Fault positioning method and electronic device

Abstract

Provided in the embodiments of the present application are a fault positioning method and an electronic device. The method is applied to an electronic device, and the method comprises: using entities in a cloud-based network as entity nodes; according to a layer domain structure of the cloud-based network, using different domains as domain nodes; acquiring a first entity node fault probability of the entity nodes, and acquiring a domain node fault probability of the domain nodes; using the domain node fault probability to bias the first entity node fault probability, so as to obtain a second entity node fault probability; and, according to the second entity node fault probability, positioning entity nodes having faults. According to the method of the embodiments of the present application, while using different entities as entity nodes, fault domains are classified by using different domains as domain nodes, and the fault probability of the entity nodes is biased by using the fault probability of the domain nodes, so as to obtain a final domain biased entity fault probability, thereby improving fault positioning accuracy.

Description

Fault location method and electronic equipment

[0001] This application claims priority to the Chinese patent application filed with the State Intellectual Property Office of China on August 18, 2023, with application number 2023110503190 and application name “A Fault Location Method and Electronic Device”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of computer technology, and in particular to a fault location method and electronic equipment. Background Art

[0003] Cloud networking is a new type of telecommunications network infrastructure architecture that uses new IT technologies such as virtualization, containers, and microservices to concentrate network resources and functions on the "cloud", thereby providing high-speed, flexible, secure, and low-cost network services.

[0004] With the development of the internet and the ever-changing and diverse business scenarios encompassing data centers, the Internet of Things (IoT), government and enterprise organizations, mobile users, and artificial intelligence, traditional network infrastructure can no longer meet the demands for high-speed, flexible, secure, and low-cost network services. Therefore, leveraging new IT technologies such as virtualization, containers, and microservices to centralize network resources and functions in the cloud—cloudification of telecommunications network infrastructure—has become a transformation trend for major operators.

[0005] Entities in cloud networks include network elements, device ports, cloud services, and other diverse elements. The overall architecture of cloud networks exhibits cross-layer and cross-domain characteristics both vertically and horizontally. While network cloudification offers numerous benefits, the cross-layer and cross-domain nature of cloud networks also presents new challenges for fault location in telecommunications networks. Therefore, a fault location method tailored to cloud networks is urgently needed to achieve efficient cross-layer and cross-domain fault location.

[0006] Summary of the Invention

[0007] To address the problem of how to achieve cross-layer and cross-domain fault location, the present application provides a fault location method and an electronic device, and also provides a computer-readable storage medium.

[0008] The embodiments of this application adopt the following technical solutions:

[0009] In a first aspect, the present application provides a fault location method, the method comprising:

[0010] The entities in the cloud network are regarded as physical nodes;

[0011] According to the layer-domain structure of the cloud network, different domains are used as domain nodes;

[0012] Obtaining a first entity node failure probability of the entity node, and obtaining a domain node failure probability of the domain node;

[0013] Using the domain node failure probability to bias the first entity node failure probability to obtain a second entity node failure probability;

[0014] The faulty physical node is located according to the second physical node failure probability.

[0015] According to the method of the embodiment of the present application, different entities are used as entity nodes and different domains are used as domain nodes to classify fault domains; by using the failure probability of the domain node to bias the failure probability of the entity node, and then obtaining the final domain-biased entity failure probability, the fault location accuracy can be improved.

[0016] In an implementation of the first aspect, calculating the first entity node failure probability of the entity node and calculating the domain node failure probability of the domain node include:

[0017] Obtaining an entity node vectorized representation of the entity node, and obtaining a domain node vectorized representation of the domain node;

[0018] The entity node vectorized representation and the domain node vectorized representation are respectively used as feature inputs, and corresponding classifiers are constructed to obtain the first entity node failure probability and the domain node failure probability.

[0019] In an implementation of the first aspect, obtaining the entity node vectorized representation of the entity node and obtaining the domain node vectorized representation of the domain node include:

[0020] Based on the entity nodes, construct an entity undirected graph and extract initial features of the entity nodes;

[0021] Based on the domain nodes, construct a layer-domain directed graph;

[0022] Based on the initial features of the entity nodes, performing representation learning on the entity nodes in the entity undirected graph to generate vectorized representations of the entity nodes;

[0023] Based on the vectorized representation of the entity nodes, representation learning is performed on the domain nodes in the layer domain directed graph to generate the vectorized representation of the domain nodes.

