Optical transmission network alarm root identification method and device based on space-time diagram network

Abstract

The invention provides an optical transmission network root alarm identification method and device based on a space-time diagram network. The method comprises the following steps: constructing a space-time alarm sub-graph according to a space-time clustering result of a plurality of alarm data; the multiple pieces of alarm data comprise root alarm data and derived alarm data, and the space-time alarm sub-graph is used for representing an alarm relationship with space-time characteristics; recognizing the space-time alarm sub-graph based on a space-time graph network to obtain a target alarm recognition result; the time-space diagram network is obtained through training in the mode that multiple pieces of sample alarm data serve as nodes, correlation among the multiple pieces of sample alarm data serves as edge weight parameters among different node features, and an attention mechanism is sampled to update the edge weight parameters. According to the method, the spatial and temporal characteristics of the alarm are fully considered, the identification accuracy of the root alarm of the optical transmission network is improved, and the interpretability of the alarm identification result is enhanced at the same time.

Description

Technical Field

[0001] The present invention relates to the field of network security technology, and in particular to a method and device for identifying root alarms in an optical transmission network based on a space-time graph network. Background Art

[0002] In an optical transmission network, any service interruption may lead to serious business interruption and huge economic losses. Faced with complex network structures and diverse failure modes, alarm information becomes an important means of fault management, which can extract key fault information from complex network environments. Real-time and accurate alarm analysis is essential for effective fault management, which can not only reveal abnormal conditions in the network in a timely manner, but also predict potential fault points.

[0003] In a complex optical transmission network system, multiple entities are interconnected. The failure of a single device may affect related modules, triggering a large number of derived alarms and even an alarm storm. The root alarm is usually a direct indicator of the initial fault, but it is often masked by the derived alarms generated by other devices affected by the fault. The process of finding the root alarm in a large number of alarms in sequence is not only inefficient, but also prolongs the recovery time and increases the risk. Therefore, quickly and accurately locating the root alarm that triggers the chain reaction is crucial to efficient fault management.

[0004] In related technologies, timestamps and time intervals are usually used as indicators to measure the relevance of alarms, or graph theory methods are used to explore the propagation path of alarms in specific service lines. However, the spatiotemporal characteristics of alarms are not fully considered, and the comprehensive impact of the propagation path of logical faults and the fault time on the root cause location of optical transmission network alarms cannot be effectively expressed, resulting in low accuracy in root alarm identification and location. Summary of the invention

[0005] The present invention provides a method and device for identifying root alarms of an optical transmission network based on a time-space graph network, so as to solve the defect in the prior art that the time-space characteristics of alarms are not fully considered in the process of locating the root cause of optical transmission network faults, resulting in low accuracy in root alarm identification and locating, thereby improving the accuracy of root alarm identification in the optical transmission network.

[0006] The present invention provides a method for identifying root alarms in an optical transmission network based on a time-space graph network, comprising: Constructing a spatiotemporal alarm subgraph according to the spatiotemporal clustering results of a plurality of alarm data; wherein the plurality of alarm data include root alarm data and derived alarm data, and the spatiotemporal alarm subgraph is used to represent an alarm relationship with spatiotemporal characteristics; The spatiotemporal alarm subgraph is identified based on the spatiotemporal graph network to obtain a target alarm identification result; wherein the target alarm identification result includes at least one of the alarm type, edge weight parameters between different alarm identification results, and alarm location information; the spatiotemporal graph network is trained by taking multiple sample alarm data as nodes, the correlation between the multiple sample alarm data as the edge weight parameters between different node features, and sampling the attention mechanism to update the edge weight parameters.

[0007] According to a method for identifying root alarms in an optical transmission network based on a spatiotemporal graph network provided by the present invention, the step of constructing a spatiotemporal alarm subgraph based on the spatiotemporal clustering results of a plurality of alarm data comprises: Clustering the plurality of alarm data according to the generation time of each alarm data to obtain a time clustering result; The temporal clustering result is spatially clustered according to the physical topological relationship between the multiple alarm data to obtain the spatiotemporal clustering result, and the spatiotemporal alarm subgraph is constructed according to the spatiotemporal clustering result.

