Network time delay tracing method and device

Abstract

The invention discloses a network time delay tracing method and device. The method comprises the following steps: acquiring resource tree information reflecting a multi-level network element structure relationship of a network system and time delay detection data of all users in the network system in a target time period; determining a first time delay state of each user according to the time delay detection data, and determining a second time delay state of each network element according to the first time delay states of all users under each network element; determining whether the user side or the network element side causes the time delay abnormity according to the second time delay state of the network element with the time delay abnormity; when the network element end is a network element end, determining each level of target network element associated with the network element with the abnormal time delay according to the resource tree information, and determining a target time delay state sequence corresponding to the network element with the abnormal time delay according to a second time delay state of the target network element; and determining a target fault network element matched with the target time delay state sequence from a preset fault database. According to the method and the device, the technical problem that accurate tracing of the network element or equipment causing time delay is difficult in a network operation and maintenance scene is solved.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a method and device for tracing network delay. Background Art

[0002] In recent years, as users' expectations for network quality have increased, poor latency has become a primary issue impacting user experience. Poor latency refers to a generally increased network latency when users use network services, resulting in noticeable lags and pauses. Poor latency can affect the entire network or only a specific network segment or device. Therefore, locating poor latency requires real-time monitoring of latency changes and precise detection and location of poor latency to quickly resolve the issue and improve the network experience.

[0003] Existing methods for detecting poor network latency mainly rely on passive methods such as manual inspections, user complaints, and fault location to detect poor latency. These methods are not only inefficient but also fail to detect problems before they occur. Consequently, the location of poor network latency is inefficient and inaccurate, making it impossible to quickly resolve the problem and resulting in a poor user experience.

[0004] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0005] The embodiments of the present application provide a network delay tracing method and device to at least solve the technical problem of difficulty in accurately tracing the network elements or devices that cause delays in network operation and maintenance scenarios.

[0006] According to one aspect of an embodiment of the present application, a network delay tracing method is provided, comprising: obtaining resource tree information of a target network system, and obtaining delay detection data of all users in the target network system within a target time period, wherein the resource tree information is used to reflect the structural relationship of network elements at multiple levels in the target network system; determining a first network delay state of each user based on the delay detection data, and determining a second network delay state of each network element based on the first network delay state of all users under each network element; determining a target fault end that causes the abnormal network delay of the abnormal network element based on the second network delay state of the abnormal delay network element, wherein the target fault end includes: a user end or a network element end; when the fault end is a network element end, determining target network elements of each level associated with the abnormal delay network element based on the resource tree information, and determining a target delay state sequence corresponding to the abnormal delay network element based on the second network delay state of the target network element; and determining a target fault network element that matches the target delay state sequence from a preset fault database, wherein the fault database stores a mapping relationship between fault network elements of different levels and different delay state sequences.

[0007] Optionally, determining the first network delay state of each user according to the delay detection data includes: for each user, determining the first network delay state of the user according to the following formula:

[0008]

[0009] In the formula, i represents the i-th day, t1 represents the number of days in which all the user's delay detection data are within the preset normal range, t2 represents the number of days in which the user's delay detection data exceeds the preset normal range, and t s =t1+t2, indicating the total number of days in the target time period, Φ(1)=1, indicating that network delay has an impact on user perception, Φ(0)=0, indicating that network delay has no impact on user perception, and f(t) represents the user’s first network delay state in the target time period.

[0010] Optionally, determining the second network delay state of each network element according to the first network delay state of all users connected to each network element includes: for each network element, determining the second network delay state of the network element according to the following formula:

[0011]

[0012] In the formula, j represents the jth user, m represents the total number of users connected to the network element, m1 represents the number of users whose delay detection data on the i-th day is within the preset normal range, and delay dev (t) represents the second network delay state of the network element within the target time period.

[0013] Optionally, the fault end causing the abnormal network delay in the delay abnormal network element to generate abnormal network delay is determined based on the second network delay status of the delay abnormal network element, including: when the second network delay status is less than a first preset delay threshold, determining that the fault end causing the abnormal network delay in the delay abnormal network element to generate abnormal network delay is the network element end; when the second network delay status is not less than a second preset delay threshold, determining that the fault end causing the abnormal network delay in the delay abnormal network element to generate abnormal network delay is the user end, wherein the second preset delay threshold is greater than the first preset delay threshold.

[0014] Optionally, the process of determining the first preset delay threshold and the second preset delay threshold includes: obtaining multiple sets of delay detection data for all users in the target network system in multiple time periods, and determining the fault end corresponding to each historical time period; for each historical time period, determining that the ratio of the number of users whose delay detection data exceeds a preset normal range in the historical time period to the total number of users in the target network system is a discrete rate corresponding to the historical time period; for each day of each historical time period, determining that the ratio of the number of users whose delay detection data exceeds the preset normal range on that day to the number of users whose delay detection data exceeds the preset normal range in the historical time period is a discrete frequency corresponding to the historical time period; and determining the first preset delay threshold and the second preset delay threshold respectively according to the following formulas:

[0015] delay dev1 (c,v)=1-Φ(1)·c max ·v max

[0016] delay dev2 (c,v)=1-Φ(1)·c min ·v min

[0017] θ1=min(delay dev1 (c,v),delay dev2 (c,v))

[0018] θ2=max(delay dev1 (c,v),delay dev2 (c,v))

[0019] Where θ1 represents the first preset delay threshold, θ2 represents the second preset delay threshold, c represents the discrete rate, v represents the discrete frequency, Φ(1) = 1, indicating that network delay affects user perception, c max Indicates the maximum discrete rate corresponding to the historical time period when the fault end is the user end, v max Indicates the maximum discrete frequency of the historical time period corresponding to the fault end being the user end, c min Indicates the minimum discrete rate corresponding to the historical time period when the fault end is the network element end, v min Indicates the minimum discrete frequency corresponding to the historical time period when the fault end is the network element end. min() and max() represent the minimum and maximum values ​​respectively.