[0024] According to the above implementation method, the cloud network is jointly represented based on the entity undirected graph and the layer-domain directed graph, which improves the accuracy of cloud network representation, solves the problems of difficulty and computational efficiency in fault location caused by cross-layer and cross-domain, and can achieve more accurate and faster fault location.

[0025] In an implementation of the first aspect, in the layer-domain directed graph, the edge direction between domain nodes in the same layer is bidirectional, and the edge direction between domain nodes in different layers is from the upper layer domain to the lower layer domain.

[0026] According to the above implementation method, drawing on the prior knowledge of "first locating the domain on a large scale and then locating the entity on a fine-grained basis" and "top-down" traceability and positioning, a layer-domain directed graph is constructed according to the layer-domain structure of the cloud network, and a hierarchical message passing mechanism is proposed to characterize domain nodes. This can reduce the probability of false positives and improve the accuracy of fault location.

[0027] In an implementation of the first aspect, performing representation learning on the entity nodes in the entity undirected graph based on the initial features of the entity nodes to generate vectorized representations of the entity nodes includes:

[0028] Representation learning is performed on entity nodes in the entity undirected graph based on a spectral domain graph transformer model.

[0029] In an implementation of the first aspect, performing representation learning on entity nodes in the entity undirected graph based on a spectral domain graph transformer model includes:

[0030] Use graph filtering to decompose the input features of each entity node into multiple sub-features of different frequencies;

[0031] Feature transformation is performed through a cross-attention mechanism between the input features of the entity node and the sub-features of different frequencies.

[0032] According to the above implementation method, the graph filter and the transformer are combined, and the graph structure and node features are integrated into the transformer. While ensuring the model representation capability, the computational complexity is reduced to linear complexity, thereby improving the computational efficiency.

[0033] In an implementation of the first aspect, performing representation learning on domain nodes in the layer-domain directed graph based on the vectorized representation of the entity nodes to generate the vectorized representation of the domain nodes includes:

[0034] Transforming the entity node vectorized representation using a multilayer perceptron, and performing sum pooling or average pooling on the entity node vectorized representations of the entity nodes corresponding to the domain nodes according to the corresponding relationship between the domain nodes in the layer domain directed graph and the entity nodes in the entity undirected graph, to obtain an initial vectorized representation of the domain node;

[0035] On the basis of the initial vectorized representation, the domain node representation is updated layer by layer from top to bottom according to the hierarchical structure in the layer-domain directed graph to obtain the domain node vectorized representation.

[0036] In an implementation of the first aspect, the constructing corresponding classifiers using the entity node vectorized representation and the domain node vectorized representation as feature inputs to obtain the first entity node failure probability and the domain node failure probability includes:

[0037] Taking the vectorized representation of the entity node as a feature input, constructing an entity node classifier based on a multi-layer perceptron, and calculating the failure probability of each entity node;

[0038] and / or,

[0039] The vectorized representation of the domain node is used as a feature input, a domain node classifier based on a multi-layer perceptron is constructed, and the failure probability of each domain node is calculated.

[0040] In an implementation of the first aspect, the vectorized representation of the entity node is used as a feature input, an entity node classifier based on a multilayer perceptron is constructed, and the failure probability of each entity node is calculated, wherein:

[0041] In the process of training the entity node classifier, the binary cross entropy between the predicted entity node failure probability and the entity node failure label is used as the loss function, and the parameters to be trained in the entity node classifier are optimized by gradient descent.

[0042] According to the above implementation, if the failure probability of a non-physical node is high, but the failure probability of its domain is very low, in this case, due to the bias of the domain failure probability, the final failure probability of the physical node is still low, thereby reducing the frequency of false positives.

[0043] In an implementation of the first aspect, using the domain node failure probability to bias the first entity node failure probability to obtain the second entity node failure probability includes:

[0044] The first entity node failure probability is multiplied by the domain node failure probability, and the obtained product is the second entity node failure probability.

