Communication link fault detection method and device and electronic equipment

Abstract

The invention discloses a communication link fault detection method and device and electronic equipment. The method comprises the following steps: determining a node state matrix corresponding to a network element node in a first time step in a communication link; determining a state transition matrix corresponding to the network element node in the first time step; according to the node state matrix, the state transition matrix and a state success rate mapping matrix corresponding to the network element node, determining an end-to-end success rate corresponding to the communication link in the second time step, the state success rate mapping matrix being used for representing communication success rates of the network element node in different node states, and the state success rate mapping matrix being used for representing communication success rates of the network element node in different node states; the end-to-end success rate is used for representing the overall communication success probability of the communication link; and when the end-to-end success rate is lower than a preset success rate threshold, determining that the communication link has a fault. The technical problem that a communication network fault detection method in the prior art is poor in dynamic adaptability and lacks prediction capability is solved.

Description

Technical Field

[0001] The present application relates to the field of communication network technology, and in particular to a communication link fault detection method, device and electronic equipment. Background Art

[0002] With the continuous advancement of communication technology, communication networks are becoming increasingly large and complex. The number of network element nodes in the network has increased significantly, including base stations, switches, routers, core network equipment, and other types. These network element nodes are interconnected and work together to form a complex network system. As the network structure becomes more complex, the possibility of network failures and the difficulty of fault diagnosis also increase.

[0003] The fault detection and location methods in related technologies rely on fixed test item paths, cannot adapt to dynamic changes in network topology, have poor dynamic adaptability, and can only respond to faults that have already occurred. They lack predictive capabilities and cannot provide early warnings.

[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 communication link fault detection method, device, and electronic device to at least solve the technical problems in the related art of poor dynamic adaptability and lack of predictive capability of communication network fault detection methods.

[0006] According to one aspect of an embodiment of the present application, a communication link fault detection method is provided, including: determining a node state matrix corresponding to a network element node in a communication link at a first time step, wherein the node state matrix is ​​used to characterize the probability that the network element node is in different node states at the first time step; determining a state transition matrix corresponding to the network element node at the first time step, wherein the state transition matrix is ​​used to characterize the transition probability of the node state of the network element node from the first time step to the second time step, and the second time step is the next time step immediately adjacent to the first time step; determining an end-to-end success rate of the communication link corresponding to the second time step based on the node state matrix, the state transition matrix, and a state success rate mapping matrix corresponding to the network element node, wherein the state success rate mapping matrix is ​​used to characterize the communication success rate of the network element node in different node states, and the end-to-end success rate is used to characterize the probability of overall communication success of the communication link; when the end-to-end success rate is lower than a preset success rate threshold, it is determined that there is a fault in the communication link.

[0007] Optionally, the method also includes: using a software-defined network controller to detect traffic and path information in the network to obtain a communication link from a source terminal to a target terminal, wherein the communication link includes multiple network element nodes of different types; determining a node status indicator corresponding to each type of network element node, and determining a mapping relationship between different indicator values ​​of the node status indicator and different node states of the network element node; and determining a state success rate mapping matrix based on the mapping relationship.

[0008] Optionally, the method also includes: obtaining the index value of the node state index corresponding to the network element node after each time step, and determining the node state matrix of the network element node at each time step based on the index value; counting the state transition frequency of the network element node from one node state to another node state within a preset time window, wherein the preset time window includes at least one time step; calculating the transition probability between different node states based on the state transition frequency, and updating the state transition matrix based on the transition probability.

[0009] Optionally, determining the end-to-end success rate of the communication link corresponding to the second time step based on the node state matrix, the state transfer matrix, and the state success rate mapping matrix corresponding to the network element node includes: predicting the node state matrix corresponding to the network element node at the second time step based on the node state matrix and the state transfer matrix corresponding to the network element node at the first time step; determining the communication success rate corresponding to the network element node based on the predicted node state matrix and the state success rate mapping matrix corresponding to the second time step; determining the end-to-end success rate of the communication link corresponding to the second time step based on the communication success rate corresponding to each network element node in the communication link.

[0010] Optionally, the method also includes: determining the network element node where a fault occurs in the communication link by: determining the link node length of the communication link that is determined to have a fault; when the link node length is not greater than a preset node length, traversing each network element node in the communication link, determining whether each network element node has a fault, and when there is an abnormal transition in the state transfer matrix corresponding to the network element node, determining the network element node as the network element node where a fault occurs; when the link node length is greater than a preset node length, using a binary method to divide the communication link into multiple sub-link segments, and recursively processing the sub-link segments as new communication links until the faulty network element node is located.

[0011] Optionally, a bisection method is used to divide the communication link into multiple sub-link segments, and the sub-link segments are recursively processed as new communication links until the faulty network element node is located, including: dividing the communication link into a first sub-link segment and a second sub-link segment, and determining the end-to-end success rate corresponding to the first sub-link segment and the second sub-link segment respectively; taking the first sub-link segment and / or the second sub-link segment whose end-to-end success rate is less than a preset success rate threshold as a new communication link; iteratively repeating the above steps of dividing the sub-link segments, determining the end-to-end success rate of the sub-link segments, and comparing it with the preset success rate threshold until the link node length of the newly obtained communication link is no greater than the preset node length; traversing each network element node in the finally obtained communication link, determining whether each network element node has a fault, and determining the network element node as a faulty network element node if there is an abnormal transition in the state transfer matrix corresponding to the network element node.

[0012] Optionally, after determining the network element node where a fault occurs in the communication link, the method further includes: generating a fault work order based on the information of the located faulty network element node, and dispatching the fault work order to the terminal device of the maintenance personnel corresponding to the network element node; obtaining processing information for the fault work order returned by the terminal device, wherein the processing information includes at least one of the following: fault type, fault cause, and fault handling strategy; storing the node status data and processing information corresponding to the network element node in a knowledge base, wherein the node status data includes: characteristics of the state transition matrix corresponding to the network element node when a fault occurs.