[0020] Optionally, the target network elements of each level associated with the delay abnormal network element are determined based on the resource tree information, and the target delay state sequence corresponding to the delay abnormal network element is determined based on the second network delay state of the target network element, including: determining the target network elements of each level associated with the delay abnormal network element based on the resource tree information, and sorting the target network elements and the delay abnormal network elements from high to low according to the structural hierarchy; for each target network element with a hierarchy higher than the delay abnormal network element, determining the target network element of the hierarchy of the delay abnormal network element under the target network element, and determining all target network elements. The ratio of the sum of the second network delay states of the hierarchical network elements to the number of target hierarchical network elements is the weighting coefficient of the target network element for the delay-abnormal network element; the ratio of the number of users whose delay detection data exceeds the preset normal range within the target time period to the total number of users in the target network system is determined as the discrete rate corresponding to the target time period; the second network delay states of the delay-abnormal network element and each target network element, the weighting coefficient of each target network element at a level higher than the delay-abnormal network element for the delay-abnormal network element, and the discrete rate are combined to form a target delay state sequence corresponding to the delay-abnormal network element.

[0021] Optionally, the network elements in the target network system include at least one of the following in descending order of hierarchy: a broadband access server, a switch, an optical line terminal, a passive optical network, and a gateway; the target delay state sequence also includes: second network delay states corresponding to different types of gateways, wherein the second network delay state corresponding to each type of gateway is the average value of the second network delay states of all gateways of that type.

[0022] Optionally, each delay state sequence in the fault database has a preset priority, and a target fault network element that matches the target delay state sequence is determined from the preset fault database, including: matching each delay state sequence in the fault database with the target delay state sequence in sequence according to the priority; when any delay state sequence matches the target delay state sequence, determining the target network element level corresponding to the delay state sequence, and determining the delay abnormal network element and the network element corresponding to the target network element level among the target network elements of each level as the target fault network element.

[0023] According to another aspect of the embodiment of the present application, a network delay tracing device is also provided, including: an acquisition module for acquiring resource tree information of a target network system, and acquiring delay detection data of all users in the target network system within a target time period, wherein the resource tree information is used to reflect the structural relationship of network elements at multiple levels in the target network system; a delay analysis module for determining a first network delay state of each user based on the delay detection data, and determining a second network delay state of each network element based on the first network delay state of all users under each network element; a first tracing module for determining a second network delay state of each network element based on the second network delay state of all users under each network element with abnormal delay; The network delay state determines the target fault end that causes the abnormal network delay of the delay-abnormal network element, wherein the target fault end includes: a user end or a network element end; a sequence generation module is used to determine the target network elements of each level associated with the delay-abnormal network element based on the resource tree information when the fault end is the network element end, and determine the target delay state sequence corresponding to the delay-abnormal network element based on the second network delay state of the target network element; a second tracing module is used to determine the target fault network element that matches the target delay state sequence from a preset fault database, wherein the fault database stores the mapping relationship between different fault network elements and different delay state sequences.

[0024] According to another aspect of an embodiment of the present application, an electronic device is further provided, comprising: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the above-mentioned network delay tracing method through the computer program.

[0025] In an embodiment of the present application, by obtaining the resource tree information of the target network system, the hierarchical structure and connection relationship between network elements at all levels are clarified, which is the basis for building the entire network model. At the same time, the delay detection data of all users in the target network system within the target time period are collected. These data come directly from the user end and are first-hand information for evaluating the quality of network services. The collected data includes the delay information of various levels of equipment such as user-side gateways, OLTs, switches, BASs, and fluctuations in user delays. The technical effect of this process is to establish a real-time status view at the network level and the user level, providing data support for subsequent analysis. By analyzing user latency data, each user's primary network latency status (i.e., whether the user's network latency is normal or abnormal) is determined. Based on the user's primary network latency status, the secondary network latency status of each network element is calculated. By aggregating user data, the health of each network element can be assessed, identifying those with poor latency. When a latency anomaly is detected for a network element, its secondary network latency status can be used to determine whether the anomaly originates from the network element or the user. For issues identified as network element-side, resource tree information is used to identify the target network elements at each level associated with the abnormal latency network element. The secondary network latency statuses of these network elements are collected, and a target latency status sequence corresponding to the abnormal latency network element is constructed. A pre-set fault database is then used to search for target faulty network elements that match this sequence. This database stores mappings between faulty network elements at different levels and different latency status sequences. This matching allows rapid locating of the specific network element (e.g., switch, OLT, BAS) that has experienced a fault. The effect of this technology is that it utilizes historical data collected and analyzed in advance, and through an intelligent algorithm of sequence matching, it can quickly locate the abnormal delay phenomenon from the faulty equipment, thereby improving the speed and accuracy of problem solving, and thus solving the technical problem of difficulty in accurately tracing the network elements or devices that cause delays in network operation and maintenance scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] 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:

[0027] Figure 1 This is a flow chart of an optional network delay tracing method according to an embodiment of the present application;

[0028] Figure 2 This is a schematic structural diagram of an optional network delay tracing device according to an embodiment of the present application;

[0029] Figure 3 is a schematic diagram of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0031] It should be noted that the terms "first", "second", etc. in the specification, claims, and drawings of the present application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. 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 variations thereof 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.

[0032] Example 1

[0033] According to an embodiment of the present application, a network delay tracing method 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.

[0034] Figure 1 FIG. 1 is a flow chart of a network delay tracing method provided in accordance with an embodiment of the present application, such as Figure 1 As shown, the method includes the following steps:

[0035] Step S102: Obtain resource tree information of the target network system and obtain latency detection data of all users in the target network system during a target time period, wherein the resource tree information is used to reflect the structural relationship of network elements at multiple levels in the target network system;

[0036] Step S104: determining a first network delay state of each user based on the delay detection data, and determining a second network delay state of each network element based on the first network delay states of all users connected to each network element;

[0037] Step S106, determining a target fault end causing the abnormal network delay of the abnormal network element according to the second network delay state of the abnormal network element, wherein the target fault end includes: a user end or a network element end;

[0038] Step S108: When the fault end is a network element end, target network elements at each level associated with the network element with abnormal delay are determined based on the resource tree information, and a target delay state sequence corresponding to the network element with abnormal delay is determined based on the second network delay state of the target network element.