[0008] According to a method for identifying root alarms in an optical transmission network based on a time-space graph network provided by the present invention, a target alarm identification result includes a plurality of root alarm identification results; After obtaining the target alarm identification result, the method further includes: The target alarm identification result is screened according to the edge weight parameters corresponding to each alarm identification result to obtain a first alarm identification result.

[0009] According to a method for identifying root alarms in an optical transmission network based on a spatiotemporal graph network provided by the present invention, the target alarm identification result also includes a plurality of derived alarm identification results; After obtaining the first alarm identification result, the method further includes: The target alarm identification result is screened according to the edge weight parameter corresponding to the first root alarm identification result and the edge weight parameters corresponding to each derived alarm identification result to obtain a second root alarm identification result.

[0010] According to a method for identifying root alarms of an optical transmission network based on a space-time graph network provided by the present invention, the target alarm identification result is an alarm identification subgraph; wherein the alarm identification subgraph includes the alarm type, the edge weight values ​​between different alarm identification results, and the physical topological relationship between each alarm identification result.

[0011] The present invention also provides an optical transmission network root alarm identification device based on a time-space graph network, comprising: A spatiotemporal clustering and mapping module, used to construct a spatiotemporal alarm subgraph according to the spatiotemporal clustering results of a plurality of alarm data; wherein the plurality of alarm data includes root alarm data and derived alarm data, and the spatiotemporal alarm subgraph is used to represent an alarm relationship with spatiotemporal characteristics; An identification module is used to identify the spatiotemporal alarm subgraph based on a spatiotemporal graph network to obtain a target alarm identification result; wherein the target alarm identification result includes at least one of the alarm type, edge weight parameters between different alarm identification results, and alarm location information; the spatiotemporal graph network is trained by taking multiple sample alarm data as nodes, the correlation between multiple sample alarm data as edge weight parameters between different node features, and sampling attention mechanism to update edge weight parameters.

[0012] According to a method and device for identifying root alarms in an optical transmission network based on a time-space graph network provided by the present invention, the target alarm identification result includes a plurality of root alarm identification results; The device also includes: The screening module is used to screen the target alarm identification result according to the edge weight parameters corresponding to each root alarm identification result after the target alarm identification result is obtained, so as to obtain the first root alarm identification result.

[0013] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the optical transmission network root alarm identification method based on the space-time graph network as described in any one of the above is implemented.

[0014] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described optical transmission network root alarm identification methods based on a time-space graph network.

[0015] The present invention also provides a computer program product, comprising a computer program, which, when executed by a processor, implements any of the above-mentioned optical transmission network root alarm identification methods based on a time-space graph network.

[0016] The optical transmission network root alarm identification method and device based on the space-time graph network provided by the present invention obtain identification results such as alarm type, edge weight parameters between different alarm identification results or alarm location information by performing time clustering and space clustering on multiple alarm data in sequence, fully considering the space-time characteristics of the alarm, improving the accuracy of optical transmission network root alarm identification, and enhancing the interpretability of the alarm identification results. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 It is one of the flow charts of the optical transmission network root alarm identification method based on the space-time graph network provided by the present invention.

[0019] Figure 2 This is the second flow chart of the optical transmission network root alarm identification method based on the space-time graph network provided by the present invention.

[0020] Figure 3 It is a schematic diagram of the topological relationship between network elements and corresponding edges in the spatiotemporal alarm subgraph provided by the present invention.

[0021] Figure 4 It is a structural schematic diagram of an optical transmission network root alarm identification device based on a time-space graph network provided by the present invention.

[0022] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] Combine the following Figure 1-Figure 4 The present invention describes an optical transmission network root alarm identification method and device based on a time-space graph network.

