Network element state monitoring method, device and system, electronic equipment and storage medium

Abstract

The invention discloses a network element state monitoring method, device and system, electronic equipment and a storage medium. The method comprises the following steps: in a target monitoring period, obtaining target index data corresponding to a core network element reported by a health monitoring client, the health monitoring client being used for determining a target strategy corresponding to the core network element, the target strategy is at least used for indicating the collection, reporting and alarm strategy of the index data of the health monitoring index corresponding to the core network element; determining an alarm threshold condition corresponding to each health monitoring index of the network element of the core network in the target monitoring period according to historical index data corresponding to the health monitoring index of the network element of the core network in the historical monitoring period; and giving an alarm when the target index data meets the alarm threshold condition. According to the method and the device, the technical problem of poor core network element state monitoring effect caused by the fact that a fixed alarm threshold value and a unified monitoring strategy are generally adopted in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of communication network management and operation and maintenance technology, and specifically, to a network element status monitoring method, device, system, electronic device and storage medium. Background Art

[0002] The current 5G (5th Generation Mobile Communication Technology) core network health monitoring system has many limitations in health monitoring and fault diagnosis. The monitoring schemes in related technologies usually adopt fixed alarm thresholds and unified monitoring strategies, which are difficult to dynamically adjust according to the actual conditions of different network elements. Network elements with different characteristics and operating conditions are evaluated by the same standards, which is prone to false alarms and missed alarms, and there are technical problems such as poor monitoring of core network element status.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present application provide a network element status monitoring method, device, system, electronic device and storage medium to at least solve the technical problem of poor core network network element status monitoring effect caused by the fact that related technologies generally adopt fixed alarm thresholds and unified monitoring strategies.

[0005] According to one aspect of an embodiment of the present application, a network element status monitoring method is provided, including: in a target monitoring period, obtaining target indicator data corresponding to a core network element reported by a health monitoring client, wherein the health monitoring client is used to determine a target policy corresponding to the core network element, the target policy is at least used to indicate the collection, reporting and alarm policy of indicator data of the health monitoring indicator corresponding to the core network element, and each core network element corresponds to a health monitoring client; determining the alarm threshold conditions corresponding to each health monitoring indicator of the core network element in the target monitoring period based on historical indicator data corresponding to the health monitoring indicator of the core network element in a historical monitoring period, wherein the historical monitoring period is a monitoring period before the target monitoring period; and issuing an alarm when the target indicator data meets the alarm threshold conditions.

[0006] Optionally, determining the alarm threshold conditions corresponding to various health monitoring indicators of the core network network elements within the target monitoring period based on the historical indicator data corresponding to the health monitoring indicators of the core network network elements in the historical monitoring periods includes: obtaining the historical indicator data of the health monitoring indicators of the core network network elements within multiple historical monitoring periods; determining the arithmetic characteristic parameters of multiple historical indicator data corresponding to the health monitoring indicators, wherein the arithmetic characteristic parameters include: mean, standard deviation, upper quartile, lower quartile; determining the basic threshold corresponding to the health monitoring indicator based on the mean and standard deviation corresponding to the multiple historical indicator data, and determining the quantile threshold corresponding to the health monitoring indicator based on the upper quartile and lower quartile corresponding to the multiple historical indicator data; determining the alarm threshold conditions corresponding to the health monitoring indicator based on the basic threshold and quantile threshold corresponding to the health monitoring indicator.

[0007] Optionally, the basic threshold includes: a basic threshold upper limit and a basic threshold lower limit; determining the basic threshold corresponding to the health monitoring indicator based on the mean and standard deviation corresponding to multiple historical indicator data includes: determining the initial basic threshold based on the mean and standard deviation; using a sliding window, according to a preset sliding step, performing a sliding average operation on the historical indicator data sequence, wherein the historical indicator data sequence is obtained by sorting the historical indicator data according to the chronological order of the historical monitoring period corresponding to each historical indicator data, and the sliding average operation is used to calculate the average value of the historical indicator data within the range selected by the sliding window to obtain the sliding average value, and a sliding average operation is performed each time the sliding window is moved; based on the sliding average value, determining the incremental trend parameter corresponding to the historical indicator data of the health monitoring indicator, wherein the incremental trend parameter is used to characterize the changing trend of the historical indicator data; when the incremental trend parameter exceeds the preset incremental trend threshold, using an adjustment factor to adjust the initial basic threshold to obtain a final basic threshold.

[0008] Optionally, the quantile threshold includes: an upper quantile threshold and a lower quantile threshold; the alarm threshold condition includes: an upper target threshold and a lower target threshold corresponding to the health monitoring indicator; based on the basic threshold and quantile threshold corresponding to the health monitoring indicator, determining the alarm threshold condition corresponding to the health monitoring indicator includes: comparing the size relationship between the upper basic threshold and the upper quantile threshold, and determining the larger value between the upper basic threshold and the upper quantile threshold as the upper target threshold corresponding to the health monitoring indicator; comparing the size relationship between the lower basic threshold and the lower quantile threshold, and determining the smaller value between the lower basic threshold and the lower quantile threshold as the lower target threshold corresponding to the health monitoring indicator.

[0009] Optionally, different core network elements correspond to different target strategies under different operating conditions, wherein the target strategy is determined by the health monitoring client based on the basic information and operating conditions of the core network elements, the operating conditions include at least one of the following: the load status of the core network elements, the operating stage of the core network elements, the operating stage includes at least one of the following: the upgrade stage, and the target strategy includes at least one of the following: various health monitoring indicators that the core network elements need to collect, and the period length of the target monitoring period corresponding to the core network elements.

[0010] Optionally, the method also includes: when an abnormality is detected in a core network element, using a target service to obtain log and stack files corresponding to the core network element from the file system, wherein the target service is used to collect fault stack information and logs when the core network element exits abnormally; based on the log and stack files, determining diagnostic information corresponding to the core network element, wherein the diagnostic information is at least used to characterize the cause of the abnormality in the core network element.

[0011] Optionally, before obtaining the target indicator data corresponding to the core network network element reported by the health monitoring client, the method also includes: receiving a registration request sent by the core network network element and the health monitoring client corresponding to the core network network element, wherein the registration request includes: the target strategy, basic information of the core network network element; registering the core network network element and the health monitoring client corresponding to the core network network element based on the information in the registration request, and returning the registration result to the core network network element and the health monitoring client corresponding to the core network network element, wherein the health monitoring client after successful registration is used to report the target indicator data corresponding to the core network network element to the monitoring center.