[0039] Step S110 : determining a target faulty network element that matches a target delay state sequence from a preset fault database, wherein the fault database stores mapping relationships between faulty network elements at different levels and different delay state sequences.

[0040] The following describes the steps of the network delay tracing method in conjunction with a specific implementation process.

[0041] Obtain resource tree information of the target network system and obtain delay detection data of all users in the target network system within a target time period, wherein the resource tree information is used to reflect the structural relationship of network elements at multiple levels in the target network system.

[0042] Resource tree information is a graph that reflects the hierarchical structure and connectivity of network devices. For example, the resource tree includes the structural relationships and hierarchical information of various layers of equipment, from the user-side gateway to the network side, such as OLTs (Optical Line Terminals), switches, and BASs (Broadband Access Servers). The resource tree provides a structural framework for latency quality assessment and traceability, enabling algorithms to perform hierarchical latency quality assessments and locate potential vulnerabilities along the resource tree path. Resource tree information is acquired to accurately identify each layer and device in the network, facilitating subsequent determination of which network-side device is responsible for latency anomalies in latency measurement data. Constructing a resource tree involves the use of a network asset management system. Through a network resource database or corresponding resource management platform, information such as the device list, device type, and inter-device connectivity within the target network system is obtained. This information is organized into a tree structure, forming the resource tree. Each node represents a network element, and the connections between nodes represent the physical or logical connections between network elements.

[0043] Latency measurement data can be obtained by using a probe system to perform regular ping tests on user-side devices (such as optical broadband gateways) within the target network system. Typically, the probe system monitors large user groups at a high frequency, for example, performing a ping test on each user every two hours, sending 10 data packets per test, to collect extensive and comprehensive latency information. Latency data is fundamental to evaluating network latency quality. By analyzing this data, it is possible to identify which users and periods experience latency degradation, and thus determine the network's latency issues. The frequency and breadth of data collection (i.e., the user coverage) are critical, as only a sufficient number of samples and sufficiently frequent testing can accurately reflect the true network status, especially for intermittent or hidden latency issues.

[0044] After obtaining the above information and data, the first network delay status of each user is determined according to the delay detection data, and the second network delay status of each network element is determined according to the first network delay status of all users connected to each network element.

[0045] As an optional implementation, determining the first network delay state of each user based on the delay detection data can be performed in the following manner:

[0046] For each user, the user's first network delay state is determined according to the following formula:

[0047]

[0048] In the formula, i represents the i-th day, t1 represents the number of days in which all the user's delay detection data are within the preset normal range, t2 represents the number of days in which the user's delay detection data exceeds the preset normal range, and t s =t1+t2, indicating the total number of days in the target time period, Φ(1)=1, indicating that network delay has an impact on user perception, Φ(0)=0, indicating that network delay has no impact on user perception, and f(t) represents the user’s first network delay state in the target time period.

[0049] The above formula can be derived as follows:

[0050] The probe system collects ping data from a single user every two hours to evaluate the user's latency quality. The user latency quality evaluation model is calculated using the following formula:

[0051]

[0052] Where f(x)∈(0,1) represents the user's delay quality evaluation index, that is, the first network delay state, 1 represents the best quality, x(Δt) represents the user's single ping delay value, represents the normalization processing of the delay data, Φ(x)∈(0,1) represents the perception impact factor corresponding to the delay value, which presents a normal distribution, 1 represents no impact on perception, and n represents the total number of user tests.

[0053] To more accurately assess latency quality, the user latency value set {x} is decomposed into two parts: a normal interval, where latency values ​​are less than a discrete threshold (e.g., a local network latency discrete threshold = 15ms), denoted as {x(Φ(1))}; and an abnormal interval, where latency values ​​are greater than or equal to the discrete threshold, denoted as {x(Φ(0))}. The decomposed characteristics are: latency in the normal interval is mostly constant and has no impact on user perception, Φ(x)≈1; latency in the abnormal interval is pseudo-randomly distributed within a certain range, which affects user perception, Φ(x)≈0. Based on actual observations and analysis, two important propositions are proposed: f(x) is insensitive to the number of tests and anomalies within a day, but only to whether an anomaly exists within a day; f(x) is sensitive to whether an anomaly exists every day. This means that even if there are multiple anomalies in a day, f(x) will drop significantly as long as an anomaly exists. Therefore, the model focuses more on whether an anomaly occurs rather than the specific number of anomalies. Since the impact of delay degradation on user data is intermittent and continuous, and exhibits a time series on a daily basis, when there is enough sample data, the abnormal delay {x(Φ(0))} exhibits periodicity on a daily basis, forming an ordered series. Based on the above analysis, the delay value set {x} is decomposed into {x(Φ(1))} and {x(Φ(0))}, and Δt is merged on a daily basis, resulting in a simplified formula for the user delay quality indicator:

[0054]

[0055] Further simplification can be expressed as:

[0056]

[0057] This formula shows that the user's delay quality evaluation index f(t) mainly depends on whether there is abnormal delay within a day. If there is no abnormal delay within a day (that is, t2 = 0), then f(t) = 1, indicating the best delay quality. If there is abnormal delay, f(t) < 1, and f(t) gradually decreases as the number of abnormalities increases.

[0058] As an optional implementation manner, the second network delay state of each network element is determined based on the first network delay state of all users connected to each network element, which can be performed in the following manner:

[0059] For each network element, the second network delay state of the network element is determined according to the following formula:

[0060]

[0061] In the formula, j represents the jth user, m represents the total number of users connected to the network element, m1 represents the number of users whose delay detection data on the i-th day is within the preset normal range, and delay dev (t) represents the second network delay state of the network element within the target time period.