[0045] In a second aspect, the present application provides an electronic device, comprising a memory for storing computer program instructions and a processor for executing computer program instructions, wherein when the computer program instructions are executed by the processor, the electronic device is triggered to execute the method steps described in the first aspect.

[0046] In a third aspect, the present application provides a computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which, when executed on a computer, enables the computer to execute the method described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] FIG1 shows an example diagram of the overall layer domain structure of a cloud network according to an embodiment of the present application;

[0048] FIG2 is a flowchart of a fault location process based on graph learning according to an embodiment of the present application;

[0049] FIG3 is a schematic diagram of a fault location process according to an embodiment of the present application;

[0050] FIG4 is a diagram showing a system architecture according to an embodiment of the present application;

[0051] FIG5 is a schematic diagram of a fault location process according to an embodiment of the present application;

[0052] FIG6 shows an entity undirected graph according to an embodiment of the present application;

[0053] FIG7 shows a layer-domain directed graph according to an embodiment of the present application;

[0054] FIG8 is a schematic diagram of an SGT model calculation process according to an embodiment of the present application;

[0055] FIG9 is a schematic diagram showing a domain node representation process according to an embodiment of the present application;

[0056] FIG10 is a schematic diagram showing a failure probability calculation process according to an embodiment of the present application;

[0057] FIG11 is a schematic structural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0058] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0059] The terms used in the implementation section of this application are only used to explain the specific embodiments of this application and are not intended to limit this application.

[0060] After cloudification, the overall architecture of telecommunications networks exhibits cross-layer and cross-domain characteristics in both vertical and horizontal directions.

[0061] FIG1 shows an example diagram of the overall layer domain structure of a cloud network according to an embodiment of the present application.

[0062] As shown in FIG1 , in the vertical direction, the cloud network architecture includes different layers: a network element network management layer 110 , a virtualized network element layer 120 , a virtual resource layer 130 , a virtualization layer 140 , and a general hardware layer 150 .

[0063] Each layer also involves different domains. For example, the virtual resource layer 130 includes three domains: virtual computing resources 131, virtual storage resources 132, and virtual network resources 133; the network element network management layer 110 includes three domains: element management system (EMS) 1, EMS2, and EMS3; the virtualized network element layer 120 includes three domains: virtual network function (VNF) 1, VNF2, and VNF3; and the general hardware layer 150 includes three domains: hardware computing resources 151, hardware storage resources 152, and hardware network resources 153.

[0064] The purpose of cross-layer and cross-domain fault location is to locate faults in entities in different domains and layers of the cloud network, that is, to locate the faulty entity that causes cloud network anomalies.

[0065] One solution for fault location is manual locating. Based on their experience, operations engineers first check the KPIs, logs, and alarms on each device in the cloud network to diagnose the device's operating status. Then, combining the network's macroscopic layer structure with the microscopic topological relationships between devices, they analyze each device according to the business logic of "analyzing and locating from top to bottom, layer by layer," to identify the root cause of the fault.

[0066] However, cross-layer and cross-domain fault location involves entities from different technical fields. For example, the entities in virtualized network element layer 120 in Figure 1 belong to the core network technical field; the entities in virtual resource layer 130 and virtualization layer 140 belong to the cloud computing technical field; and the entities in general hardware layer 150 belong to the IT technical field. This requires a high level of knowledge from operations and maintenance engineers, making it difficult for single-domain operations and maintenance engineers to troubleshoot faults in this situation. This increases the labor costs of operations and maintenance engineers. Furthermore, the increased complexity of faults caused by cross-layer and cross-domain operations makes manual location inefficiency low.

[0067] Another solution for fault localization is a graph learning-based fault localization solution, which abstracts the fault localization problem in telecommunication networks into a graph node representation and classification problem.

[0068] FIG2 is a flowchart showing a fault location process based on graph learning according to an embodiment of the present application.

[0069] The graph learning-based fault location process mainly includes the following steps, as shown in Figure 2:

[0070] S210, Telecom Network Graph Construction: The telecom network is represented as a graph, where nodes represent different entities in the telecom network, such as network elements, device ports, and cloud services. Edges represent interactions between two entities, such as physical topological connections and communication relationships. The initial attribute feature vectors of the nodes can be constructed from data such as KPIs, logs, and alarms.