[0013] According to another aspect of an embodiment of the present application, a communication link fault detection device is also provided, including: a state matrix determination module, used to determine the node state matrix corresponding to the network element node in the communication link at the first time step, wherein the node state matrix is ​​used to characterize the probability of the network element node being in different node states in the first time step; a transfer matrix determination module, used to determine the state transfer matrix corresponding to the network element node at the first time step, wherein the state transfer matrix is ​​used to characterize the transition probability of the node state of the network element node from the first time step to the second time step, and the second time step is the next time step immediately adjacent to the first time step; a success rate prediction module, used to determine the end-to-end success rate of the communication link corresponding to the second time step based on the node state matrix, the state transfer matrix, and the state success rate mapping matrix corresponding to the network element node, wherein the state success rate mapping matrix is ​​used to characterize the communication success rate of the network element node in different node states, and the end-to-end success rate is used to characterize the probability of overall communication success of the communication link; a fault node locating module, used to determine that there is a fault in the communication link when the end-to-end success rate is lower than a preset success rate threshold.

[0014] According to another aspect of the embodiments of the present application, an electronic device is provided, including: a memory and a processor, wherein the processor is configured to run a program stored in the memory, wherein the communication link failure detection 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 communication link failure detection 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 communication link failure detection method when executed by a processor.

[0017] In an embodiment of the present application, a node state matrix corresponding to a network element node in a communication link at a first time step is determined, wherein the node state matrix is ​​used to characterize the probability that the network element node is in different node states at the first time step; a state transition matrix corresponding to the network element node at the first time step is determined, wherein the state transition matrix is ​​used to characterize the transition probability of the node state of the network element node from the first time step to the second time step, and the second time step is the next time step immediately adjacent to the first time step; based on the node state matrix, the state transition matrix, and the state success rate mapping matrix corresponding to the network element node, an end-to-end success rate of the communication link corresponding to the second time step is determined, wherein the state success rate mapping matrix is ​​used to characterize the communication success rate of the network element node in different node states, and the end-to-end success rate is used to characterize the probability of overall communication success of the communication link; when the end-to-end success rate is lower than a preset success rate threshold, a method of determining that a fault exists in the communication link is adopted. By introducing a Markov chain model to predict and locate faults in the communication link, the adaptability in a dynamic network environment is improved, and the fault prediction and early warning capabilities are enhanced, thereby solving the technical problems of poor dynamic adaptability and lack of prediction capabilities of communication network fault detection methods in related technologies. 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 This is a hardware structure block diagram of a computer terminal (or electronic device) for implementing a method for detecting a communication link failure according to an embodiment of the present application;

[0020] Figure 2 This is a schematic diagram of a method flow for detecting a communication link failure according to an embodiment of the present application;

[0021] Figure 3 This is a schematic diagram of a method flow for predicting and locating network element node faults based on a Markov chain according to an embodiment of the present application;

[0022] Figure 4 It is a structural diagram of a communication link fault detection device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0023] 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.

[0024] 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 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 a sequence 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.

[0025] To facilitate those skilled in the art to better understand the embodiments of the present application, some technical terms or nouns involved in the embodiments of the present application are explained as follows:

[0026] End-to-end communication link: refers to the complete communication path from the source terminal to the target terminal, including but not limited to the following nodes: 1) Base station: wireless signal transceiver equipment (such as 5G gNB); 2) Access network: the network layer connecting the base station and the core network (such as NGRAN (5G Next Generation Radio Access Network)); 3) Core network element node: core network function entity (such as UPF, AMF, SMF); 4) Target terminal: communication receiving device (such as mobile phone, IoT (Internet of Things) device).

[0027] Network element node response success rate: The probability of a single network functional unit (such as UPF) successfully completing a service request within a specific time period, dynamically calculated based on performance indicators (CPU, memory, packet loss rate, etc.).

[0028] Markov chain: A random process model used to describe the transition pattern of network element node states (normal, overloaded, faulty), whose future state depends only on the current state.

[0029] State transition matrix: A matrix describing the state transition probability in a Markov chain, in the form of: P = [p ij ], where p ij represents the probability of transitioning from state i to state j.

[0030] With the continuous advancement of communication technology, communication networks are becoming increasingly large and complex. From traditional 2G and 3G networks to today's 4G, 5G, and even future 6G networks, the number of network element nodes has increased significantly, including base stations, switches, routers, core network equipment, and other types. These network element nodes are interconnected and work together to form a complex network system.

[0031] To achieve high-speed, low-latency communication services, 5G networks use massive multiple-input multiple-output (MIMO) technology and millimeter wave communication technology. This makes the network element nodes more diverse and the network architecture more complex, which also increases the possibility of network failures and the difficulty of fault diagnosis.

[0032] Failures in network element nodes can lead to interruptions and degradation of communication services, resulting in a poor user experience, such as dropped calls, slow data transmission, and video freezes. For industries heavily reliant on communication networks, such as finance, transportation, and healthcare, network element node failures can even lead to serious consequences, such as the inability to conduct financial transactions, uncontrolled traffic signals, and interrupted medical equipment communications, resulting in significant economic losses and social impact.

[0033] Related technologies locate nodes within the core network by analyzing the failure overlap rate and critical paths in call logs. However, these fault detection and location methods rely on fixed test paths, making them incapable of adapting to dynamic changes in network topology. Furthermore, they can only respond to existing faults, lacking predictive capabilities and providing early warning.

[0034] To address the above issues, the present application provides a solution in the following embodiments, enabling automated fault prediction and diagnosis. This reduces manual intervention and data analysis, thereby lowering operation and maintenance costs. Furthermore, timely and accurate fault prediction and diagnosis optimize network resource allocation, improve the overall efficiency of network operation and maintenance, ensure the stable operation of the communication network, and provide users with high-quality communication services. This is described in detail below.

[0035] According to an embodiment of the present application, a method embodiment for detecting a communication link failure 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.