[0062] The above formula can be derived as follows:

[0063] Based on the user delay quality evaluation model, the network element delay quality evaluation model evaluates the overall delay quality of the network element by calculating the average delay index of all users connected to the network element. The specific formula is as follows:

[0064]

[0065] When t≥7, the amount of calculation is very large, especially when there are many users, and the real-time calculation delay dev The number of times may reach hundreds of millions of times. In order to compress the amount of calculation and improve the efficiency of calculation, the delay dev Delay to timing indicator dev (t) is converted so that the system can perform time-sharing calculations on a daily basis. By counting the user's delay indicators on a daily basis, the delay dev Convert to timing indicator delay dev (t), the specific formula is as follows:

[0066]

[0067] After obtaining the above delay status, the target fault end causing the abnormal network delay of the abnormal network element is determined according to the second network delay status of the abnormal network element. The target fault end includes: a user end or a network element end. The specific steps of this process can be as follows:

[0068] When the second network delay state is less than the first preset delay threshold, it is determined that the fault end causing the abnormal network delay of the abnormal network element is the network element end.

[0069] When the second network delay state is not less than a second preset delay threshold, it is determined that the faulty end causing the abnormal network delay of the abnormal delay network element is the user end, wherein the second preset delay threshold is greater than the first preset delay threshold.

[0070] As an optional implementation manner, the process of determining the first preset delay threshold and the second preset delay threshold may take the following steps:

[0071] Obtain multiple sets of delay detection data for all users in the target network system over multiple time periods, and determine the fault end corresponding to each historical time period. For each historical time period, determine that the ratio of the number of users whose delay detection data exceeds a preset normal range in the historical time period to the total number of users in the target network system is the discrete rate corresponding to the historical time period. For each day of each historical time period, determine that the ratio of the number of users whose delay detection data exceeds the preset normal range on that day to the number of users whose delay detection data exceeds the preset normal range in the historical time period is the discrete frequency corresponding to the historical time period. Determine the first preset delay threshold and the second preset delay threshold respectively according to the following formulas:

[0072] delay dev1 (c,v)=1-Φ(1)·c max ·v max

[0073] delay dev2 (c,v)=1-Φ(1)·c min ·v min

[0074] θ1=min(delay dev1 (c,v),delay dev2 (c,v))

[0075] θ2=max(delay dev1 (c,v),delay dev2 (c,v))

[0076] Where θ1 represents the first preset delay threshold, θ2 represents the second preset delay threshold, c represents the discrete rate, v represents the discrete frequency, Φ(1) = 1, indicating that network delay affects user perception, c max Indicates the maximum discrete rate corresponding to the historical time period when the fault end is the user end, v max Indicates the maximum discrete frequency of the historical time period corresponding to the fault end being the user end, c min Indicates the minimum discrete rate corresponding to the historical time period when the fault end is the network element end, v min Indicates the minimum discrete frequency corresponding to the historical time period when the fault end is the network element end. min() and max() represent the minimum and maximum values ​​respectively.

[0077] For example, based on the existing delay data set (4 million probes, ping test every 2 hours, and a data set formed over 30 days), simulation calculations yield the following results: User-side delay degradation: discrete rate: (0%, 41%), discrete frequency: (0%, 22%), Network-side delay degradation: discrete rate: (28%, 100%), discrete frequency: (19%, 100%). Substituting these values ​​into delaydev1 (c,v) and delay dev2 (c, v), get the boundary value of user-side and network-side degradation: User-side delay degradation: delay dev ∈(0.9098,1), network side delay degradation: delay dev ∈(0,0.9468), thus obtaining delay dev Judgment threshold: good: delay dev ≥0.95, excellent latency, no need to worry; poor: delay dev <0.90, there is a potential delay risk on the network side, intervention is required, observation area: 0.90≤delay dev <0.95, the latency quality is good, observation is recommended.

[0078] Delay dev That is, the D value is simplified according to the interval: 0: invalid value, 1: D < 0.9, 2: 0.9 ≤ D < 0.95, 3: D ≥ 0.95. The simplified formula is only valid for simple network structures, and complex network structures are polynomials.

[0079] After determining the target fault end, if the fault end is a network element end, determine the target network elements at each level associated with the abnormal delay network element based on the resource tree information, and determine the target delay state sequence corresponding to the abnormal delay network element based on the second network delay state of the target network element. This process can be carried out in the following steps:

[0080] Determine the target network elements at each level associated with the abnormal latency network element based on the resource tree information, and sort the target network elements and abnormal latency network elements from high to low according to the structural hierarchy;

[0081] For each target network element at a higher level than the delay abnormal network element, determine the target network element at the same level as the delay abnormal network element connected to the target network element, and determine the ratio of the sum of the second network delay states of all target network elements to the number of target network elements as the weighting coefficient of the target network element to the delay abnormal network element;

[0082] Determine the ratio of the number of users whose delay detection data exceeds a preset normal range within the target time period to the total number of users in the target network system as the discrete rate corresponding to the target time period;

[0083] The second network delay status of the delay abnormal network element and each target network element, the weighted coefficient of each target network element with a higher level than the delay abnormal network element for the delay abnormal network element, and the discrete rate are combined to form a target delay status sequence corresponding to the delay abnormal network element.

[0084] Among them, as an optional implementation method, the network elements in the target network system include at least one of the following in descending order of hierarchy: broadband access server, switch, optical line terminal, passive optical network, gateway; the target delay state sequence also includes: second network delay states corresponding to different types of gateways, wherein the second network delay state corresponding to each type of gateway is the average value of the second network delay states of all gateways of that type.