[0025] Figure 1 This is one of the flow charts of the optical transmission network root alarm identification method based on the time-space graph network provided by the present invention, such as Figure 1 As shown, the optical transmission network root alarm identification method based on the time-space graph network includes the following steps: Step 110: construct a spatiotemporal alarm subgraph according to the spatiotemporal clustering results of the multiple alarm data; wherein the multiple alarm data include root alarm data and derived alarm data, and the spatiotemporal alarm subgraph is used to represent alarm relations with spatiotemporal characteristics.

[0026] In this step, the alarm data includes one or more of equipment alarm, service alarm, OTU alarm, ODU alarm, network configuration error and system upgrade and maintenance data.

[0027] In this embodiment, time clustering and space clustering are performed on a plurality of alarm data in sequence, so as to group together truly relevant alarms indicating the same fault, so as to construct a corresponding time-space alarm subgraph.

[0028] In this embodiment, for time clustering, timestamps or time intervals may be used as indicators for measuring alarm relevance. For example, alarms occurring within a window of m (the value of m may be set according to user requirements) minutes are classified into the same category.

[0029] In this embodiment, for spatial clustering, as long as two alarm events are physically topologically connected, they can be clustered into one category.

[0030] In this embodiment, corresponding spatiotemporal alarm subgraphs can be constructed for multiple alarm data in turn through two-stage clustering based on time and space (for example, the topological relationship between multiple alarm events); specifically, alarms and network elements are regarded as graph nodes, network elements are connected according to physical topology, and alarms are associated with the network element nodes that report the alarms.

[0031] Step 120: Identify the spatiotemporal alarm subgraph based on the spatiotemporal graph network to obtain a target alarm identification result; wherein the target alarm identification result includes at least one of the alarm type, edge weight parameters between different alarm identification results, and alarm location information; the spatiotemporal graph network is trained by taking multiple sample alarm data as nodes, the correlation between the multiple sample alarm data as the edge weight parameters between different node features, and sampling the attention mechanism to update the edge weight parameters.

[0032] In this step, the spatiotemporal graph network is the same as the spatiotemporal graph attention network (GAT), which learns the weights between nodes by introducing an attention mechanism to achieve a more efficient representation of graph data; the spatiotemporal graph network can assign different attention weights to different nodes in the graph to reflect the importance of different node features.

[0033] In this step, the spatiotemporal alarm subgraph includes multiple alarm clustering results and edge weight parameters thereof, and the edge weight parameters include weight values ​​corresponding to the edges between two nodes.

[0034] In this embodiment, the spatiotemporal graph network uses a multi-head attention mechanism to capture different aspects of node features. Each attention head learns a set of attention scores, and the final node representation is a combination or average of the results of all heads, which enables the model to learn the representation of nodes from different perspectives; for example, the spatiotemporal graph network uses a multi-head attention mechanism to learn the category information, location information and correlation between different types of alarms of multiple alarm data.

[0035] It should be noted that spatiotemporal graph networks excel in predicting edge weights because they intuitively adjust the importance of node interactions without requiring explicit information about the global graph structure.

[0036] In this embodiment, the spatiotemporal graph network updates the edge weights in the spatiotemporal alarm subgraph and identifies the root alarm; specifically, the spatiotemporal graph network recalibrates the edge weights between alarm nodes during the identification process to reflect the relevance of the nodes rather than just the time interval; and the spatiotemporal graph network uses attention to dynamically evaluate the importance of each node's neighbors, thereby focusing the model on the most relevant connections during feature aggregation.

[0037] The optical transmission network root alarm identification method based on the space-time graph network provided by the embodiment of the present invention obtains identification results such as alarm type, edge weight parameters between different alarm identification results or alarm location information by performing time clustering and space clustering on multiple alarm data in sequence, fully considers the space-time characteristics of the alarm, improves the accuracy of optical transmission network root alarm identification, and enhances the interpretability of the alarm identification results.

[0038] In some embodiments, constructing a spatiotemporal alarm subgraph based on the spatiotemporal clustering results of multiple alarm data includes: clustering multiple alarm data according to the generation time of each alarm data to obtain a time clustering result; spatially clustering the time clustering results according to the physical topological relationship between the multiple alarm data to obtain a spatiotemporal clustering result, and constructing a spatiotemporal alarm subgraph based on the spatiotemporal clustering results.