[0012] According to another aspect of an embodiment of the present application, a network element status monitoring device is also provided, including: a data acquisition module, used to acquire target indicator data corresponding to the core network network element reported by a health monitoring client in a target monitoring period, wherein the health monitoring client is used to determine the target policy corresponding to the core network network element, and the target policy is at least used to indicate the collection, reporting and alarm policy of the indicator data of the health monitoring indicator corresponding to the core network network element, and each core network network element corresponds to a health monitoring client; a threshold determination module, used to determine the alarm threshold conditions corresponding to each health monitoring indicator of the core network network element in the target monitoring period based on the historical indicator data corresponding to the health monitoring indicator of the core network network element in the historical monitoring period, wherein the historical monitoring period is a monitoring period located before the target monitoring period; an alarm prompt module, used to issue an alarm when the target indicator data meets the alarm threshold conditions.

[0013] According to another aspect of the embodiment of the present application, a network element status monitoring system is also provided, including: a health monitoring client and a monitoring center, wherein the health monitoring client is used to determine the target strategy corresponding to the core network network element, the target strategy is at least used to indicate the collection, reporting and alarm strategy of the indicator data of the health monitoring indicator corresponding to the core network network element, wherein each core network network element corresponds to a health monitoring client; the monitoring center is used to obtain the target indicator data corresponding to the core network network element reported by the health monitoring client in the target monitoring period; determine the alarm threshold conditions corresponding to each health monitoring indicator of the core network element in the target monitoring period based on the historical indicator data corresponding to the health monitoring indicator of the core network element in the historical monitoring period, wherein the historical monitoring period is the monitoring period before the target monitoring period; and issue an alarm when the target indicator data meets the alarm threshold conditions.

[0014] According to another aspect of the embodiments of the present application, there is further provided an electronic device, including: a memory and a processor, the processor being configured to run a program stored in the memory, wherein the network element status monitoring method is executed when the program is run.

[0015] According to another aspect of the embodiments of the present application, a non-volatile storage medium is provided, the non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the network element status monitoring method by running the computer program.

[0016] According to another aspect of the embodiments of the present application, a computer program product is provided, including a computer program, which implements the steps of the network element status monitoring method when the computer program is executed by a processor.

[0017] In an embodiment of the present application, the target indicator data corresponding to the core network network element reported by the health monitoring client is obtained during the target monitoring period, wherein the health monitoring client is used to determine the target strategy corresponding to the core network network element, and the target strategy is at least used to indicate the collection, reporting and alarm strategy of the indicator data of the health monitoring indicator corresponding to the core network network element, and each core network network element corresponds to a health monitoring client; according to the historical indicator data corresponding to the health monitoring indicator of the core network network element in the historical monitoring period, the alarm threshold conditions corresponding to the various health monitoring indicators of the core network network element in the target monitoring period are determined, wherein the historical monitoring period is within the target monitoring period. The monitoring cycle before the measurement cycle; when the target indicator data meets the alarm threshold conditions, the alarm is issued. By integrating the health monitoring client in the core network element, the client can formulate dynamic strategies according to the needs of the element itself. In addition, by performing multi-dimensional analysis on the indicator data reported by the monitoring client, the alarm threshold and pattern recognition are automatically set to realize intelligent or customized alarms, thereby achieving the purpose of monitoring the core network elements throughout their life cycle, identifying potential faults in advance and performing preventive maintenance, thereby solving the technical problem of poor core network element status monitoring caused by the fact that related technologies usually adopt fixed alarm thresholds and unified monitoring strategies. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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:

[0019] Figure 1 It is a hardware structure block diagram of a computer terminal (or electronic device) for implementing a method for network element status monitoring provided in an embodiment of the present application;

[0020] Figure 2 It is a schematic diagram of a method flow for network element status monitoring provided according to an embodiment of the present application;

[0021] Figure 3 It is a structural diagram of a method module for 5G core network element full life cycle health monitoring and diagnosis according to an embodiment of the present application;

[0022] Figure 4 It is a timing diagram of a method for full life cycle health monitoring and diagnosis of 5G core network elements provided in accordance with an embodiment of the present application;

[0023] Figure 5 It is a structural diagram of a network element status monitoring device provided according to an embodiment of the present application;

[0024] Figure 6It is a structural diagram of a network element status monitoring system provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] 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.

[0026] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings 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.

[0027] The monitoring solutions in related technologies usually adopt fixed alarm thresholds and unified monitoring strategies, which are difficult to dynamically adjust according to the actual conditions of different network elements. Network elements with different characteristics and operating conditions are evaluated by the same standards, which easily leads to false positives and false negatives. In addition, the monitoring solutions in related technologies often cannot collect enough fault information when the process terminates abnormally, which limits the rapid location and analysis of problems by developers and operation and maintenance personnel. These deficiencies lead to problems such as long fault location time, difficult preventive maintenance, and low operation and maintenance efficiency in 5G networks, which directly affect the service quality and stability of the network.

[0028] In order to solve the above problems, relevant solutions are provided in the embodiments of the present application, and intelligent monitoring and diagnosis based on the entire life cycle are proposed, which comprehensively covers the normal operation, abnormal status and fault diagnosis stages of the network element. While solving the above problems, it also improves the monitoring and management of the network element throughout the entire life cycle, which is described in detail below.

[0029] According to an embodiment of the present application, a method embodiment of network element status monitoring 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.

[0030] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal (or electronic device) for implementing a network element status monitoring method. Figure 1 As shown, the computer terminal 10 (or electronic device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 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 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0031] It should be noted that the one or more processors 102 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 computer terminal 10 (or electronic device). 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).

[0032] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the network element status monitoring method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the above-mentioned network element status monitoring method is realized. The memory 104 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 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 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.

[0033] The transmission device 106 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 computer terminal 10. In one example, the transmission device 106 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 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0034] 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 computer terminal 10 (or electronic device).

[0035] In the above operating environment, the embodiment of the present application provides a network element status monitoring method, Figure 2 is a schematic diagram of a method flow for monitoring network element status according to an embodiment of the present application, such as Figure 2 As shown, the method comprises the following steps:

[0036] Step S202, in the target monitoring period, obtaining the target indicator data corresponding to the core network element reported by the health monitoring client, wherein the health monitoring client is used to determine the target strategy corresponding to the core network element, and the target strategy is at least used to indicate the collection, reporting and alarm strategy of the indicator data of the health monitoring indicator corresponding to the core network element, and each core network element corresponds to a health monitoring client;

[0037] Step S204, determining the alarm threshold conditions corresponding to the health monitoring indicators of the core network elements in the target monitoring period according to the historical indicator data corresponding to the health monitoring indicators of the core network elements in the historical monitoring period, wherein the historical monitoring period is the monitoring period before the target monitoring period;

[0038] Step S206: When the target indicator data meets the alarm threshold condition, an alarm is issued.

