. Memory can primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area can store the operating system, application programs or instructions required for at least one function (such as sound playback, image playback, etc.). Furthermore, memory can include volatile memory or non-volatile memory, or both. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (Synchlink DRAM, SLDRAM), and direct memory bus RAM (DRRAM).

[0086] The processor may include one or more processing units; optionally, the processor integrates an application processor and a modem processor, wherein the application processor mainly handles operations related to the operating system, user interface, and applications, while the modem processor mainly handles wireless communication signals, such as a baseband processor. It is understood that the aforementioned modem processor may also not be integrated into the processor.

[0087] This application also provides a readable storage medium storing a program or instructions. When the program or instructions are executed by a processor, they implement the various processes of the above-described network element device identification method embodiments and achieve the same technical effect. To avoid repetition, they will not be described again here.

[0088] The processor is the processor in the electronic device described in the above embodiments. The readable storage medium includes computer-readable storage media, such as computer read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk.

[0089] This application embodiment also provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled. The processor is used to run programs or instructions to implement the various processes of the above-described network element device identification method embodiment, and can achieve the same technical effect. To avoid repetition, it will not be described again here.

[0090] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0091] This application also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium. The computer program includes a program or instructions. When the program or instructions are executed, they implement the various processes of the above-described network element device identification method embodiments and can achieve the same technical effect. To avoid repetition, they will not be described again here.

[0092] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, it should be noted that the scope of the methods and apparatuses in the embodiments of this application is not limited to performing functions in the order shown or discussed, but may also include performing functions substantially simultaneously or in the reverse order, depending on the functions involved. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

[0093] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0094] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the claims.

[0095] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A method for identifying network element devices, characterized in that, include: Obtain the target data of each network element device at the current time point and the historical data at historical time points; The actual extreme value ratio of the target indicator is determined based on the target data, and the predicted extreme value ratio of the target indicator is determined based on the historical data. If the target indicator is determined to be unbalanced based on the actual extreme value ratio and the predicted extreme value ratio, the network element device whose target data meets the preset conditions is identified as the target network element device.

2. The method according to claim 1, characterized in that, The step of determining the actual extreme value ratio of the target indicator based on the target data, and determining the predicted extreme value ratio of the target indicator based on the historical data, includes: Based on the maximum and minimum values ​​of the target data, determine the actual extreme value ratio of the target indicator; The predicted extreme value ratio of the target indicator is determined based on the median fluctuation value of the target data and the historical data, as well as the average extreme value ratio of the historical data.

3. The method according to claim 2, characterized in that, The step of determining the predicted extreme value ratio of the indicator based on the median fluctuation value of the target data and the historical data, and the average extreme value ratio of the historical data, includes: The median fluctuation value is determined based on the actual median of the target data and the predicted median of the historical data; Based on historical data from multiple historical time points within a preset time period, the average extreme value ratio of the target indicator within that preset time period is determined; wherein, the preset time period is the time period prior to the current time point; The predicted extreme value ratio of the target indicator is determined based on the median fluctuation value and the average ratio of the extreme values.

4. The method according to claim 3, characterized in that, The step of determining the median fluctuation value based on the actual median of the target data and the predicted median of the historical data includes: Based on the target data, determine the actual median at the current time point; Based on the median corresponding to the historical data of each network element at multiple historical time points, the median corresponding to the current time point is predicted based on the prediction model, and the predicted median at the current time point is determined. The median fluctuation value at the current time point is determined based on the actual median and the predicted median.

5. The method according to claim 1, characterized in that, The step of determining the network element device whose target data meets preset conditions as the target network element device when the target indicator is determined to be unbalanced based on the actual extreme value ratio and the predicted extreme value ratio includes: If the actual extreme value ratio is greater than the predicted extreme value ratio, the target index is determined to be unbalanced. Cluster the target data of the target indicators of each network element device to obtain multiple clusters; The network element devices corresponding to the clusters that meet the preset conditions among the multiple clusters are identified as target network element devices.

6. The method according to claim 5, characterized in that, The target data of the target indicators of each network element device are clustered to obtain multiple clusters, including: Based on the target index, the target data of each network element device are clustered according to the binary clustering algorithm to obtain two clusters.

7. The method according to claim 5, characterized in that, The step of determining the network element devices corresponding to clusters that meet preset conditions among the multiple clusters as target network element devices includes: The preset conditions are determined based on the type of the target indicator; The network element devices corresponding to the clusters that meet the preset conditions are identified as the target network element devices; The preset conditions include: the centroid data in the cluster is greater than a preset threshold; or the centroid data in the cluster is less than the preset threshold.

8. The method according to claim 1, characterized in that, The target network element device includes abnormal network element devices; After determining the network element devices corresponding to the clusters that meet the preset conditions among the plurality of clusters as the target network element devices, the method further includes: Report network element device abnormality messages; wherein, the network element device abnormality messages are used to indicate that the abnormal network element device has generated an abnormality.

9. An electronic device, characterized in that, The electronic device includes a processor and a memory, the memory storing programs or instructions that can run on the processor, the programs or instructions being executed by the processor to implement the steps of the identification method for network element devices as described in any one of claims 1 to 8.

10. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions, which, when executed by a processor, implement the steps of the identification method for network element devices as described in any one of claims 1 to 8.

Images