[0036] 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 FIG1 shows a hardware structure block diagram of a computer terminal (or electronic device) for implementing a communication link failure detection method. Figure 1 As shown, the computer terminal 10 (or electronic device) may include one or more (illustrated as 102a, 102b, ..., 102n in the figure) 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 will 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 than shown, or with Figure 1 Different configurations shown.

[0037] 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 circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other components of the computer terminal 10 (or electronic device). 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).

[0038] 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 communication link fault detection 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, implementing the above-mentioned communication link fault detection method. 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 examples, the memory 104 may further include a memory remotely located 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.

[0039] The transmission device 106 is configured to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the communications provider of the computer terminal 10. In one embodiment, the transmission device 106 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 another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is configured to communicate with the Internet wirelessly.

[0040] 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).

[0041] In the above operating environment, the embodiment of the present application provides a communication link failure detection method. Figure 2 FIG. 1 is a schematic diagram of a method flow for detecting a communication link failure according to an embodiment of the present application. Figure 2 As shown, the method includes the following steps:

[0042] Step S202: determining a node state matrix corresponding to a network element node in the communication link at a first time step, wherein the node state matrix is ​​used to represent the probability of the network element node being in different node states at the first time step;

[0043] Step S204: determining a state transition matrix corresponding to the network element node at the first time step, wherein the state transition matrix is ​​used to represent the transition probability of the node state of the network element node from the first time step to the second time step, where the second time step is the next time step immediately following the first time step;

[0044] Step S206: Determine the end-to-end success rate of the communication link corresponding to the second time step based on the node state matrix, the state transition matrix, and the state success rate mapping matrix corresponding to the network element node, wherein the state success rate mapping matrix is ​​used to represent the communication success rate of the network element node in different node states, and the end-to-end success rate is used to represent the probability of overall communication success of the communication link;

[0045] Step S208: When the end-to-end success rate is lower than a preset success rate threshold, it is determined that a fault exists in the communication link.

[0046] Through the above steps, by introducing the Markov chain model to predict and locate faults in the communication link, the purpose of improving adaptability in dynamic network environments and enhancing fault prediction and early warning capabilities is achieved, thereby solving the technical problems of poor dynamic adaptability and lack of prediction capabilities of communication network fault detection methods in related technologies.

[0047] The following further introduces the communication link failure detection method in steps S202 to S208 of the embodiment of the present application.

[0048] Figure 3 FIG is a schematic diagram of a method flow for predicting and locating network element node faults based on a Markov chain according to an embodiment of the present application, such as Figure 3 As shown, the entire process can be divided into three phases. The first phase is model construction, which includes the path discovery and link modeling submodule, the network element node state modeling submodule, and the Markov chain state transition matrix construction submodule. The second phase is computational prediction, which includes the end-to-end success rate calculation submodule and the next time period success rate prediction submodule. The third phase is root cause location, which includes the faulty link determination submodule and the faulty network element node location submodule. In addition, the experience consolidation module serves both the second and third phases, and the system interface module provides management functions for all of these modules in a webpage format. The following describes the functions of each module and the execution process steps.

[0049] In an embodiment of the present application, a path discovery and link modeling module can be used to obtain communication links in real time, and a network element node status modeling module can be used to model the status of each network element node based on different indicators and form a corresponding status success rate mapping table. The specific steps are as follows.

[0050] In some embodiments of the present application, the method also includes the following steps: using a software-defined network controller to detect traffic and path information in the network to obtain a communication link from a source terminal to a target terminal, wherein the communication link includes multiple network element nodes of different types; determining the node status indicator corresponding to each type of network element node, and determining the mapping relationship between different indicator values ​​of the node status indicator and different node states of the network element node; and determining a state success rate mapping matrix based on the mapping relationship.

[0051] Specifically, an SDN (Software-Defined Networking) controller or other tools can be used to obtain communication path information in real time. In this embodiment, dynamic path updates (such as load balancing switching paths) are supported, and then the unique identifiers and types of all nodes in the path (such as base stations, UPF (User Plane Function), SMF (Session Management Function), AMF (Access and Mobility Management Function), etc.) are stored to form a list of simulated link nodes (i.e., communication links).

[0052] Then, we can collect existing communication network element node fault-related data sets, combine them with expert annotations of existing network alarm data, and form a comprehensive data set that includes various types of communication network element nodes, their fault types, and log descriptions. We can also complete the elimination of redundant data and the cleaning of abnormal data. The status of each network element node is based on the node status indicators such as packet loss rate, transmission delay, throughput, CPU usage, and memory occupancy, and a corresponding state success rate mapping table (matrix) is formed. For example, when modeling UPF, there are three node states for UPF network element nodes: S0-normal, S1-overload, and S2-fault. The mapping relationship between the indicator values ​​of the corresponding node status indicators is as follows:

[0053] S0: All indicators are within the baseline range, such as CPU < 70%, packet loss rate < 0.5%;

[0054] S1: Any indicator exceeds the threshold, such as CPU > 70% for 5 minutes or packet loss rate > 0.5%;

[0055] S2: Key business indicator anomalies, hardware failure, or indicator conflicts, etc.

[0056] Based on this mapping relationship, a state success rate mapping table can be formed as shown in the following table.

[0057] state Success rate S0 99％ S1 95％ S2 10％

[0058] Then we can get the state success rate mapping matrix

[0059] Afterwards, in the Markov chain state transition matrix construction submodule, the node state matrix and state transition matrix of each network element node can be determined, as follows.

[0060] In some embodiments of the present application, the method also includes: obtaining the index value of the node state index corresponding to the network element node after each time step, and determining the node state matrix of the network element node at each time step based on the index value; counting the state transition frequency of the network element node from one node state to another node state within a preset time window, wherein the preset time window includes at least one time step; calculating the transition probability between different node states based on the state transition frequency, and updating the state transition matrix based on the transition probability.