[0039] Through the above steps, by integrating the health monitoring client in the core network element, the client can formulate dynamic strategies according to the needs of the element itself. In addition, by performing multi-dimensional analysis on the indicator data reported by the monitoring client, the alarm threshold and pattern recognition are automatically set to realize intelligent or customized alarms, thereby achieving the purpose of monitoring the core network elements throughout their life cycle, identifying potential faults in advance and performing preventive maintenance, thereby solving the technical problem of poor core network element status monitoring caused by the fact that related technologies usually adopt fixed alarm thresholds and unified monitoring strategies.

[0040] The following further introduces the network element status monitoring method in steps S202 to S206 of the embodiment of the present application.

[0041] The embodiment of the present application can be based on the monitoring and diagnosis of the whole life cycle, comprehensively covering the normal operation, abnormal state and fault diagnosis stages of the network element, ensuring more perfect management of the network element throughout the life cycle, so as to improve the operation stability of the network element in the 5G core network and the efficiency of operation and maintenance, optimization and location problems. The whole method process can be implemented through modules such as the health monitoring client and the intelligent monitoring center, and with the help of the collection tool as a crash collection service, the collection and push of crash information can be realized. Specifically, Figure 3 As shown, in this embodiment, the health monitoring client can be embedded in the core network element, and is mainly responsible for real-time monitoring of the network element's operating status and the collection and reporting of health indicator data. The client is adaptive and intelligent, and can flexibly formulate and adjust monitoring strategies according to the network element's own operating conditions and environmental changes; the monitoring center is the core management component of the system, and has two major functions: intelligent alarm and intelligent error diagnosis. It is used to centrally process the data reported by the network element monitoring client, perform intelligent analysis, and perform fault information diagnosis and analysis; the crash collection service can push error information by configuring the monitoring center's service address. The overall process is as follows.

[0042] First, a health monitoring client can be integrated into the core network element. The health monitoring client can formulate dynamic strategies according to the needs of the network element itself; the monitoring center can intelligently adjust the health assessment method according to the strategy reported by the health monitoring client to ensure accurate health status judgment throughout the life cycle of the network element. Secondly, the monitoring center also performs multi-dimensional analysis of the indicator data reported by the health monitoring client based on the AI ​​algorithm, and realizes intelligent or customized alarms by automatically (or manually) setting alarm thresholds and pattern recognition, helping the operation and maintenance team to identify potential faults in advance and perform preventive maintenance. In addition, when the network element terminates abnormally, the monitoring center can also collect fault stack information and logs through the crash collection service (ie, the target service), and intelligently generate fault analysis reports through AI diagnostic tools to provide developers and operation and maintenance personnel with detailed diagnostic information, which is further explained below.

[0043] Figure 4 This is a timing diagram of a method for health monitoring and diagnosis of a 5G core network element throughout its life cycle provided in an embodiment of the present application, such as Figure 4 shown.

[0044] First, after the network element is started, it is necessary to complete the registration in the monitoring center. The specific steps are as follows.

[0045] In some embodiments of the present application, before obtaining the target indicator data corresponding to the core network network element reported by the health monitoring client, the method also includes: receiving a registration request sent by the core network network element and the health monitoring client corresponding to the core network network element, wherein the registration request includes: the target strategy, basic information of the core network network element; registering the core network network element and the health monitoring client corresponding to the core network network element based on the information in the registration request, and returning the registration result to the core network network element and the health monitoring client corresponding to the core network network element, wherein the health monitoring client after successful registration is used to report the target indicator data corresponding to the core network network element to the monitoring center.

[0046] Specifically, the network element process starts, triggering a registration request to the monitoring center, carrying the policy information of the monitoring client (i.e., the target policy) and the basic information of the network element (e.g., network element identification, type, etc.); the monitoring center receives the registration request and processes the data, and returns the registration result, thus completing the registration of the core network network element, i.e., its corresponding health monitoring client. The registration mechanism ensures that the monitoring center can accurately grasp the network element information and monitoring strategy, which is suitable for dynamic access and management of network equipment.

[0047] Afterwards, the health monitoring client corresponding to the core network element can collect the indicator data of various health monitoring indicators corresponding to the core network element according to the target strategy and report them, as follows.

[0048] In some embodiments of the present application, different core network elements correspond to different target strategies under different operating conditions, wherein the target strategy is determined by the health monitoring client based on the basic information and operating conditions of the core network element, and the operating conditions include at least one of the following: the load status of the core network element, the operating stage of the core network element, the operating stage includes at least one of the following: the upgrade stage, and the target strategy includes at least one of the following: various health monitoring indicators that the core network element needs to collect, and the period length of the target monitoring period corresponding to the core network element.

[0049] Specifically, in response to the problem that the monitoring system in the related art collects network element data in a unified and fixed manner and does not support a more fine-grained collection strategy, the embodiment of the present application integrates an adaptive health monitoring client for the network element, which can support the dynamic formulation of monitoring strategies according to the operating conditions (status) of the network element to adapt to the needs of each stage in the life cycle. In various situations such as load peaks, resource bottlenecks or performance anomalies, the health monitoring client can dynamically adjust the reporting target strategy and monitoring indicators through AI algorithms, and realize different reporting strategies for different indicator data as required, which is different from the traditional consistent static standards, and realizes personalized and phased adjustments, thereby improving the accuracy and flexibility of monitoring.

[0050] For example, in this embodiment, the network element can determine the reporting cycle (i.e., the cycle length of the target monitoring cycle), the reporting data (i.e., the various health monitoring indicators that need to be collected), etc. according to its own situation. For example, when a 5G UPF (UserPlane Function) network element is started, the health monitoring client starts to collect indicators such as CPU usage, memory occupancy, and packet processing rate according to the preset strategy, and reports them to the monitoring center. If the UPF processing capacity reaches its limit during peak hours, the client will identify the anomaly and adjust the reporting frequency to ensure that the monitoring center receives timely performance data. For example, when the CPU usage exceeds 70%, it is reported once per second; when the memory occupancy exceeds 75% of the total memory, detailed memory usage is reported every 5 minutes; when there is a delay in packet processing, the current processing status is reported immediately. This strategy ensures that the monitoring data is both comprehensive and timely, while avoiding the network burden caused by excessive reporting.