[0085] The following example uses a target network system including a broadband access server, a switch, an optical line terminal, a passive optical network, and a gateway. For example, the resource tree path library is used to calculate the second network delay state D(T n ), the specific steps are as follows:

[0086] For the metropolitan area network, the target network elements and the network elements with abnormal latency are sorted from high to low according to the structural hierarchy as follows: T3, T2, T1, T0 = BAS, SW, OLT, GATE;

[0087] For all resource tree paths, a delay path sequence group is formed under the network [{T n}];

[0088] For the same device T k , the subsequence group where it is located satisfies the conditions: Among them, m k-1 T k All T included k-1 The number of D(T k ) and all D(T k-1 ) has a weighted relationship, so the sequence group [{D(T n )}] performs iterative calculations and expands into two groups of sequences: one is the original data, and the other is each level node T n D(T k ) weighted coefficient F n ,[{D(T n )}]→[{D(T n )}]*[{F n (T k )}]; the target delay state sequence corresponding to the delay abnormal network element is:

[0089]

[0090] Considering the overall impact of gateway models and versions on latency, it is necessary to decompose D(T0) by mainstream manufacturers:

[0091] D(T0)→D(T 0x )={D(T 0h ),D(T 0z),D(T 0f ),D(T 0q )}

[0092] Adding the discrete rate C of the substitution factor of the time series characteristics, we can obtain the target delay state sequence for traceability calculation:

[0093]

[0094] After obtaining the target delay state sequence, a target faulty network element that matches the target delay state sequence is determined from a preset fault database, wherein the fault database stores mapping relationships between faulty network elements at different levels and different delay state sequences. This process may include the following steps:

[0095] Each delay state sequence in the fault database is matched with the target delay state sequence in sequence according to priority; when any delay state sequence matches the target delay state sequence, the target network element level corresponding to the delay state sequence is determined, and the network element with abnormal delay and the network element corresponding to the target network element level in the target network elements of each level are determined as the target fault network element.

[0096] For the OLT (Optical Line Terminal) optical broadband metropolitan area network, a total of 36 sets of feature sequences were constructed, that is, there are 36 delay state sequences in the fault database, involving 8 types of resource tree nodes: BAS (Broadband Access Server) (uplink), switch (uplink), switch, switch (OLT), OLT (uplink), OLT (PON (Passive Optical Network)), PON (gateway), and manufacturer-specific model network.

[0097] Feature sequence of a certain manufacturer's gateway (partial):

[0098] Feature 1, priority p=1: {P(T 0f )}={D(T 0h )=3,D(T 0z )=3,D(T 0f )=1};

[0099] Feature 2, priority p=1: {P(T 0f )}={D(T 0h )=3,D(T 0z )=0,D(T 0f )=1}.

[0100] The characteristic sequence of the vendor gateway is the simplest because the weighting coefficient Fn of the resource tree network element to T1 (ie, OLT) does not include the gateway.

[0101] The characteristic sequence of BAS upper link (part):

[0102] Feature 1, priority p=1:

[0103] {P(T3)}={D(T3)=1,{D(T 0h )=1,D(T 0z )=0,D(T 0f )=1},F3(T1)=1},C>0.8};

[0104] Feature 2, priority p=1:

[0105] {P(T3)}={D(T3)=1,{D(T 0h )=1,D(T 0z )=1,D(T 0f )=0},F3(T1)=1},C>0.8};

[0106] Feature 3, priority p=1:

[0107] {P(T3)}={D(T3)=1,{D(T 0h )=1,D(T 0z )=0,D(T 0f )=1},F3(T1)=1},C>0.8}.

[0108] The acquired BAS feature sequence includes the judgment condition of the gateway subset and is mutually exclusive with the gateway feature sequence. All BAS priorities are the same as the gateway priority, that is, p=1.

[0109] Switch characteristic sequence (partial):

[0110] Feature 1, priority p=2:{P(T2)}={D(T2)=1,{F 2x (T1)=1,F 2z (T1)>1},C>0.8};

[0111] Feature 2, priority p=2:{P(T2)}={D(T2)≠1,{F 2x (T1)=1,F 2z (T1)=1},C>0.8};

[0112] Feature 3, priority p=2:{P(T2)}={F 2x (T1)=1,C>0.8}.

[0113] The calculated switch feature sequence is relatively complex because the switch resource path structure is relatively complex and the weighting coefficient F n Decompose.

[0114] OLT characteristic sequence (part):

[0115] Feature 1, priority p=2:{P(T1)}={{F 2x (T1)>1,F 2z (T1)>1},0.5 <c>0.8};

[0116] Feature 2, priority p=2: {P(T1)}={{(T1)=1}, C<0.5}.

[0117] In an embodiment of the present application, by obtaining the resource tree information of the target network system, the hierarchical structure and connection relationship between network elements at all levels are clarified, which is the basis for building the entire network model. At the same time, the delay detection data of all users in the target network system within the target time period are collected. These data come directly from the user end and are first-hand information for evaluating the quality of network services. The collected data includes the delay information of various levels of equipment such as user-side gateways, OLTs, switches, BASs, and fluctuations in user delays. The technical effect of this process is to establish a real-time status view at the network level and the user level, providing data support for subsequent analysis. By analyzing user latency data, each user's primary network latency status (i.e., whether the user's network latency is normal or abnormal) is determined. Based on the user's primary network latency status, the secondary network latency status of each network element is calculated. By aggregating user data, the health of each network element can be assessed, identifying those with poor latency. When a latency anomaly is detected for a network element, its secondary network latency status can be used to determine whether the anomaly originates from the network element or the user. For issues identified as network element-side, resource tree information is used to identify the target network elements at each level associated with the abnormal latency network element. The secondary network latency statuses of these network elements are collected, and a target latency status sequence corresponding to the abnormal latency network element is constructed. A pre-set fault database is then used to search for target faulty network elements that match this sequence. This database stores mappings between faulty network elements at different levels and different latency status sequences. This matching allows rapid locating of the specific network element (e.g., switch, OLT, BAS) that has experienced a fault. The effect of this technology is that it utilizes historical data collected and analyzed in advance, and through an intelligent algorithm of sequence matching, it can quickly locate the abnormal delay phenomenon from the faulty equipment, thereby improving the speed and accuracy of problem solving, and thus solving the technical problem of difficulty in accurately tracing the network elements or devices that cause delays in network operation and maintenance scenarios.