[0061] Specifically, the state probability of each network element node (i.e., the node state matrix) can be formed based on the collected indicator value data set of the node state indicator. For example, [0.95 0.05 0] indicates that the probability of the current network element node being in the S0 state is 95%, the probability of being in the S1 state is 5%, and the probability of being in the S2 state is 0;

[0062] In addition, a time slice (step) interval update method can be adopted to update a new state probability (i.e., node state matrix) using the indicator value data generated in the next time slice (step), and periodically generate a certain amount of state data of each network element node, that is, obtain the node state matrix data of the network element node for multiple time steps in the preset time window. Afterwards, the historical data can be used to statistically generate a state transition matrix, and update it after each time slice (step), that is, the state transition frequency of the network element node from one node state to another node state in the preset time window is counted, and the state transition matrix is ​​updated according to the transition probability. For example, the state transition matrix of the UPF is generated as shown below:

[0063]

[0064] After obtaining the node state matrix, state transition matrix, and state success rate mapping matrix corresponding to the network element node, the end-to-end success rate calculation submodule and the prediction of the success rate in the next time period submodule can be used to predict the end-to-end success rate of the communication link in the next time step (the second time step). The specific steps are as follows.

[0065] In some embodiments of the present application, determining the end-to-end success rate of the communication link corresponding to the second time step based on the node state matrix, the state transition matrix, and the state success rate mapping matrix corresponding to the network element node includes the following steps: predicting the node state matrix corresponding to the network element node at the second time step based on the node state matrix and the state transition matrix corresponding to the network element node at the first time step; determining the communication success rate corresponding to the network element node based on the predicted node state matrix and the state success rate mapping matrix corresponding to the second time step; determining the end-to-end success rate of the communication link corresponding to the second time step based on the communication success rate corresponding to each network element node in the communication link.

[0066] In the embodiment of the present application, the end-to-end success rate calculation submodule adopts a product model, and its calculation formula is: the total success rate of the communication link = the product of the success rates of all network element nodes. For example, P total (t) = P UPF (t)×P SMF (t)×….

[0067] The success rate of each network element node is calculated by multiplying its state probability matrix (i.e., node state matrix) by the state success rate mapping matrix. UPF Taking (t) as an example, assuming that the probability of the current UPF being in the S0 state is 95%, the probability of being in the S1 state is 5%, and the probability of being in the S2 state is 0, then:

[0068]

[0069] When determining the end-to-end success rate of the communication link corresponding to the second time step based on the node state matrix and state transfer matrix corresponding to the first time step, and the state success rate mapping matrix corresponding to the network element node, the node state matrix corresponding to the network element node at the second time step can be predicted by using the success rate prediction submodule in the next time period. Specifically, the node state matrix at the second time step can be predicted by using the node state matrix and state transfer matrix at the first time step, and then combined with the state success rate mapping matrix, the end-to-end success rate of the communication link at the second time step can be obtained, as shown in the following formula:

[0070] P UPF (t+k) = current node state matrix × state transition matrix × state success rate mapping matrix

[0071] For example, the probability that the current UPF is in the state S0 is 95%, the probability that it is in the state S1 is 5%, and the probability that it is in the state S2 is 0, then That is, the success rate of the UPF node in the next time slice (the second time step) is 97.66%.

[0072] The total success rate of predicting the future time slice k based on the Markov chain is: total (t+k)=∏P 节点 (t+k).

[0073] After determining the end-to-end success rate of the communication link corresponding to the second time step, the fault link judgment submodule can be used to compare the size relationship between the end-to-end success rate and the preset success rate threshold x. If the end-to-end success rate is less than this threshold, it is determined that the communication link has a fault.

[0074] Furthermore, if it is determined that a communication link has a fault, the faulty network element node location submodule can be used to locate the faulty network element node in the communication link by reviewing the state transition matrix of each network element node. The specific steps are as follows.

[0075] In some embodiments of the present application, the method also includes the following steps: determining the network element node where a fault occurs in the communication link by: determining the link node length of the communication link that is determined to have a fault; when the link node length is not greater than the preset node length, traversing each network element node in the communication link, judging whether each network element node has a fault, and when there is an abnormal transition in the state transfer matrix corresponding to the network element node, determining the network element node as the network element node where a fault occurs; when the link node length is greater than the preset node length, using a binary method to divide the communication link into multiple sub-link segments, and recursively processing the sub-link segments as new communication links until the faulty network element node is located.

[0076] Specifically, by reviewing the state transition matrix of each node, network element nodes with significant changes (i.e., network element nodes with abnormal transitions in the state transition matrix) are located and reported back to the operations and maintenance personnel. Abnormal transitions may include, but are not limited to, a state jump from normal (S0) to faulty (S2), a sudden and significant change in the state transition probability, or a state transition probability exceeding a preset threshold. If the link is too long and there are too many nodes, a binary search is performed to calculate the end-to-end link success rate for the first half of the nodes and the end-to-end link success rate for the second half of the nodes. The problematic nodes are identified and the binary search is repeated or the state transition matrix is ​​reviewed until the faulty network element node is located. The specific steps are as follows.

[0077] In some embodiments of the present application, a bisection method is used to divide a communication link into multiple sub-link segments, and the sub-link segments are recursively processed as new communication links until the faulty network element node is located, including the following steps: dividing the communication link into a first sub-link segment and a second sub-link segment, and determining the end-to-end success rate corresponding to the first sub-link segment and the second sub-link segment respectively; taking the first sub-link segment and / or the second sub-link segment whose end-to-end success rate is less than a preset success rate threshold as a new communication link; iteratively repeating the above steps of dividing the sub-link segments, determining the end-to-end success rate of the sub-link segments, and comparing them with the preset success rate threshold until the link node length of the newly obtained communication link is no greater than the preset node length; traversing each network element node in the finally obtained communication link, determining whether each network element node has a fault, and determining the network element node as a faulty network element node if there is an abnormal transition in the state transfer matrix corresponding to the network element node.

[0078] The specific algorithm flow of the dichotomy method is as follows:

[0079] Step 1: node sequence preprocessing;

[0080] 1.1 If len(current_nodes)≤5 (preset node length), review the state transition matrix of each node, find the network element node with abnormal transition and return it;

[0081] 1.2 If len(current_nodes)>5, go to step 2.