[0051] In addition, the target strategy in the embodiment of the present application also includes some customized alarm strategies flexibly formulated by the health monitoring client according to the network element's own operating conditions and environmental changes. For example, an alarm is issued if the number of underreporting of indicator data exceeds a certain threshold. Or, when the network element is in the upgrade stage, the target strategy can indicate to the monitoring center that the network element is in the system upgrade state, and no alarm is triggered for the underreporting of the network element during the upgrade process.

[0052] It should be noted that the health monitoring client in the embodiment of the present application can actively and adaptively adjust the target strategy corresponding to each network element according to various environments and states of various network elements, so as to better realize the health monitoring of the network element throughout its life cycle.

[0053] The monitoring center can continuously receive various indicator data reported by the health monitoring client, and continuously analyze the received data through AI, comprehensively combine historical indicator data and network element information to dynamically adjust the alarm threshold conditions, and perform trend prediction to generate intelligent alarms or early warning information. The specific steps are as follows.

[0054] In some embodiments of the present application, determining the alarm threshold conditions corresponding to various health monitoring indicators of the core network network elements within the target monitoring period based on the historical indicator data corresponding to the health monitoring indicators of the core network network elements in the historical monitoring periods includes the following steps: obtaining the historical indicator data of the health monitoring indicators of the core network network elements within multiple historical monitoring periods; determining the arithmetic characteristic parameters of the multiple historical indicator data corresponding to the health monitoring indicators, wherein the arithmetic characteristic parameters include: mean, standard deviation, upper quartile, lower quartile; determining the basic threshold corresponding to the health monitoring indicator based on the mean and standard deviation corresponding to the multiple historical indicator data, and determining the quantile threshold corresponding to the health monitoring indicator based on the upper quartile and lower quartile corresponding to the multiple historical indicator data; determining the alarm threshold conditions corresponding to the health monitoring indicator based on the basic threshold and quantile threshold corresponding to the health monitoring indicator.

[0055] Specifically, in response to the problem that the alarm thresholds in the related technology need to be manually configured and need to rely on manual modification of the configuration in capacity expansion or other scenarios, the embodiment of the present application integrates an intelligent big model in the monitoring center, which can continuously perform multi-dimensional analysis of indicator data, automatically set alarm thresholds according to scenario changes, realize intelligent alarms and predictions, identify potential abnormal risks in advance, help the operation and maintenance team deploy maintenance resources in advance, effectively improve the system's preventive capabilities, and solve the problem of dependence on manual configuration.

[0056] For example, assume that the data set consisting of the historical indicator data of multiple historical monitoring periods corresponding to the health monitoring indicator (such as CPU usage) of a core network element is: {x1, x2, ..., x n}. By calculating the mean of the historical indicator data in the data set and standard deviation The basic thresholds corresponding to the health monitoring indicators can be determined. The specific steps are as follows.

[0057] In some embodiments of the present application, the basic threshold includes: a basic threshold upper limit and a basic threshold lower limit; determining the basic threshold corresponding to the health monitoring indicator based on the mean and standard deviation corresponding to multiple historical indicator data includes: determining the initial basic threshold based on the mean and standard deviation; using a sliding window, according to a preset sliding step, performing a sliding average operation on the historical indicator data sequence, wherein the historical indicator data sequence is obtained by sorting the historical indicator data according to the chronological order of the historical monitoring period corresponding to each historical indicator data, and the sliding average operation is used to calculate the average value of the historical indicator data within the range selected by the sliding window to obtain the sliding average value, and the sliding average operation is performed each time the sliding window is moved; based on the sliding average value, determining the incremental trend parameter corresponding to the historical indicator data of the health monitoring indicator, wherein the incremental trend parameter is used to characterize the changing trend of the historical indicator data; when the incremental trend parameter exceeds the preset incremental trend threshold, using an adjustment factor to adjust the initial basic threshold to obtain a final basic threshold.

[0058] Specifically, firstly, a high threshold T is set based on the mean and standard deviation. upper and low threshold T lower (i.e. the initial upper and lower limits of the basic thresholds mentioned above), as shown in the following formula:

[0059] T upper =μ+k·σ

[0060] T lower =max(0,μ-k·σ)

[0061] Here, k is an adjustable constant (eg, k=2, which is suitable for common threshold settings).

[0062] Afterwards, the data set (data series) composed of historical indicator data can be subjected to sliding average processing to detect the transformation trend of the data. In this embodiment, the window length of the sliding window is defined as w. By continuously moving the sliding window, multiple sliding average values ​​MA can be obtained. Then, the trend value Trend (i.e., the above-mentioned incremental trend parameter) of the historical indicator data can be determined through the difference change value of adjacent sliding average values ​​and the window length of the sliding window. According to the trend value Trend, the initial basic threshold can be adjusted to obtain the final basic threshold.

[0063] Specifically, if Trend>Trendthreshold (preset incremental trend threshold), the upper threshold (upper limit of the basic threshold) is raised, as shown in the following formula:

[0064] Tupper=T upper ×(1+α)

[0065] If Trend<-Trendthreshold, lower the lower threshold (basic threshold lower limit), as shown in the following formula:

[0066] Tlower=T lower ×(1-β)

[0067] Among them, α and β are adjustment factors.

[0068] For example, taking CPU usage as an example, the monitoring center analyzed the CPU usage of a UPF network element in the past month and found that its average usage was 60%, the standard deviation was 10%, and an initial high threshold was set at 80%. As the network element load changes, the monitoring center detects that the CPU usage trend is rising. By calculating the trend value and setting the trend threshold (Trendthreshold), the monitoring center can automatically adjust the high threshold to 85%, thereby making a more timely response to the upcoming high load state and avoiding false alarms and missed alarms.

[0069] On the other hand, it is also possible to determine that the data set composed of historical indicator data is: {x1, x2, ..., x n}, including the upper quartile Q 75 and the lower quartile Q 25 , and based on the upper quartile and the lower quartile, determine the quantile threshold corresponding to the health monitoring indicator, including: the upper limit of the quantile threshold T upper\quantile and the lower limit of the quantile threshold T lower\quantile , as shown in the following formula:

[0070] T upper\quantile =Q 75 +1.5×(Q 75 -Q 25 )

[0071] T lower\quantile =Q 25 -1.5×(Q 75 -Q 25 )Finally, the basic threshold and quantile threshold can be used to determine the final alarm threshold condition. The specific steps are as follows.