[0039] Figure 2 This is a second flow chart of the optical transmission network root alarm identification method based on the time-space graph network provided by the present invention. Figure 2 In the illustrated embodiment, the spatiotemporal alarm subgraph is constructed by the following steps: (1) Perform two-stage alarm clustering based on topology and time.

[0040] Specifically, firstly, time-based clustering is performed to ensure that only alarms occurring within a window of m = 15 minutes are classified into the same category; then, topology-based clustering is performed. As long as the physical topology of the alarms in the time clustering results is connected, the corresponding alarms are grouped into a cluster.

[0041] (2) Construct a spatiotemporal alarm subgraph based on the final clustering results to fully consider the spatiotemporal characteristics of the alarm.

[0042] In this embodiment, for recurring alarm events, the spatiotemporal alarm subgraph does not add new alarm nodes, but increases the number of connected edges.

[0043] In this embodiment, the temporal feature embedding in the spatiotemporal alarm subgraph is reflected by the edge weights of the graph: alarms are associated with network elements in time series, and all alarms are connected by weights represented by the time intervals at which they occur.

[0044] In this embodiment, since the identification of the root alarm is highly dependent on time characteristics, using time as the initial weight helps to accelerate the convergence of the model.

[0045] Figure 3 is a schematic diagram of the topological relationship between network elements and corresponding edges in the spatiotemporal alarm subgraph provided by the present invention. Figure 3 In the illustrated embodiment, the spatiotemporal alarm subgraph includes 16 network element topology interconnections (NE1-NE16), generating 45 alarm events. The spatiotemporal alarm subgraph embeds spatial attributes of network elements and alarm nodes and uses time intervals as edge weights to fully represent time characteristics. The edge values ​​between alarms include the time difference between alarm occurrences.

[0046] The optical transmission network root alarm identification method based on the space-time graph network provided by the embodiment of the present invention clusters multiple alarm data according to the generation time of each alarm data, and then spatially clusters the time clustering results according to the physical topological relationship between the multiple alarm data. The obtained clustering results are constructed as a space-time alarm subgraph, so that the space-time correlation between each alarm event can be characterized in the form of a graph, and multiple alarm analysis tasks are supported, further enhancing the interpretability of the alarm identification results.

[0047] In some embodiments, the target alarm identification result includes multiple root alarm identification results; after obtaining the target alarm identification result, the optical transmission network root alarm identification method based on the space-time graph network also includes: screening the target alarm identification result according to the edge weight parameters corresponding to each root alarm identification result to obtain the first root alarm identification result.

[0048] In this embodiment, the target alarm identification includes multiple root alarm identification results and edge weights corresponding to each root alarm identification result. The larger the edge weight, the greater the possibility that the good view data is the root cause of the fault.

[0049] exist Figure 2 In the embodiment shown, the graph attention network model (3) (i.e., the spatiotemporal graph network) is used to predict the function f ( x) predicts the edge weights of the edge features between the features of each node in the spatiotemporal alarm subgraph, identifies the corresponding root alarm (R_LOS) node from the N alarm clustering results, and implements multiple analysis tasks based on each root alarm node: Task 1: root alarm identification, Task 2: alarm association, and Task 3: alarm positioning; wherein the constructed spatiotemporal alarm subgraph (2) includes network elements NE1 and NE2, including alarms A1, A2 and A3, and the network elements are connected through physical topology. The connection relationship between the network element and the alarm indicates that the alarm is reported to the network element, and the reporting order is 1, 2, ..., n; the connection relationship between alarm A1 and alarm A2 indicates that A1 occurs 6 seconds before A2, and so on; the alarm subgraph (4) after the graph attention network updates the connection relationship between the alarms, and the corresponding edge values ​​are represented by α1, α2 and α3 networks.