[0082] Step 2: Link segmentation and success rate calculation;

[0083] 2.1 Split node sequence;

[0084] mid=len(current_nodes) / / 2;

[0085] front_segment=current_nodes[:mid];

[0086] back_segment=current_nodes[mid:];

[0087] 2.2 Calculate the prediction success rate of each segment;

[0088] P front =∏ n∈front_segment P n (t);

[0089] P back =∏ n∈back_segment P n (t).

[0090] Step 3: Fault determination;

[0091] 3.1 If P front <P back , fault segment = front_segment;

[0092] 3.2 Otherwise: fault segment = back_segment;

[0093] 3.3 Recursively call step 1 with the fault segment as input;

[0094] 3.4 Return to the faulty network element node and output it.

[0095] In addition, the experience consolidation module can also record fault location results and repair work order data to build a "fault mode-state transition characteristics-repair solution" knowledge base; through incremental learning, it optimizes the state transition matrix parameters to improve the prediction accuracy of similar faults, as shown below.

[0096] In some embodiments of the present application, after determining the network element node where a fault occurs in the communication link, the method further includes the following steps: generating a fault work order based on the information of the located faulty network element node, and dispatching the fault work order to the terminal device of the maintenance personnel corresponding to the network element node; obtaining processing information for the fault work order returned by the terminal device, wherein the processing information includes at least one of the following: fault type, fault cause, and fault handling strategy; storing the node status data and processing information corresponding to the network element node in a knowledge base, wherein the node status data includes: characteristics of the state transition matrix corresponding to the network element node when a fault occurs.

[0097] Specifically, after the real-time fault processing module and the fault prediction module provide fault diagnosis results and optimization measures, operators, drawing on their operational experience, repair the network element node fault. The data involved in this entire process (i.e., fault link discovery → real-time fault processing → operator repair completion or fault prediction → operator repair) can be recorded as a fault repair work order using the experience consolidation module. Employees with specialized knowledge of communications networks can correct any errors in these work order data, record the erroneous data details, and add them to the knowledge base. This knowledge base is continuously updated through iterative optimization, improving the system's processing efficiency and accuracy when similar faults occur in the future.

[0098] In addition, in this embodiment, the model parameters of the fault prediction and diagnosis model running in the gateway device, the network element node status library parameters, and the fault log overview and processing suggestions at the time of the fault will all be displayed in the system interface module, and the progress of the entire diagnostic process will also be displayed in the system interface to facilitate the operator to determine the operation sequence.

[0099] In order to enable those skilled in the art to better understand the embodiments of the present application, the above-mentioned communication link failure detection method is illustrated below by way of example.

[0100] In the video call scenario between terminal A and terminal B, the path discovery and link modeling unit uses the SDN controller to obtain the real-time communication link as follows: terminal A→base station 1→UPF_1→SMF→AMF→AUSF (Authentication Server Function)→PCF (Policy and Charging Function)→NSSF (Network Slice Selection Function)→UPF_2→DN (Data Network)→terminal B.

[0101] The unique identifiers and types of all nodes in the storage path are formed to form a simulated link node list {terminal A, base station 1, UPF_1, SMF, AMF, AUSF, PCF, NSSF, UPF_2, DN, terminal B}.

[0102] For each type of network element node in the communication link, in the network element node state modeling unit, the state of each type of network element node is modeled according to different indicators and a corresponding state success rate mapping table (matrix) is formed, as shown below.

[0103] 1) Base Station:

[0104] The mapping relationship between the node status corresponding to the network element node and the indicator value of the node status indicator is as follows:

[0105] S0: PRB (Physical Resource Block) utilization <75%, RRC connection number <500, packet loss rate <0.1%;

[0106] S1: PRB utilization rate 75% to 90% or the number of RRC (Radio Resource Control) connections > 500 or the packet loss rate 0.1% to 1%;

[0107] S2: The indicator is obviously abnormal, there is a hardware failure, or the indicator conflicts, etc.

[0108] The status success rate mapping table is as follows:

[0109] state Success rate S0 99％ S1 95％ S2 10％

[0110] 2)UPF:

[0111] The mapping relationship between the node status corresponding to the network element node and the indicator value of the node status indicator is as follows:

[0112] S0: CPU usage < 70%, throughput < 80% bandwidth capacity, number of sessions < 80% of design capacity;

[0113] S1: CPU utilization 70% to 90% or throughput > 80% of bandwidth capacity or number of sessions > 80% of design capacity;

[0114] S2: The indicator is obviously abnormal, there is a hardware failure, or the indicator conflicts, etc.

[0115] The status success rate mapping table is as follows:

[0116] state Success rate S0 99％ S1 95％ S2 10％

[0117] 3)SMF:

[0118] The mapping relationship between the node status corresponding to the network element node and the indicator value of the node status indicator is as follows:

[0119] S0: Session success rate > 99.9%, N4 latency < 50ms, UPF handover failure rate < 1%;

[0120] S1: Session success rate 95% to 99.9% or N4 delay 50ms to 200ms or UPF handover failure rate 1% to 5%;

[0121] S2: The indicator is obviously abnormal, there is a hardware failure, or the indicator conflicts, etc.

[0122] The status success rate mapping table is as follows:

[0123] state Success rate S0 99％ S1 95％ S2 10％

[0124] 4)AMF:

[0125] The mapping relationship between the node status corresponding to the network element node and the indicator value of the node status indicator is as follows:

[0126] S0: Registration success rate > 99.5%, signaling delay < 100ms, context loss rate < 0.1%;

[0127] S1: Registration success rate 98% to 99.5% or signaling delay 100ms to 500ms or context loss rate 0.1% to 1%; S2: Indicators are obviously abnormal, hardware failure or indicator conflict, etc.