[0071] S220, node representation learning: Node representation learning is performed using a graph learning model, such as a graph neural network, a graph attention model (graph transformer, which is a model that uses the transformer architecture for graph data representation), etc., to obtain a node representation;

[0072] S230, fault node classification: taking the node representation as feature input, using a classifier such as logistic regression or multi-layer perceptron to output the fault probability of each node.

[0073] Although the above solution can reduce the manual workload of fault location, it does not incorporate prior knowledge of cross-layer and cross-domain location logic in the business. In scenarios with insufficient data, such as network fault location, directly representing and classifying nodes is like "finding a needle in a haystack", and the location effect is mediocre.

[0074] Furthermore, in the above schemes, most existing graph neural network models are based on the aggregation of local neighbor node features, which suffers from over-smoothing and over-squeezing optimization problems, resulting in limited representation capabilities. In addition, the existing graph Transformer model learns the graph as a fully connected graph and calculates the attention scores between all nodes, with a computational complexity of O(N 2 ), where N is the number of nodes. The computational efficiency is low and it is not suitable for learning large-scale graphs. In addition, the N×N optimization space can easily lead to overfitting.

[0075] Furthermore, unified management of entities across layers and domains will inevitably make the scale of entities in the network very large. On the one hand, this itself further increases the difficulty of fault location; on the other hand, it also requires related analysis algorithms to have high computational complexity, further increasing the difficulty of implementing fault location.

[0076] To address the above issues, an embodiment of the present application proposes a fault location method that incorporates prior knowledge of the cloud network layer domain structure and traceability location logic, and can effectively address the problem of increased fault complexity brought about by cross-layer and cross-domain network cloudification.

[0077] FIG3 is a schematic diagram of a fault location process according to an embodiment of the present application.

[0078] The electronic device executes the following process shown in FIG3 to achieve fault location.

[0079] S301 , taking an entity in a cloud network as an entity node, calculating a failure probability of the entity node (a first entity node failure probability).

[0080] S302 , according to the layer-domain structure of the cloud network, different domains are used as domain nodes, and the failure probability of the domain nodes (domain node failure probability) is calculated.

[0081] S303 : Use the failure probability of the domain node to bias the failure probability of the entity node to obtain a domain-biased entity node failure probability (a second entity node failure probability).

[0082] Specifically, in S303, for each entity node, the failure probability of the domain node corresponding to the domain in which it is located is used to bias the failure probability of its entity node (first entity node failure probability), and the domain-biased entity node failure probability (second entity node failure probability) is output.

[0083] S304: Locate the physical node where the fault occurs according to the physical node failure probability of the domain bias.

[0084] Specifically, in one embodiment, a physical node with a failure probability exceeding a first preset threshold (e.g., 85%) is considered a failed physical node, and a domain node with a failure probability exceeding a second preset threshold (the second threshold may be the same as the first threshold) is considered a failed domain node. Multiple physical nodes and / or multiple domain nodes may have failed. When the failure probability of all physical nodes is below the first preset threshold (and / or the failure probability of all domain nodes is below the second preset threshold), no failure is considered to have occurred.

[0085] In another embodiment, the entity node with the highest failure probability among the entity nodes whose failure probability exceeds a third preset threshold (for example, 85%) is the entity node where the failure occurs, and the domain node with the highest failure probability among the domain nodes whose failure probability exceeds a fourth preset threshold (the fourth threshold may be the same as the third threshold) is the domain node where the failure occurs.

[0086] According to the method of the embodiment of the present application, different entities are used as entity nodes and different domains are used as domain nodes to classify fault domains; by using the failure probability of the domain node to bias the failure probability of the entity node, and then obtaining the final domain-biased entity failure probability, the fault location accuracy can be improved.

[0087] Furthermore, in one embodiment, a joint representation is constructed by constructing an entity undirected graph and a layer-domain directed graph to generate vectorized representations of entity nodes and domain nodes. Using the entity node vectorized representation and the domain node representation as feature inputs, corresponding classifiers are constructed to obtain the first entity node failure probability and the domain node failure probability.

[0088] FIG4 shows a system architecture diagram according to an embodiment of the present application.