[0050] Table 1 Weight ranking table of the warning subgraph after learning the graph attention network model

[0051] In the above Table 1, the weights of all edges in the spatiotemporal alarm subgraph are sorted through the spatiotemporal graph network, which can explain whether the root alarm identification is successful; among them, for the two root alarms A12 and A1, since the edge weight of the A12 alarm is the largest, it can be determined that the alarm is the root alarm, which means that the larger the weight value, the greater the possibility that the alarm is the root cause.

[0052] The optical transmission network root alarm identification method based on the space-time graph network provided by the embodiment of the present invention screens the target alarm identification results through the edge weight parameters corresponding to each root alarm identification result, thereby improving the reliability of obtaining the root alarm identification results.

[0053] Furthermore, the target alarm identification result also includes multiple derived alarm identification results; after obtaining the first root alarm identification result, the optical transmission network root alarm identification method based on the space-time graph network also includes: screening the target alarm identification result according to the edge weight parameters corresponding to the first root alarm identification result and the edge weight parameters corresponding to each derived alarm identification result to obtain the second root alarm identification result.

[0054] In this embodiment, the target recognition result includes one or more alarm recognition results obtained by recognition and their corresponding edge weights, and also includes each derived alarm recognition result and its corresponding edge weight.

[0055] In Table 1, by further screening the topological relationship of alarm A1, it is found that the edge weight of non-root alarm A9 (i.e., derived alarm) is 0.08 higher than that of root alarm A1, indicating that A9 has a stronger connection with other alarms and is more likely to be a root alarm. Therefore, this embodiment may fail to attempt to identify A1 as a root alarm. In summary, the target alarm identification result corresponding to the spatiotemporal alarm subgraph can be used as an interpretable graph to support A12 as the root cause of the alarm.

[0056] exist Figure 2 In the illustrated embodiment, the alarm subgraph (4) after passing through the spatiotemporal graph network contains the root alarm identification result, and the output edge weight represents the correlation between the alarm events, including the spatiotemporal relationship and the potential derivative interaction; the larger the edge weight corresponding to the alarm in the subgraph, the higher the possibility that the alarm is the root cause, indicating the origin of the fault; if a subgraph may contain multiple root alarms, if the weight of the root alarm is higher than that of the non-root alarm in the same subgraph, successful identification can be achieved.

[0057] The optical transmission network root alarm identification method based on the space-time graph network provided by the embodiment of the present invention further improves the reliability of obtaining the root alarm identification results by screening the target alarm identification results according to the edge weight parameters corresponding to the first root alarm identification result and the edge weight parameters corresponding to each derived alarm identification result.

[0058] In some embodiments, the target alarm identification result is an alarm identification subgraph; wherein the alarm identification subgraph includes the alarm type, edge weight values ​​between different alarm identification results, and the physical topological relationship between the alarm identification results.

[0059] In this embodiment, by screening and analyzing the alarm identification subgraph, it is convenient to quickly obtain the root alarm location and the relationship between the root alarm and other alarms, enhance the explainability of the success or failure of root alarm identification, and facilitate subsequent maintenance and management of optical transmission network faults.

[0060] The optical transmission network root alarm identification device based on the space-time graph network provided by the present invention is described below. The optical transmission network root alarm identification device based on the space-time graph network described below and the optical transmission network root alarm identification method based on the space-time graph network described above can be referenced to each other.

[0061] Figure 4 Schematic diagram of the structure of the optical transmission network root alarm identification device based on the time-space graph network provided by the present invention. Figure 4 As shown, the optical transmission network root alarm identification device based on the space-time graph network includes: a clustering module 410 and an identification module 420.

[0062] The spatiotemporal clustering and mapping module 410 is used to construct a spatiotemporal alarm subgraph according to the spatiotemporal clustering results of the multiple alarm data; wherein the multiple alarm data include root alarm data and derived alarm data, and the spatiotemporal alarm subgraph is used to represent the alarm relationship with spatiotemporal characteristics; The identification module 420 is used to identify the spatiotemporal alarm subgraph based on the spatiotemporal graph network to obtain a target alarm identification result; wherein the target alarm identification result includes at least one of the alarm type, the edge weight parameter between different alarm identification results, and the alarm location information; the spatiotemporal graph network is trained by taking multiple sample alarm data as nodes, the correlation between the multiple sample alarm data as the edge weight parameter between different node features, and sampling the attention mechanism to update the edge weight parameter.