[0128] The status success rate mapping table is as follows:

[0129] state Success rate S0 99％ S1 95％ S2 10％

[0130] 5) PCF:

[0131] The mapping relationship between the node status corresponding to the network element node and the indicator value of the node status indicator is as follows:

[0132] S0: Policy conflict rate <0.1%, delivery delay <100ms, violation rate <1%;

[0133] S1: Policy conflict rate 0.1% to 5% or delivery delay 100ms to 500ms or violation rate 1% to 5%;

[0134] S2: The indicator is obviously abnormal, there is a hardware failure, or the indicator conflicts, etc.

[0135] The status success rate mapping table is as follows:

[0136] state Success rate S0 99％ S1 95％ S2 10％

[0137] 6) DN:

[0138] The mapping relationship between the node status corresponding to the network element node and the indicator value of the node status indicator is as follows:

[0139] S0: N6 packet loss rate <0.1%, DNS (Domain Name System) success rate >99.9%, firewall conflict rate <0.1%;

[0140] S1: N6 packet loss rate 0.1% to 1%, DNS success rate 95% to 99.9%, firewall conflict rate 0.1% to 5%;

[0141] S2: The indicator is obviously abnormal, there is a hardware failure, or the indicator conflicts, etc.

[0142] The status success rate mapping table is as follows:

[0143] state Success rate S0 99％ S1 95％ S2 10％

[0144] 7)AUSF:

[0145] The mapping relationship between the node status corresponding to the network element node and the indicator value of the node status indicator is as follows:

[0146] S0: Authentication success rate > 99.9%, key delay < 50ms;

[0147] S1: Authentication success rate 95% to 99.9% or key delay 50ms to 200ms;

[0148] S2: The indicator is obviously abnormal, the hardware fails, or the certificate expires, etc.

[0149] The status success rate mapping table is as follows:

[0150] state Success rate S0 99％ S1 95％ S2 10％

[0151] 8)NSSF:

[0152] The mapping relationship between the node status corresponding to the network element node and the indicator value of the node status indicator is as follows:

[0153] S0: selection failure rate < 0.1%, resource utilization < 60%;

[0154] S1: selection failure rate 0.1% to 5%, resource utilization 60% to 80%;

[0155] S2: The indicator is obviously abnormal, there is a hardware failure, or the indicator conflicts, etc.

[0156] The status success rate mapping table is as follows:

[0157] state Success rate S0 99％ S1 95％ S2 10％

[0158] In the Markov chain state transition matrix construction unit, the state probability of each network element node is formed based on the previously collected data set, and is updated every 10 minutes using a time slice interval update method. The new state probability is updated using the amount of data generated in the next time slice, and a certain amount of state data of each network element node is periodically generated. The state transition matrix is ​​generated using historical data statistics and updated after each time slice.

[0159] In the end-to-end success rate calculation unit, the product model is used for calculation, as shown in the following formula:

[0160] P total (t) = P 基站1 (t)×P UPF_1 (t)×P SMF (t)×P AMF (t)×P AUSF (t)×P PCF (t)×P NSSF (t)

[0161] ×P UPF_2 (t)×P DN (t)

[0162] Taking base station 1 as an example, assuming that the probability of base station 1 being in state S0 is 99%, the probability of being in state S1 is 1%, and the probability of being in state S2 is 0, then The success rate calculation method for other nodes is the same.

[0163] In the success rate prediction unit for the next time period, the node success rate of each node in the next time slice k can be generated according to the state transfer matrix. Taking base station 1 as an example, assuming that the state transfer matrix is but: That is, the success rate of the base station 1 node in the next time slice is 98.48%, and the calculation method of the remaining nodes is the same.

[0164] The total success rate of predicting the future time slice k based on the Markov chain: P total (t+k)=∏P 节点 (t+k).

[0165] In the fault link determination sheet, a threshold of 85% is set for the link success rate. If the link success rate falls below this threshold, a predicted link failure is determined. In the faulty network element node location unit, if a link failure is predicted, the state transition matrix of each node is reviewed to locate the network element node with significant changes, and feedback is provided to the operations and maintenance personnel. If the link is too long and has too many nodes, a binary search method is used to calculate the link success rate of the first half of the nodes and the link success rate of the second half of the nodes. Once the problematic node is identified, the binary search method is repeated or the state transition matrix is ​​reviewed again until the faulty network element node is located.

[0166] This application solves the dynamic adaptability problem of static threshold detection in related technologies by modeling the state transition rules of network element nodes through Markov chains. The end-to-end success rate product model and recursive binary location algorithm are used to quickly identify the root cause node of the fault in a complex network topology. Compared with the existing technology, it has the following advantages: 1) Strong dynamic prediction ability: The fault trend of future time slices is predicted based on the state transition matrix, which improves the prediction accuracy; 2) High precision positioning efficiency: The binary method reduces the time complexity of fault positioning from O(n) to O(log n), which improves the positioning speed of multi-node scenarios; 3) Adaptive learning mechanism: The experience solidification module continuously optimizes the state transition model through historical work orders to reduce the false alarm rate; 4) Resource optimization benefits: Overload risks are predicted 3-5 time slices in advance, which reduces the cost of preventive resource scheduling. This application provides core technical support for the intelligent operation and maintenance of 5G / 6G core networks, significantly improving network reliability and operation and maintenance efficiency.

[0167] According to an embodiment of the present application, an embodiment of a communication link failure detection device is also provided. Figure 4 Schematic diagram of a communication link fault detection device according to an embodiment of the present application. Figure 4 As shown, the device includes:

[0168] A state matrix determination module 40 is configured to determine a node state matrix corresponding to a network element node in a communication link at a first time step, wherein the node state matrix is ​​used to represent the probability of the network element node being in different node states at the first time step;

[0169] a transfer matrix determination module 42, configured to determine a state transfer matrix corresponding to the network element node at a first time step, wherein the state transfer matrix is ​​used to represent a transition probability of the node state of the network element node from the first time step to a second time step, where the second time step is a time step immediately following the first time step;

[0170] a success rate prediction module 44 for determining an end-to-end success rate of the communication link corresponding to the second time step based on the node state matrix, the state transition matrix, and the state success rate mapping matrix corresponding to the network element node, wherein the state success rate mapping matrix is ​​used to represent the communication success rate of the network element node under different node states, and the end-to-end success rate is used to represent the probability of overall communication success of the communication link;

[0171] The fault node location module 46 is configured to determine that a fault exists in the communication link when the end-to-end success rate is lower than a preset success rate threshold.