[0118] Example 2

[0119] According to an embodiment of the present application, a network delay tracing device for implementing the network delay tracing method in embodiment 1 is also provided. Figure 2 As shown, the network delay tracing device includes at least: an acquisition module 21, a delay analysis module 22, a first tracing module 23, a sequence generation module 34, and a second tracing module 25, wherein:

[0120] An acquisition module 21 is configured to acquire resource tree information of a target network system and latency detection data of all users in the target network system during a target time period, wherein the resource tree information is used to reflect the structural relationship of network elements at multiple levels in the target network system;

[0121] The delay analysis module 22 is configured to determine a first network delay state of each user based on the delay detection data, and determine a second network delay state of each network element based on the first network delay states of all users connected to each network element;

[0122] The first tracing module 23 is configured to determine a target fault end causing the abnormal network delay of the abnormal network element according to the second network delay state of the abnormal network element, wherein the target fault end includes: a user end or a network element end;

[0123] A sequence generation module 24 is configured to determine, when the fault end is a network element end, target network elements at each level associated with the network element with abnormal delay based on the resource tree information, and determine a target delay state sequence corresponding to the network element with abnormal delay based on the second network delay state of the target network element;

[0124] The second tracing module 25 is configured to determine a target faulty network element that matches the target delay state sequence from a preset fault database, wherein the fault database stores mapping relationships between different faulty network elements and different delay state sequences.

[0125] The following describes the functions of each module of the network delay tracing device in conjunction with a specific implementation process.

[0126] The acquisition module acquires resource tree information of the target network system and acquires delay detection data of all users in the target network system within a target time period, wherein the resource tree information is used to reflect the structural relationship of network elements at multiple levels in the target network system.

[0127] After obtaining the above information and data, the delay analysis module determines the first network delay status of each user based on the delay detection data, and determines the second network delay status of each network element based on the first network delay status of all users connected to each network element.

[0128] As an optional implementation, determining the first network delay state of each user based on the delay detection data can be performed in the following manner:

[0129] For each user, the user's first network delay state is determined according to the following formula:

[0130]

[0131] In the formula, i represents the i-th day, t1 represents the number of days in which all the user's delay detection data are within the preset normal range, t2 represents the number of days in which the user's delay detection data exceeds the preset normal range, and t s =t1+t2, indicating the total number of days in the target time period, Φ(1)=1, indicating that network delay has an impact on user perception, Φ(0)=0, indicating that network delay has no impact on user perception, and f(t) represents the user’s first network delay state in the target time period.

[0132] As an optional implementation manner, the second network delay state of each network element is determined based on the first network delay state of all users connected to each network element, which can be performed in the following manner:

[0133] For each network element, the second network delay state of the network element is determined according to the following formula:

[0134]

[0135] In the formula, j represents the jth user, m represents the total number of users connected to the network element, m1 represents the number of users whose delay detection data on the i-th day is within the preset normal range, and delay dev (t) represents the second network delay state of the network element within the target time period.

[0136] After obtaining the above delay status, the first tracing module determines the target fault end that causes the abnormal network delay of the abnormal network element based on the second network delay status of the abnormal network element. The target fault end includes: a user end or a network element end. The specific steps of this process can be as follows:

[0137] When the second network delay state is less than the first preset delay threshold, it is determined that the fault end causing the abnormal network delay of the abnormal network element is the network element end.

[0138] When the second network delay state is not less than a second preset delay threshold, it is determined that the faulty end causing the abnormal network delay of the abnormal delay network element is the user end, wherein the second preset delay threshold is greater than the first preset delay threshold.

[0139] As an optional implementation manner, the process of determining the first preset delay threshold and the second preset delay threshold may take the following steps:

[0140] Obtain multiple sets of delay detection data for all users in the target network system over multiple time periods, and determine the faulty end corresponding to each historical time period;

[0141] For each historical time period, the ratio of the number of users whose delay detection data exceeds a preset normal range within the historical time period to the total number of users in the target network system is determined as the discrete rate corresponding to the historical time period;

[0142] For each day of each historical time period, determine the ratio of the number of users whose latency detection data exceeds the preset normal range on that day to the number of users whose latency detection data exceeds the preset normal range in the historical time period as the discrete frequency corresponding to the historical time period;

[0143] The first preset delay threshold and the second preset delay threshold are determined according to the following formulas:

[0144] delay dev1 (c,v)=1-Φ(1)·c max ·v max

[0145] delay dev2 (c,v)=1-Φ(1)·c min ·v min

[0146] θ1=min(delay dev1 (c,v),delay dev2 (c,v))

[0147] θ2=max(delay dev1 (c,v),delay dev2 (c,v))

[0148] Where θ1 represents the first preset delay threshold, θ2 represents the second preset delay threshold, c represents the discrete rate, v represents the discrete frequency, Φ(1) = 1, indicating that network delay affects user perception, c max Indicates the maximum discrete rate corresponding to the historical time period when the fault end is the user end, v max Indicates the maximum discrete frequency of the historical time period corresponding to the fault end being the user end, c min Indicates the minimum discrete rate corresponding to the historical time period when the fault end is the network element end, v min Indicates the minimum discrete frequency corresponding to the historical time period when the fault end is the network element end. min() and max() represent the minimum and maximum values ​​respectively.

[0149] After determining the target fault end, if the fault end is a network element end, the sequence generation module determines the target network elements at each level associated with the delay abnormal network element based on the resource tree information, and determines the target delay state sequence corresponding to the delay abnormal network element based on the second network delay state of the target network element. This process can be carried out in the following steps:

[0150] Determine the target network elements at each level associated with the abnormal latency network element based on the resource tree information, and sort the target network elements and abnormal latency network elements from high to low according to the structural hierarchy;

[0151] For each target network element at a higher level than the delay abnormal network element, determine the target network element at the same level as the delay abnormal network element connected to the target network element, and determine the ratio of the sum of the second network delay states of all target network elements to the number of target network elements as the weighting coefficient of the target network element to the delay abnormal network element;

[0152] Determine the ratio of the number of users whose delay detection data exceeds a preset normal range within the target time period to the total number of users in the target network system as the discrete rate corresponding to the target time period;

[0153] The second network delay status of the delay abnormal network element and each target network element, the weighted coefficient of each target network element with a higher level than the delay abnormal network element for the delay abnormal network element, and the discrete rate are combined to form a target delay status sequence corresponding to the delay abnormal network element.