[0072] In some embodiments of the present application, the quantile threshold includes the following steps: a quantile threshold upper limit and a quantile threshold lower limit; the alarm threshold condition includes: a target threshold upper limit and a target threshold lower limit corresponding to the health monitoring indicator; based on the basic threshold and the quantile threshold corresponding to the health monitoring indicator, determining the alarm threshold condition corresponding to the health monitoring indicator includes: comparing the size relationship between the basic threshold upper limit and the quantile threshold upper limit, and determining the larger value between the basic threshold upper limit and the quantile threshold upper limit as the target threshold upper limit corresponding to the health monitoring indicator; comparing the size relationship between the basic threshold lower limit and the quantile threshold lower limit, and determining the smaller value between the basic threshold lower limit and the quantile threshold lower limit as the target threshold lower limit corresponding to the health monitoring indicator.

[0073] Specifically, in this embodiment, the target threshold upper limit T upper\final and the target threshold lower limit T lower\final The determination formula can be shown as follows:

[0074] T upper\final =max(T upper , T upper\quantile )

[0075] T lower\final =min(T lower , T lower\quantile )

[0076] While dynamically determining the alarm warning conditions, the monitoring center can issue warning information through trend forecasting, make intelligent judgments based on the overall situation, generate alarms and report them to the alarm center. For example, when real-time data exceeds the final upper threshold or is lower than the final lower threshold, that is, when the target indicator data meets the alarm threshold conditions, an alarm is triggered.

[0077] The embodiment of the present application uses an AI-driven approach to automatically build an alarm model through multi-dimensional analysis of historical data of network elements, so that the monitoring center can adaptively generate personalized alarm thresholds, reduce manual intervention and workload, and improve operation and maintenance efficiency.

[0078] In addition, in view of the problem that the monitoring system in the related art only monitors the network elements under normal operating conditions and does not support the information collection and diagnosis of abnormal and fault conditions, the embodiment of the present application also adds a crash collection service (i.e., target service) to comprehensively cover the monitoring and management of the normal operation, abnormal state, and fault diagnosis of the network elements at all stages, thereby realizing the health monitoring of the entire life cycle of the network elements, filling the limitations of traditional monitoring, and helping the operation and maintenance or developers to quickly locate the problem when a fault occurs, effectively shortening the fault recovery time, and providing a basis for subsequent optimization. The specific steps are as follows.

[0079] In some embodiments of the present application, the method also includes: when an abnormality is detected in a core network network element, using a target service to obtain log and stack files corresponding to the core network network element from a file system, wherein the target service is used to collect fault stack information and logs when the core network network element exits abnormally; based on the log and stack files, determining diagnostic information corresponding to the core network network element, wherein the diagnostic information is at least used to characterize the cause of the abnormality in the core network network element.

[0080] Specifically, when the network element program terminates abnormally, logs and memory stack information will be generated in the file system. In this embodiment, the collected logs and stack information can be pushed to the monitoring center through the target service (crash collection service), and the monitoring center generates diagnostic reports and summary information through AI intelligent diagnosis of logs and memory stack information; operation and maintenance personnel can directly obtain diagnostic reports and summaries from the monitoring center to locate and repair errors. Among them, the crash collection tools in the embodiments of the present application include but are not limited to Linux system-level programs Apport, ABRT and other tools.

[0081] For example, if a network element suddenly crashes, the crash collection service will collect the system log and stack information at that moment and upload it to the monitoring center. The AI-driven intelligent diagnosis module of the monitoring center will analyze this information and identify the crash caused by a memory leak. It will generate a detailed diagnostic report, including the specific location and possible causes of the memory leak, to help operation and maintenance personnel quickly locate the problem and reduce the time for fault recovery.

[0082] The embodiment of the present application uses a method of full life cycle health monitoring of network elements. In the event of a network element failure, log and stack information can be automatically collected and diagnostic information can be generated, which significantly shortens the time for locating errors and repairing problems, and provides support for rapid recovery of network elements.

[0083] This application scheme collects and reports health monitoring indicators of core network elements according to the target strategy through the health monitoring client. The monitoring center dynamically adjusts the alarm threshold conditions based on historical data, which can more accurately reflect the operating status of the network elements and avoid the false alarm or missed alarm problems caused by fixed thresholds. At the same time, by analyzing the logs and stack files under abnormal conditions, the cause of the problem can be quickly located, improving the efficiency of troubleshooting. In addition, by adjusting the monitoring strategy according to different network elements and operating conditions, more refined network element status monitoring is achieved, which improves the intelligent level of network operation and maintenance.

[0084] According to an embodiment of the present application, an embodiment of a network element status monitoring device is also provided. Figure 5 Schematic diagram of a network element status monitoring device provided according to an embodiment of the present application. Figure 5 As shown, the device comprises:

[0085] The data acquisition module 50 is used to obtain the target indicator data corresponding to the core network element reported by the health monitoring client during the target monitoring period, wherein the health monitoring client is used to determine the target strategy corresponding to the core network element, and the target strategy is at least used to indicate the collection, reporting and alarm strategy of the indicator data of the health monitoring indicator corresponding to the core network element, and each core network element corresponds to a health monitoring client;

[0086] A threshold determination module 52, configured to determine the alarm threshold conditions corresponding to the health monitoring indicators of the core network elements in the target monitoring period according to the historical indicator data corresponding to the health monitoring indicators of the core network elements in the historical monitoring period, wherein the historical monitoring period is the monitoring period before the target monitoring period;

[0087] The alarm prompt module 54 is used to issue an alarm when the target indicator data meets the alarm threshold conditions.

[0088] Optionally, determining the alarm threshold conditions corresponding to various health monitoring indicators of the core network network elements within the target monitoring period based on the historical indicator data corresponding to the health monitoring indicators of the core network network elements in the historical monitoring periods includes: obtaining the historical indicator data of the health monitoring indicators of the core network network elements within multiple historical monitoring periods; determining the arithmetic characteristic parameters of multiple historical indicator data corresponding to the health monitoring indicators, wherein the arithmetic characteristic parameters include: mean, standard deviation, upper quartile, lower quartile; determining the basic threshold corresponding to the health monitoring indicator based on the mean and standard deviation corresponding to the multiple historical indicator data, and determining the quantile threshold corresponding to the health monitoring indicator based on the upper quartile and lower quartile corresponding to the multiple historical indicator data; determining the alarm threshold conditions corresponding to the health monitoring indicator based on the basic threshold and quantile threshold corresponding to the health monitoring indicator.