[0172] Optionally, the communication link fault detection device is also used to: use a software-defined network controller to detect traffic and path information in the network, and obtain a communication link from a source terminal to a target terminal, wherein the communication link includes multiple network element nodes of different types; determine the node status indicator corresponding to each type of network element node, and determine the mapping relationship between different indicator values ​​of the node status indicator and different node states of the network element node; based on the mapping relationship, determine the state success rate mapping matrix.

[0173] Optionally, the communication link fault detection device is also used to: obtain the index value of the node status index corresponding to the network element node after each time step, and determine the node state matrix of the network element node at each time step based on the index value; count the state transition frequency of the network element node from one node state to another node state within a preset time window, wherein the preset time window includes at least one time step; calculate the transition probability between different node states based on the state transition frequency, and update the state transition matrix based on the transition probability.

[0174] Optionally, determining the end-to-end success rate of the communication link corresponding to the second time step based on the node state matrix, the state transfer matrix, and the state success rate mapping matrix corresponding to the network element node includes: predicting the node state matrix corresponding to the network element node at the second time step based on the node state matrix and the state transfer matrix corresponding to the network element node at the first time step; determining the communication success rate corresponding to the network element node based on the predicted node state matrix and the state success rate mapping matrix corresponding to the second time step; determining the end-to-end success rate of the communication link corresponding to the second time step based on the communication success rate corresponding to each network element node in the communication link.

[0175] Optionally, the communication link fault detection device is also used to: determine the network element node where the fault occurs in the communication link by: determining the link node length of the communication link that is determined to have a fault; when the link node length is not greater than the preset node length, traverse each network element node in the communication link to determine whether each network element node has a fault, and when there is an abnormal transition in the state transfer matrix corresponding to the network element node, determine the network element node as the network element node where the fault occurs; when the link node length is greater than the preset node length, use a binary method to divide the communication link into multiple sub-link segments, and recursively process the sub-link segments as new communication links until the faulty network element node is located.

[0176] Optionally, a bisection method is used to divide the communication link into multiple sub-link segments, and the sub-link segments are recursively processed as new communication links until the faulty network element node is located, including: dividing the communication link into a first sub-link segment and a second sub-link segment, and determining the end-to-end success rate corresponding to the first sub-link segment and the second sub-link segment respectively; taking the first sub-link segment and / or the second sub-link segment whose end-to-end success rate is less than a preset success rate threshold as a new communication link; iteratively repeating the above steps of dividing the sub-link segments, determining the end-to-end success rate of the sub-link segments, and comparing it with the preset success rate threshold until the link node length of the newly obtained communication link is no greater than the preset node length; traversing each network element node in the finally obtained communication link, determining whether each network element node has a fault, and determining the network element node as a faulty network element node if there is an abnormal transition in the state transfer matrix corresponding to the network element node.

[0177] Optionally, after determining the network element node where a fault occurs in the communication link, the method further includes: generating a fault work order based on the information of the located faulty network element node, and dispatching the fault work order to the terminal device of the maintenance personnel corresponding to the network element node; obtaining processing information for the fault work order returned by the terminal device, wherein the processing information includes at least one of the following: fault type, fault cause, and fault handling strategy; storing the node status data and processing information corresponding to the network element node in a knowledge base, wherein the node status data includes: characteristics of the state transition matrix corresponding to the network element node when a fault occurs.

[0178] It should be noted that the various modules in the above-mentioned communication link fault detection 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.

[0179] It should be noted that the communication link fault detection device provided in this embodiment can be used to perform Figure 2 The communication link fault detection method shown in FIG. 4 is a flowchart of a communication link fault detection method. Therefore, the relevant explanations and descriptions of the above communication link fault detection method are also applicable to the embodiments of the present application and will not be repeated here.

[0180] An embodiment of the present application also provides a non-volatile storage medium, which includes a stored computer program, wherein the device where the non-volatile storage medium is located executes the following communication link fault detection method by running the computer program: determining a node state matrix corresponding to a network element node in the communication link at a first time step, wherein the node state matrix is ​​used to characterize the probability that the network element node is in different node states at the first time step; determining a state transition matrix corresponding to the network element node at the first time step, wherein the state transition matrix is ​​used to characterize the transition probability of the node state of the network element node from the first time step to the second time step, and the second time step is the next time step immediately adjacent to the first time step; determining the end-to-end success rate of the communication link corresponding to the second time step based on the node state matrix, the state transition matrix, and the state success rate mapping matrix corresponding to the network element node, wherein the state success rate mapping matrix is ​​used to characterize the communication success rate of the network element node in different node states, and the end-to-end success rate is used to characterize the probability of overall communication success of the communication link; when the end-to-end success rate is lower than a preset success rate threshold, it is determined that there is a fault in the communication link.

[0181] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the communication link fault detection method described in each embodiment of the present application: determining a node state matrix corresponding to a network element node in the communication link at a first time step, wherein the node state matrix is ​​used to characterize the probability that the network element node is in different node states at the first time step; determining a state transition matrix corresponding to the network element node at the first time step, wherein the state transition matrix is ​​used to characterize the transition probability of the node state of the network element node from the first time step to the second time step, and the second time step is the next time step immediately adjacent to the first time step; determining the end-to-end success rate of the communication link corresponding to the second time step based on the node state matrix, the state transition matrix, and the state success rate mapping matrix corresponding to the network element node, wherein the state success rate mapping matrix is ​​used to characterize the communication success rate of the network element node in different node states, and the end-to-end success rate is used to characterize the probability of overall communication success of the communication link; when the end-to-end success rate is lower than a preset success rate threshold, it is determined that there is a fault in the communication link.

[0182] 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.