[0063] The optical transmission network root alarm identification device based on the space-time graph network provided by the embodiment of the present invention obtains identification results such as alarm type, edge weight parameters between different alarm identification results or alarm location information by performing time clustering and space clustering on multiple alarm data in sequence, fully considers the space-time characteristics of the alarm, improves the accuracy of optical transmission network root alarm identification, and enhances the interpretability of the alarm identification results.

[0064] In some embodiments, the target alarm identification result includes multiple root alarm identification results; the optical transmission network root alarm identification device based on the space-time graph network also includes: a screening module, which is used to screen the target alarm identification result according to the edge weight parameters corresponding to each root alarm identification result after obtaining the target alarm identification result, to obtain the first root alarm identification result.

[0065] The optical transmission network root alarm identification device based on the space-time graph network provided by the embodiment of the present invention screens the target alarm identification results through the edge weight parameters corresponding to each root alarm identification result, thereby improving the reliability of obtaining the root alarm identification results.

[0066] Figure 5 is a schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 5As shown, the electronic device may include: a processor (processor) 510, a communication interface (Communications Interface) 520, a memory (memory) 530 and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540. The processor 510 can call the logic instructions in the memory 530 to execute the optical transmission network root alarm identification method based on the space-time graph network, the method comprising: constructing a space-time alarm subgraph based on the space-time clustering results of multiple alarm data; wherein the multiple alarm data include root alarm data and derived alarm data, and the space-time alarm subgraph is used to represent the alarm relationship with space-time characteristics; based on the space-time graph network, the space-time alarm subgraph is identified to obtain the target alarm identification result; wherein the target alarm identification result includes at least one of the alarm type, the edge weight parameter between different alarm identification results and the alarm location information; the space-time graph network is trained by taking multiple sample alarm data as nodes, the correlation between the multiple sample alarm data as the edge weight parameter between different node features, and sampling the attention mechanism to update the edge weight parameter.

[0067] In addition, the logic instructions in the above-mentioned memory 530 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the 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 a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0068] On the other hand, the present invention also provides a computer program product, which includes a computer program, and the computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the optical transmission network root alarm identification method based on the spatiotemporal graph network provided by the above-mentioned methods, and the method includes: constructing a spatiotemporal alarm subgraph according to the spatiotemporal clustering results of multiple alarm data; wherein the multiple alarm data include root alarm data and derived alarm data, and the spatiotemporal alarm subgraph is used to represent the alarm relationship with spatiotemporal characteristics; based on the spatiotemporal graph network, the spatiotemporal alarm subgraph is identified to obtain a target alarm identification result; wherein the target alarm identification result includes at least one of the alarm type, edge weight parameters between different alarm identification results, and alarm location information; the spatiotemporal graph network is trained by taking multiple sample alarm data as nodes, the correlation between multiple sample alarm data as the edge weight parameters between different node features, and sampling the attention mechanism to update the edge weight parameters.

[0069] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the optical transmission network root alarm identification method based on the spatiotemporal graph network provided by the above-mentioned methods, the method comprising: constructing a spatiotemporal alarm subgraph based on the spatiotemporal clustering results of multiple alarm data; wherein the multiple alarm data include root alarm data and derived alarm data, and the spatiotemporal alarm subgraph is used to represent the alarm relationship with spatiotemporal characteristics; identifying the spatiotemporal alarm subgraph based on the spatiotemporal graph network to obtain a target alarm identification result; wherein the target alarm identification result includes at least one of the alarm type, edge weight parameters between different alarm identification results, and alarm location information; the spatiotemporal graph network is trained by taking multiple sample alarm data as nodes, the correlation between the multiple sample alarm data as the edge weight parameters between different node features, and updating the edge weight parameters by sampling the attention mechanism.