[0089] Optionally, the basic threshold includes: a basic threshold upper limit and a basic threshold lower limit; determining the basic threshold corresponding to the health monitoring indicator based on the mean and standard deviation corresponding to multiple historical indicator data includes: determining the initial basic threshold based on the mean and standard deviation; using a sliding window, according to a preset sliding step, performing a sliding average operation on the historical indicator data sequence, wherein the historical indicator data sequence is obtained by sorting the historical indicator data according to the chronological order of the historical monitoring period corresponding to each historical indicator data, and the sliding average operation is used to calculate the average value of the historical indicator data within the range selected by the sliding window to obtain the sliding average value, and a sliding average operation is performed each time the sliding window is moved; based on the sliding average value, determining the incremental trend parameter corresponding to the historical indicator data of the health monitoring indicator, wherein the incremental trend parameter is used to characterize the changing trend of the historical indicator data; when the incremental trend parameter exceeds the preset incremental trend threshold, using an adjustment factor to adjust the initial basic threshold to obtain a final basic threshold.

[0090] Optionally, the quantile threshold includes: an upper quantile threshold and a lower quantile threshold; the alarm threshold condition includes: an upper target threshold and a lower target threshold corresponding to the health monitoring indicator; based on the basic threshold and quantile threshold corresponding to the health monitoring indicator, determining the alarm threshold condition corresponding to the health monitoring indicator includes: comparing the size relationship between the upper basic threshold and the upper quantile threshold, and determining the larger value between the upper basic threshold and the upper quantile threshold as the upper target threshold corresponding to the health monitoring indicator; comparing the size relationship between the lower basic threshold and the lower quantile threshold, and determining the smaller value between the lower basic threshold and the lower quantile threshold as the lower target threshold corresponding to the health monitoring indicator.

[0091] Optionally, different core network elements correspond to different target strategies under different operating conditions, wherein the target strategy is determined by the health monitoring client based on the basic information and operating conditions of the core network elements, the operating conditions include at least one of the following: the load status of the core network elements, the operating stage of the core network elements, the operating stage includes at least one of the following: the upgrade stage, and the target strategy includes at least one of the following: various health monitoring indicators that the core network elements need to collect, and the period length of the target monitoring period corresponding to the core network elements.

[0092] Optionally, the network element status monitoring device is also used to: when an abnormality is detected in a core network network element, use a target service to obtain logs and stack files corresponding to the core network network element from the file system, wherein the target service is used to collect fault stack information and logs when the core network element exits abnormally; based on the logs and stack files, determine the diagnostic information corresponding to the core network element, wherein the diagnostic information is at least used to characterize the cause of the abnormality in the core network element.

[0093] Optionally, before obtaining the target indicator data corresponding to the core network network element reported by the health monitoring client, it also includes: receiving a registration request sent by the core network network element and the health monitoring client corresponding to the core network network element, wherein the registration request includes: the target strategy, basic information of the core network network element; registering the core network network element and the health monitoring client corresponding to the core network network element based on the information in the registration request, and returning the registration result to the core network element and the health monitoring client corresponding to the core network element, wherein the health monitoring client after successful registration is used to report the target indicator data corresponding to the core network element to the monitoring center.

[0094] By integrating the health monitoring client into the network element, the network element can flexibly control the reporting strategy of the indicator data and set different reporting conditions for different indicators to meet the monitoring needs of most situations. The network element is monitored for its entire life cycle, covering the normal state, abnormal state, and fault exit scenarios. Information collection and intelligent fault diagnosis can be performed when the network element exits abnormally. The monitoring center combines AI algorithms to build an alarm model through multi-dimensional analysis of the historical data of the network element, so that the monitoring center can adaptively generate personalized alarm thresholds and automatically identify potential fault modes.

[0095] It should be noted that the various modules in the above-mentioned network element status monitoring device can be program modules (for example, a set of program instructions that implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0096] It should be noted that the network element status monitoring device provided in this embodiment can be used to perform Figure 2 The network element status monitoring method shown, therefore, the relevant explanations and descriptions of the above-mentioned network element status monitoring method are also applicable to the embodiments of the present application and will not be repeated here.

[0097] According to an embodiment of the present application, an embodiment of a network element status monitoring system is also provided. Figure 6 is a schematic diagram of the structure of a network element status monitoring system provided according to an embodiment of the present application. Figure 6 As shown, the system includes:

[0098] A health monitoring client 60, used to determine a target strategy corresponding to a core network element, wherein the target strategy is used to at least indicate the collection, reporting and alarm strategy of the indicator data of the health monitoring indicator corresponding to the core network element, wherein each core network element corresponds to a health monitoring client 60;

[0099] The monitoring center 62 is used to obtain the target indicator data corresponding to the core network network elements reported by the health monitoring client 60 during the target monitoring period; determine the alarm threshold conditions corresponding to the various health monitoring indicators of the core network network elements during the target monitoring period based on the historical indicator data corresponding to the health monitoring indicators of the core network network elements in the historical monitoring period, wherein the historical monitoring period is the monitoring period before the target monitoring period; and issue an alarm when the target indicator data meets the alarm threshold conditions.

[0100] The monitoring client in the embodiment of the present application can assist the network element to dynamically adjust the monitoring strategy according to the actual operating status of the network element to ensure the accuracy of monitoring; the monitoring center uses the AI-driven intelligent alarm system to perform multi-dimensional analysis of the performance data of the network element throughout its life cycle and automatically set dynamic alarm thresholds. For example, the monitoring center can identify the performance trend of a specific network element during peak periods and avoid invalid alarms during normal fluctuations through adaptive threshold setting; the details are as follows.

[0101] Optionally, determining the alarm threshold conditions corresponding to various health monitoring indicators of the core network network elements within the target monitoring period based on the historical indicator data corresponding to the health monitoring indicators of the core network network elements in the historical monitoring periods includes: obtaining the historical indicator data of the health monitoring indicators of the core network network elements within multiple historical monitoring periods; determining the arithmetic characteristic parameters of multiple historical indicator data corresponding to the health monitoring indicators, wherein the arithmetic characteristic parameters include: mean, standard deviation, upper quartile, lower quartile; determining the basic threshold corresponding to the health monitoring indicator based on the mean and standard deviation corresponding to the multiple historical indicator data, and determining the quantile threshold corresponding to the health monitoring indicator based on the upper quartile and lower quartile corresponding to the multiple historical indicator data; determining the alarm threshold conditions corresponding to the health monitoring indicator based on the basic threshold and quantile threshold corresponding to the health monitoring indicator.