[0154] Among them, as an optional implementation method, the network elements in the target network system include at least one of the following in descending order of hierarchy: broadband access server, switch, optical line terminal, passive optical network, gateway; the target delay state sequence also includes: second network delay states corresponding to different types of gateways, wherein the second network delay state corresponding to each type of gateway is the average value of the second network delay states of all gateways of that type.

[0155] After obtaining the target delay state sequence, the second tracing module determines the target faulty network element that matches the target delay state sequence from a preset fault database. The fault database stores mappings between faulty network elements at different levels and different delay state sequences. This process may include the following steps:

[0156] Each delay state sequence in the fault database is matched with the target delay state sequence in sequence according to priority; when any delay state sequence matches the target delay state sequence, the target network element level corresponding to the delay state sequence is determined, and the network element with abnormal delay and the network element corresponding to the target network element level in the target network elements of each level are determined as the target fault network element.

[0157] It should be noted that each module in the network delay tracing device in the embodiment of the present application corresponds one-to-one to each implementation step of the network delay tracing method in Example 1. Since a detailed description has been given in Example 1, some details not reflected in this embodiment can be referred to Example 1 and will not be elaborated here.

[0158] Example 3

[0159] According to an embodiment of the present application, a computer program product is also provided, which includes a computer program, wherein when the computer program is executed by a processor, the network delay tracing method in Example 1 is implemented.

[0160] According to an embodiment of the present application, a non-volatile storage medium is also provided, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the network delay tracing method in Example 1 by running the computer program.

[0161] According to an embodiment of the present application, a processor is also provided, which is used to run a computer program, wherein the network delay tracing method in Example 1 is executed when the computer program is running.

[0162] According to an embodiment of the present application, an electronic device is also provided, which includes: a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to execute the network delay tracing method in Example 1 through the computer program.

[0163] Specifically, when the computer program is run, the following steps are executed: obtaining resource tree information of a target network system and obtaining delay detection data of all users in the target network system within a target time period, wherein the resource tree information is used to reflect the structural relationship of network elements at multiple levels in the target network system; determining a first network delay state of each user based on the delay detection data, and determining a second network delay state of each network element based on the first network delay states of all users connected to each network element; determining a target fault end that causes the network element with abnormal delay to generate abnormal network delay based on the second network delay state of the network element with abnormal delay, wherein the target fault end includes: a user end or a network element end; when the fault end is a network element end, determining target network elements at each level associated with the network element with abnormal delay based on the resource tree information, and determining a target delay state sequence corresponding to the network element with abnormal delay based on the second network delay state of the target network element; and determining a target fault network element that matches the target delay state sequence from a preset fault database, wherein the fault database stores a mapping relationship between fault network elements at different levels and different delay state sequences.

[0164] As an optional implementation, the electronic device may be in the form of a mobile terminal, a computer terminal or a similar computing device. Figure 3 The figure shows a hardware structure block diagram of an electronic device for implementing a network delay tracing method. Figure 3 As shown, the electronic device 30 may include one or more (illustrated as 302a, 302b, ..., 302n in the figure) processors 302 (the processor 302 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 304 for storing data, and a transmission device 306 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 3 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 3 More or fewer components than shown, or with Figure 3 Different configurations shown.

[0165] It should be noted that the one or more processors 302 and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry." The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuitry may be a single, independent processing module, or may be fully or partially integrated into any of the other components of the electronic device 30. As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0166] The memory 304 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the network delay tracing method in the embodiment of the present application. The processor 302 executes various functional applications and data processing by running the software programs and modules stored in the memory 304, that is, implementing the vulnerability detection method of the above-mentioned application. The memory 304 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 304 may further include a memory remotely located relative to the processor 302, and these remote memories may be connected to the electronic device 30 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0167] The transmission device 306 is used to receive or send data via a network. Specific examples of the aforementioned network may include a wireless network provided by the communications provider of the electronic device 30. In one embodiment, the transmission device 306 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In one embodiment, the transmission device 306 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0168] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the electronic device 30 .

[0169] The serial numbers of the above embodiments are for description only and do not represent the advantages or disadvantages of the embodiments.

[0170] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0171] 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 exemplary. For example, the division of units can be a logical function division. In actual implementation, there may be other division methods, such as 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.

[0172] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected to achieve the purpose of the present embodiment according to actual needs.

[0173] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0174] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0175] The above is only a preferred embodiment 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.< / c>

Claims

1. A network delay tracing method, characterized in that: include: Acquire resource tree information of a target network system, and acquire delay detection data of all users in the target network system within a target time period, wherein the resource tree information is used to reflect the structural relationship of network elements at multiple levels in the target network system; Determine a first network delay state of each user according to the delay detection data, and determine a second network delay state of each network element according to the first network delay state of all users connected to each network element; Determine a target fault end that causes the abnormal network delay of the abnormal network element according to the second network delay state of the abnormal network element, wherein the target fault end includes: a user end or a network element end; In the case where the fault end is a network element end, determining target network elements of each level associated with the network element with abnormal delay according to the resource tree information, and determining a target delay state sequence corresponding to the network element with abnormal delay according to the second network delay state of the target network element; A target faulty network element matching the target delay state sequence is determined from a preset fault database, wherein the fault database stores mapping relationships between faulty network elements at different levels and different delay state sequences.