[0183] 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.

[0184] 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 the 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.

[0185] The units described as separate components may or may not be physically separate, and the 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 according to actual needs to achieve the purpose of the present embodiment.

[0186] 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.

[0187] 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 is essentially 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 for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment 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.

[0188] 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.

Claims

1. A communication link failure detection method, characterized in that: include: Determine a node state matrix corresponding to a network element node in the communication link at a first time step, wherein the node state matrix is ​​used to represent the probability of the network element node being in different node states at the first time step; Determining a state transition matrix corresponding to the network element node at the first time step, wherein the state transition matrix is ​​used to represent a transition probability of the node state of the network element node from the first time step to a second time step, where the second time step is a next time step immediately adjacent to the first time step; Determining the end-to-end success rate of the communication link at the second time step based on the node state matrix, the state transition matrix, and the state success rate mapping matrix corresponding to the network element node, wherein the state success rate mapping matrix is ​​used to represent the communication success rate of the network element node under different node states, and the end-to-end success rate is used to represent the probability of overall communication success of the communication link; When the end-to-end success rate is lower than a preset success rate threshold, it is determined that a fault exists in the communication link.

2. The communication link failure detection method according to claim 1, characterized in that: The method further comprises: A software-defined network controller is used to detect traffic and path information in the network and obtain a communication link from a source terminal to a destination terminal, wherein the communication link includes multiple network element nodes of different types; Determining a node status indicator corresponding to each type of the network element node, and determining a mapping relationship between different indicator values ​​of the node status indicator and different node states of the network element node; The state success rate mapping matrix is ​​determined according to the mapping relationship.

3. The communication link failure detection method according to claim 2, characterized in that: The method further comprises: After each time step, an index value of the node state index corresponding to the network element node is obtained, and the node state matrix of the network element node at each time step is determined based on the index value; Counting the state transition frequency of the network element node from one node state to another node state within a preset time window, wherein the preset time window includes at least one time step; According to the state transition frequency, the transition probability between different node states is calculated, and the state transition matrix is ​​updated according to the transition probability.

4. The communication link failure detection method according to claim 1, wherein: Determining, based on the node state matrix, the state transition matrix, and the state success rate mapping matrix corresponding to the network element node, the end-to-end success rate of the communication link at the second time step includes: Predicting the node state matrix corresponding to the network element node at the second time step based on the node state matrix and the state transition matrix corresponding to the network element node at the first time step; Determining a communication success rate corresponding to the network element node according to the predicted node state matrix and the state success rate mapping matrix corresponding to the second time step; Determine the end-to-end success rate of the communication link at the second time step based on the communication success rate corresponding to each network element node in the communication link.

5. The communication link failure detection method according to claim 1, wherein: The method further includes: determining the network element node where a fault occurs in the communication link by: Determining the link node length of the communication link determined to be faulty; When the link node length is not greater than the preset node length, traverse each of the network element nodes in the communication link to determine whether each of the network element nodes has a fault, and when the state transition matrix corresponding to the network element node has an abnormal transition, determine the network element node as a faulty network element node; When the link node length is greater than the preset node length, the communication link is divided into multiple sub-link segments using a binary method, and the sub-link segments are recursively processed as new communication links until the faulty network element node is located.

6. The communication link failure detection method according to claim 5, characterized in that: Dividing the communication link into multiple sub-link segments using a binary method, and recursively processing the sub-link segments as new communication links until the faulty network element node is located includes: Dividing the communication link into a first sub-link segment and a second sub-link segment, and determining the end-to-end success rate corresponding to the first sub-link segment and the second sub-link segment respectively; using the first sub-link segment and / or the second sub-link segment whose end-to-end success rate is less than the preset success rate threshold as a new communication link; Iteratively repeating the steps of dividing the sub-link segments, determining the end-to-end success rate of the sub-link segments, and comparing the end-to-end success rate with a preset success rate threshold until the newly obtained link node length of the communication link is no greater than the preset node length; Traverse each of the network element nodes in the communication link finally obtained, determine whether each of the network element nodes has a fault, and if there is an abnormal transition in the state transfer matrix corresponding to the network element node, determine the network element node as a faulty network element node.

7. The communication link failure detection method according to claim 1, wherein: After determining the network element node where a fault occurs in the communication link, the method further includes: Generate a fault work order based on the located information of the faulty network element node, and dispatch the fault work order to a terminal device of a maintenance personnel corresponding to the network element node; Obtaining processing information for the fault work order returned by the terminal device, wherein the processing information includes at least one of the following: fault type, fault cause, and fault handling strategy; The node status data corresponding to the network element node and the processing information are stored in a knowledge base, wherein the node status data includes: features of the state transition matrix corresponding to the network element node when a failure occurs.

8. A communication link fault detection device, characterized in that: include: A state matrix determination module is used to determine a node state matrix corresponding to a network element node in a communication link at a first time step, wherein the node state matrix is ​​used to represent the probability of the network element node being in different node states at the first time step; a transfer matrix determination module, configured to determine a state transfer matrix corresponding to the network element node at the first time step, wherein the state transfer matrix is ​​used to represent a transition probability of the node state of the network element node from the first time step to a second time step, the second time step being a next time step immediately adjacent to the first time step; a success rate prediction module, configured to determine the end-to-end success rate of the communication link corresponding to the second time step based on the node state matrix, the state transition matrix, and the state success rate mapping matrix corresponding to the network element node, wherein the state success rate mapping matrix is ​​used to represent the communication success rate of the network element node under different node states, and the end-to-end success rate is used to represent the probability of overall communication success of the communication link; The fault node locating module is used to determine that a fault exists in the communication link when the end-to-end success rate is lower than a preset success rate threshold.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is configured to run a program stored in the memory, wherein the communication link failure detection method according to any one of claims 1 to 7 is executed when the program is run.

10. 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 communication link failure detection method according to any one of claims 1 to 7 by running the computer program.

11. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the communication link failure detection method according to any one of claims 1 to 7 are implemented.

Images