[0102] Optionally, the basic threshold includes: a basic threshold upper limit and a basic threshold lower limit; determining the basic threshold corresponding to the health monitoring indicator based on the mean and standard deviation corresponding to multiple historical indicator data includes: determining the initial basic threshold based on the mean and standard deviation; using a sliding window, according to a preset sliding step, performing a sliding average operation on the historical indicator data sequence, wherein the historical indicator data sequence is obtained by sorting the historical indicator data according to the chronological order of the historical monitoring period corresponding to each historical indicator data, and the sliding average operation is used to calculate the average value of the historical indicator data within the range selected by the sliding window to obtain the sliding average value, and a sliding average operation is performed each time the sliding window is moved; based on the sliding average value, determining the incremental trend parameter corresponding to the historical indicator data of the health monitoring indicator, wherein the incremental trend parameter is used to characterize the changing trend of the historical indicator data; when the incremental trend parameter exceeds the preset incremental trend threshold, using an adjustment factor to adjust the initial basic threshold to obtain a final basic threshold.

[0103] Optionally, the quantile threshold includes: an upper quantile threshold and a lower quantile threshold; the alarm threshold condition includes: an upper target threshold and a lower target threshold corresponding to the health monitoring indicator; based on the basic threshold and quantile threshold corresponding to the health monitoring indicator, determining the alarm threshold condition corresponding to the health monitoring indicator includes: comparing the size relationship between the upper basic threshold and the upper quantile threshold, and determining the larger value between the upper basic threshold and the upper quantile threshold as the upper target threshold corresponding to the health monitoring indicator; comparing the size relationship between the lower basic threshold and the lower quantile threshold, and determining the smaller value between the lower basic threshold and the lower quantile threshold as the lower target threshold corresponding to the health monitoring indicator.

[0104] Optionally, different core network elements correspond to different target strategies under different operating conditions, wherein the target strategy is determined by the health monitoring client based on the basic information and operating conditions of the core network elements, the operating conditions include at least one of the following: the load status of the core network elements, the operating stage of the core network elements, the operating stage includes at least one of the following: the upgrade stage, and the target strategy includes at least one of the following: various health monitoring indicators that the core network elements need to collect, and the period length of the target monitoring period corresponding to the core network elements.

[0105] Optionally, the monitoring center 62 is also used to: when an abnormality is detected in a core network element, use the target service to obtain the log and stack files corresponding to the core network element from the file system, wherein the target service is used to collect fault stack information and logs when the core network element exits abnormally; based on the log and stack files, determine the diagnostic information corresponding to the core network element, wherein the diagnostic information is at least used to characterize the cause of the abnormality in the core network element.

[0106] Optionally, before obtaining the target indicator data corresponding to the core network network element reported by the health monitoring client, it also includes: receiving a registration request sent by the core network network element and the health monitoring client corresponding to the core network network element, wherein the registration request includes: the target strategy, basic information of the core network network element; registering the core network network element and the health monitoring client corresponding to the core network network element based on the information in the registration request, and returning the registration result to the core network element and the health monitoring client corresponding to the core network element, wherein the health monitoring client after successful registration is used to report the target indicator data corresponding to the core network element to the monitoring center.

[0107] It should be noted that modules such as the health monitoring client and monitoring center in the above-mentioned network element status monitoring system can be program modules (for example, a set of program instructions to implement a certain specific function, a virtual server in the cloud, etc.) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0108] It should be noted that the network element status monitoring system provided in this embodiment can be used to perform Figure 2 The network element status monitoring method shown, therefore, the relevant explanations and descriptions of the above-mentioned network element status monitoring method are also applicable to the embodiments of the present application and will not be repeated here.

[0109] An embodiment of the present application also provides a non-volatile storage medium, the non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the following network element status monitoring method by running the computer program: in a target monitoring period, obtaining target indicator data corresponding to the core network network element reported by the health monitoring client, wherein the health monitoring client is used to determine the target policy corresponding to the core network network element, and the target policy is at least used to indicate the collection, reporting and alarm policy of the indicator data of the health monitoring indicator corresponding to the core network network element, and each core network network element corresponds to a health monitoring client; based on the historical indicator data corresponding to the health monitoring indicator of the core network network element in the historical monitoring period, determining the alarm threshold conditions corresponding to each health monitoring indicator of the core network network element in the target monitoring period, wherein the historical monitoring period is a monitoring period located before the target monitoring period; and when the target indicator data meets the alarm threshold conditions, an alarm is issued.

[0110] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the network element status monitoring method described in each embodiment of the present application: in a target monitoring period, obtaining target indicator data corresponding to the core network network element reported by a health monitoring client, wherein the health monitoring client is used to determine the target strategy corresponding to the core network network element, and the target strategy is at least used to indicate the collection, reporting and alarm strategy of the indicator data of the health monitoring indicator corresponding to the core network network element, and each core network network element corresponds to a health monitoring client; based on the historical indicator data corresponding to the health monitoring indicator of the core network network element in the historical monitoring period, determining the alarm threshold conditions corresponding to each health monitoring indicator of the core network network element in the target monitoring period, wherein the historical monitoring period is a monitoring period located before the target monitoring period; and issuing an alarm when the target indicator data meets the alarm threshold conditions.

[0111] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0112] 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.

[0113] 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 the 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.

[0114] 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 on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0115] 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.

[0116] 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, in essence, 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, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment 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 and other media that can store program codes.

[0117] The above is only a preferred implementation 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 network element status monitoring method, characterized in that: include: In the target monitoring period, the target indicator data corresponding to the core network element reported by the health monitoring client is obtained, wherein the health monitoring client is used to determine the target strategy corresponding to the core network element, and the target strategy is at least used to indicate the collection, reporting and alarm strategy of the indicator data of the health monitoring indicator corresponding to the core network element, and each core network element corresponds to one health monitoring client; Determine the alarm threshold conditions corresponding to each of the health monitoring indicators of the core network element in the target monitoring period according to the historical indicator data corresponding to the health monitoring indicator of the core network element in the historical monitoring period, wherein the historical monitoring period is a monitoring period before the target monitoring period; When the target indicator data meets the alarm threshold condition, an alarm is issued.