2. The method according to claim 1, characterized in that Determining a first network delay state of each user according to the delay detection data includes: For each user, the first network delay state of the user is determined according to the following formula: Where i represents the i-th day, t1 represents the number of days in which all the delay detection data of the user are within the preset normal range, t2 represents the number of days in which the delay detection data of the user exceeds the preset normal range, and t s =t1+t2, indicating the total number of days in the target time period, Φ(1)=1, indicating that network delay has an impact on user perception, Φ(0)=0, indicating that network delay has no impact on user perception, and f(t) indicates the first network delay state of the user in the target time period.

3. The method according to claim 2, characterized in that Determining the second network delay state of each network element according to the first network delay state of all users connected to each network element includes: For each network element, the second network delay state of the network element is determined according to the following formula: In the formula, j represents the jth user, m represents the total number of users connected to the network element, m1 represents the number of users whose delay detection data on the ith day is within the preset normal range, and delay dev (t) represents the second network delay state of the network element within the target time period.

4. The method according to claim 1, characterized in that: Determining the fault end causing the abnormal network delay of the abnormal network element to generate abnormal network delay according to the second network delay state of the abnormal network element includes: When the second network delay state is less than the first preset delay threshold, determining that the fault end causing the abnormal network delay of the abnormal delay network element is the network element end; When the second network delay state is not less than a second preset delay threshold, it is determined that the faulty end causing the abnormal network delay of the abnormal delay network element is the user end, wherein the second preset delay threshold is greater than the first preset delay threshold.

5. The method according to claim 4, characterized in that The process of determining the first preset delay threshold and the second preset delay threshold includes: Acquire multiple groups of delay detection data of all users in the target network system in multiple time periods, and determine the fault end corresponding to each historical time period; For each historical time period, determining that the ratio of the number of users whose delay detection data exceeds a preset normal range in the historical time period to the total number of users in the target network system is a discrete rate corresponding to the historical time period; For each day of each historical time period, determine that the ratio of the number of users whose delay detection data exceeds the preset normal range on that day to the number of users whose delay detection data exceeds the preset normal range in the historical time period is the discrete frequency corresponding to the historical time period; The first preset delay threshold and the second preset delay threshold are determined according to the following formulas: delay dev1 (c,v)=1-Φ(1)·c max ·v max delay dev2 (c,v)=1-Φ(1)·c min ·v min θ1=min(delay dev1 (c,v),delay dev2 (c,v)) θ2=max(delay dev1 (c,v),delay dev2 (c,v)) Wherein, θ1 represents the first preset delay threshold, θ2 represents the second preset delay threshold, c represents the discrete rate, v represents the discrete frequency, Φ(1)=1, indicating that the network delay affects the user perception, c max Indicates the maximum discrete rate corresponding to the historical time period when the fault end is the user end, v max Indicates the maximum discrete frequency of the historical time period corresponding to the faulty end being the user end, c min Indicates the minimum discrete rate corresponding to the historical time period when the fault end is the network element end, v min Indicates the minimum discrete frequency corresponding to the historical time period when the fault end is the network element end. min() and max() represent the minimum and maximum values ​​respectively.

6. The method according to claim 1, characterized in that Determining target network elements of each level associated with the abnormal delay network element according to the resource tree information, and determining a target delay state sequence corresponding to the abnormal delay network element according to the second network delay state of the target network element, including: Determine target network elements of each level associated with the abnormal delay network element according to the resource tree information, and sort the target network elements and the abnormal delay network elements from high to low according to the structural level; For each target network element whose level is higher than the network element with abnormal delay, determine the target network element at the level where the network element with abnormal delay is located under the target network element, and determine the ratio of the sum of the second network delay states of all the target network elements to the number of the target network elements as the weighting coefficient of the target network element to the network element with abnormal delay; Determine that the ratio of the number of users whose delay detection data exceeds a preset normal range within the target time period to the total number of users in the target network system is a discrete rate corresponding to the target time period; The second network delay state of the delay abnormal network element and each of the target network elements, the weighted coefficient of each target network element with a higher level than the delay abnormal network element for the delay abnormal network element, and the discrete rate are combined to form a target delay state sequence corresponding to the delay abnormal network element.

7. The method according to claim 6, characterized in that The network elements in the target network system include at least one of the following in descending order of hierarchy: a broadband access server, a switch, an optical line terminal, a passive optical network, and a gateway; The target delay state sequence also includes: second network delay states corresponding to different types of gateways, wherein the second network delay state corresponding to each type of gateway is an average value of the second network delay states of all gateways of that type.

8. The method according to claim 1, characterized in that Each delay state sequence in the fault database has a preset priority, and determining a target faulty network element matching the target delay state sequence from the preset fault database includes: Matching each delay state sequence in the fault database with the target delay state sequence in sequence according to the priority; When any delay state sequence matches the target delay state sequence, the target network element level corresponding to the delay state sequence is determined, and the network element corresponding to the target network element level among the abnormal delay network element and the target network elements at each level is determined as the target faulty network element.

9. A network delay tracing device, characterized in that: include: An acquisition module, used to acquire resource tree information of a target network system and acquire delay detection data of all users in the target network system within a target time period, wherein the resource tree information is used to reflect the structural relationship of network elements of multiple levels in the target network system; A delay analysis module, configured to determine a first network delay state of each user according to the delay detection data, and determine a second network delay state of each network element according to the first network delay state of all users connected to each network element; A first tracing module is used to determine a target fault end that causes the abnormal network delay of the abnormal network element according to the second network delay state of the abnormal network element, wherein the target fault end includes: a user end or a network element end; A sequence generation module, used for determining, when the fault end is a network element end, target network elements of each level associated with the delay abnormal network element according to the resource tree information, and determining a target delay state sequence corresponding to the delay abnormal network element according to the second network delay state of the target network element; The second tracing module is used to determine a target faulty network element that matches the target delay state sequence from a preset fault database, wherein the fault database stores a mapping relationship between different faulty network elements and different delay state sequences.

10. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the network delay tracing method according to any one of claims 1 to 8 through the computer program.

Images