[0070] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0071] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying root alarms in an optical transmission network based on a spatiotemporal graph network, characterized in that: include: Constructing a spatiotemporal alarm subgraph according to the spatiotemporal clustering results of a plurality of alarm data; wherein the plurality of alarm data include root alarm data and derived alarm data, and the spatiotemporal alarm subgraph is used to represent an alarm relationship with spatiotemporal characteristics; The spatiotemporal alarm subgraph is identified based on the spatiotemporal graph network to obtain a target alarm identification result; wherein the target alarm identification result includes at least one of the alarm type, edge weight parameters between different alarm identification results, and alarm location information; the spatiotemporal graph network is trained by taking multiple sample alarm data as nodes, the correlation between the multiple sample alarm data as the edge weight parameters between different node features, and sampling the attention mechanism to update the edge weight parameters.

2. The optical transmission network root alarm identification method based on the space-time graph network according to claim 1 is characterized in that: The step of constructing a spatiotemporal alarm subgraph according to the spatiotemporal clustering results of the plurality of alarm data comprises: Clustering the plurality of alarm data according to the generation time of each alarm data to obtain a time clustering result; The temporal clustering result is spatially clustered according to the physical topological relationship between the multiple alarm data to obtain the spatiotemporal clustering result, and the spatiotemporal alarm subgraph is constructed according to the spatiotemporal clustering result.

3. The optical transmission network root alarm identification method based on the time-space graph network according to claim 1 is characterized in that: The target alarm identification result includes multiple root alarm identification results; After obtaining the target alarm identification result, the method further includes: The target alarm identification result is screened according to the edge weight parameters corresponding to each alarm identification result to obtain a first alarm identification result.

4. The optical transmission network root alarm identification method based on the time-space graph network according to claim 3 is characterized in that: The target alarm identification result also includes a plurality of derived alarm identification results; After obtaining the first alarm identification result, the method further includes: The target alarm identification result is screened according to the edge weight parameter corresponding to the first root alarm identification result and the edge weight parameters corresponding to each derived alarm identification result to obtain a second root alarm identification result.

5. According to the optical transmission network root alarm identification method based on the spatiotemporal graph network of claim 3, the target alarm identification result is an alarm identification subgraph; wherein, The alarm identification subgraph includes alarm types, edge weight values ​​between different alarm identification results, and physical topological relationships among the alarm identification results.

6. An optical transmission network root alarm identification device based on a time-space graph network, characterized in that: include: A spatiotemporal clustering and mapping module, used to construct a spatiotemporal alarm subgraph according to the spatiotemporal clustering results of a plurality of alarm data; wherein the plurality of alarm data includes root alarm data and derived alarm data, and the spatiotemporal alarm subgraph is used to represent an alarm relationship with spatiotemporal characteristics; An identification module is used to identify the spatiotemporal alarm subgraph based on a spatiotemporal graph network to obtain a target alarm identification result; wherein the target alarm identification result includes at least one of the alarm type, edge weight parameters between different alarm identification results, and alarm location information; the spatiotemporal graph network is trained by taking multiple sample alarm data as nodes, the correlation between multiple sample alarm data as edge weight parameters between different node features, and sampling attention mechanism to update edge weight parameters.

7. The optical transmission network root alarm identification device based on time-space graph network according to claim 6 is characterized in that: The target alarm identification result includes multiple root alarm identification results; The device also includes: The screening module is used to screen the target alarm identification result according to the edge weight parameters corresponding to each root alarm identification result after the target alarm identification result is obtained, so as to obtain the first root alarm identification result.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the optical transmission network root alarm identification method based on the space-time graph network as described in any one of claims 1 to 5 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the optical transmission network root alarm identification method based on a time-space graph network as described in any one of claims 1 to 5 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the optical transmission network root alarm identification method based on a time-space graph network as described in any one of claims 1 to 5 is implemented.

Images