2. The network element status monitoring method according to claim 1, characterized in that: Determining the alarm threshold conditions corresponding to each of the health monitoring indicators of the core network network element within the target monitoring period based on the historical indicator data corresponding to the health monitoring indicator of the core network network element in the historical monitoring period includes: Acquire the historical indicator data of the health monitoring indicator of the core network element within a plurality of the historical monitoring cycles; Determine arithmetic characteristic parameters of the plurality of historical indicator data corresponding to the health monitoring indicator, wherein the arithmetic characteristic parameters include: mean, standard deviation, upper quartile, and lower quartile; Determine the basic threshold value corresponding to the health monitoring indicator according to the mean value and the standard deviation corresponding to the plurality of historical indicator data, and determine the quantile threshold value corresponding to the health monitoring indicator according to the upper quartile and the lower quartile corresponding to the plurality of historical indicator data; The alarm threshold condition corresponding to the health monitoring indicator is determined according to the basic threshold and the quantile threshold corresponding to the health monitoring indicator.

3. The network element status monitoring method according to claim 2, characterized in that: The basic threshold includes: a basic threshold upper limit and a basic threshold lower limit; determining the basic threshold corresponding to the health monitoring indicator based on the mean and the standard deviation corresponding to the plurality of historical indicator data includes: Determining the initial basic threshold value according to the mean value and the standard deviation; A sliding window is used to perform a sliding average operation on a historical indicator data sequence according to a preset sliding step size, wherein the historical indicator data sequence is obtained by sorting the historical indicator data according to the time sequence of the historical monitoring period corresponding to each of the historical indicator data, and the sliding average operation is used to calculate the average value of the historical indicator data within the range selected by the sliding window to obtain the sliding average value, and the sliding average operation is performed once each time the sliding window is moved; Determine, according to the sliding average, an incremental trend parameter corresponding to the historical indicator data of the health monitoring indicator, wherein the incremental trend parameter is used to characterize a change trend of the historical indicator data; When the incremental trend parameter exceeds the preset incremental trend threshold, the initial basic threshold is adjusted by using an adjustment factor to obtain the final basic threshold.

4. The network element status monitoring method according to claim 3, characterized in that: The quantile threshold includes: an upper quantile threshold and a lower quantile threshold; the alarm threshold condition includes: an upper target threshold and a lower target threshold corresponding to the health monitoring indicator; based on the basic threshold and the quantile threshold corresponding to the health monitoring indicator, determining the alarm threshold condition corresponding to the health monitoring indicator includes: Comparing the magnitude relationship between the upper limit of the basic threshold and the upper limit of the quantile threshold, and determining the larger value of the upper limit of the basic threshold and the upper limit of the quantile threshold as the upper limit of the target threshold corresponding to the health monitoring indicator; The magnitude relationship between the basic threshold lower limit and the quantile threshold lower limit is compared, and the smaller value between the basic threshold lower limit and the quantile threshold lower limit is determined as the target threshold lower limit corresponding to the health monitoring indicator.

5. The network element status monitoring method according to claim 1, characterized in that: Different core network elements have different corresponding target strategies under different operating conditions, wherein the target strategy is determined by the health monitoring client based on the basic information and operating conditions of the core network element, and the operating conditions include at least one of the following: the load status of the core network element, the operating stage of the core network element, and the operating stage includes at least one of the following: the upgrade stage, and the target strategy includes at least one of the following: the various health monitoring indicators that the core network element needs to collect, and the period length of the target monitoring period corresponding to the core network element.

6. The network element status monitoring method according to claim 1, characterized in that: The method further comprises: In the case where an abnormality is detected in the core network element, a target service is used to obtain a log and stack file corresponding to the core network element from a file system, wherein the target service is used to collect fault stack information and logs when the core network element exits abnormally; The diagnostic information corresponding to the core network element is determined based on the log and stack file, wherein the diagnostic information is at least used to characterize the cause of the abnormality of the core network element.

7. The network element status monitoring method according to claim 1, characterized in that: Before obtaining the target indicator data corresponding to the core network element reported by the health monitoring client, the method further includes: Receiving a registration request sent by the core network element and the health monitoring client corresponding to the core network element, wherein the registration request includes: the target policy and basic information of the core network element; Based on the information in the registration request, the core network network element and the health monitoring client corresponding to the core network network element are registered, and the registration result is returned to the core network network element and the health monitoring client corresponding to the core network network element, wherein the health monitoring client after successful registration is used to report the target indicator data corresponding to the core network network element to the monitoring center.

8. A network element status monitoring device, characterized in that: include: A data acquisition module, used to acquire target indicator data corresponding to the core network element reported by the health monitoring client during the target monitoring period, wherein the health monitoring client is used to determine the target strategy corresponding to the core network element, and the target strategy is at least used to indicate the collection, reporting and alarm strategy of the indicator data of the health monitoring indicator corresponding to the core network element, and each core network element corresponds to one health monitoring client; A threshold determination module, used to determine the alarm threshold conditions corresponding to each of the health monitoring indicators of the core network network element in the target monitoring period according to the historical indicator data corresponding to the health monitoring indicator of the core network network element in the historical monitoring period, wherein the historical monitoring period is a monitoring period before the target monitoring period; The alarm prompt module is used to issue an alarm when the target indicator data meets the alarm threshold condition.

9. A network element status monitoring system, characterized in that: include: Health monitoring client and monitoring center, where The health monitoring client is used to determine the target strategy corresponding to the core network network element, and the target strategy is at least used to indicate the collection, reporting and alarm strategy of the indicator data of the health monitoring indicator corresponding to the core network network element, wherein each core network network element corresponds to one health monitoring client; The monitoring center is used to obtain the target indicator data corresponding to the core network network element reported by the health monitoring client during the target monitoring period; determine the alarm threshold conditions corresponding to each health monitoring indicator of the core network network element during the target monitoring period based on the historical indicator data corresponding to the health monitoring indicators of the core network network element in the historical monitoring period, wherein the historical monitoring period is the monitoring period before the target monitoring period; and issue an alarm when the target indicator data meets the alarm threshold conditions.

10. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is used to run a program stored in the memory, wherein the program executes the network element status monitoring method according to any one of claims 1 to 7 when running.

11. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the network element status monitoring method according to any one of claims 1 to 7 by running the computer program.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the network element status monitoring method described in any one of claims 1 to 7 are implemented.

Images