[0089] In one embodiment, a system for implementing the fault location method of the present application includes a graph construction module 310, a graph representation module 320, and a fault classification module 330, as shown in FIG4 . The graph construction module 310 includes an entity undirected graph construction unit 311 and a layer-domain directed graph construction unit 312; the graph representation module 320 includes an entity node vectorized representation unit 321 and a domain node representation unit 322.

[0090] FIG5 is a schematic diagram of a fault location process according to an embodiment of the present application.

[0091] The system shown in FIG4 executes the following process shown in FIG5 to implement fault location.

[0092] S400, acquiring characteristic data of the cloud network, including different entities in the cloud network, interaction relationships between entities, data generated by the entities, and the layer domain structure of the cloud network.

[0093] S411 , the entity undirected graph construction unit 311 constructs an entity undirected graph using entities in the cloud network as entity nodes, and extracts initial features of the entity nodes.

[0094] S411 models the relationships between different entities in a cloud network at a micro level. Because the mutual influence between entities at the micro level is relatively vague, the relationships between entities are modeled as an undirected graph, that is, an entity undirected graph is constructed with different entities as nodes.

[0095] In one embodiment, S411 includes: abstracting nodes and edges in an entity undirected graph; and constructing an initial attribute vector of the node.

[0096] Specifically, in an entity-based undirected graph, each node can correspond to an entity in the telecom cloud network, such as a VNF, cloud service, container, virtual machine, host, switch, or port of one of these entities. Edges between nodes in the graph can be constructed based on interactions between the two entities, such as physical topology connections and communication relationships. Furthermore, data such as alarms, KPIs, and operations generated by an entity can be encoded using methods such as one-hot encoding and BoW vectors to construct the initial attribute vector for the entity node.

[0097] FIG6 shows an entity undirected graph according to an embodiment of the present application.

[0098] As shown in Figure 6, in one application scenario, the cloud network includes 21 physical nodes G1-G21. The relationship between the physical nodes is represented by the lines between the nodes.

[0099] S412 , the layer-domain directed graph construction unit 312 constructs a layer-domain directed graph according to the layer-domain structure of the cloud network, using different domains as domain nodes.

[0100] Drawing on prior knowledge of "first locating domains broadly, then locating entities at a finer granularity" and "top-down" provenance tracking, S412 models the relationships between different domains in cloud networks at a macro level. Because the interactions between domains at the macro level have a clear direction, these relationships are modeled as a directed graph, constructing a layer-domain directed graph with different domains as nodes.

[0101] Specifically, in the layer-domain directed graph, each node can correspond to a domain in the cloud network, such as virtual computing resources, virtual storage resources, virtual network resources, physical computing resources, etc.

[0102] In S412, based on the actual cloudified network, a relationship is established between the entity nodes in the entity undirected graph and the domain nodes in the layer-domain directed graph. This clarifies which domain the entity corresponding to the entity node belongs to. Specifically, based on the inclusion relationship between domains and entities in the actual network environment, a relationship is established between the domain nodes in the layer-domain directed graph and the entity nodes in the entity undirected graph. Each domain node corresponds to a subgraph in the entity undirected graph.

[0103] Furthermore, in S412, edges between different domain nodes are constructed based on the actual business relationship. That is, if there is an edge between the entity nodes corresponding to two domain nodes, then there is also an edge between the two domain nodes. At the same time, when determining the direction of the edge between domain nodes, based on the prior knowledge of "top-down analysis and positioning by layer" in actual business, the direction of the edge between domain nodes in different layers is from the upper domain to the lower domain, and the direction of the edge between domain nodes in the same layer is bidirectional (i.e., pointing to each other).

[0104] According to the method of the embodiment of the present application, drawing on the prior knowledge of "first locating the domain on a large scale and then locating the entity on a fine-grained basis" and "top-down" traceability positioning, a layer-domain directed graph is constructed according to the layer-domain structure of the cloud network, and a hierarchical structure-based message passing mechanism is proposed to characterize domain nodes, which can reduce the probability of false positives and improve the accuracy of fault location.

[0105] According to the method of the embodiment of the present application, the cloud network is jointly represented based on the entity undirected graph and the layer-domain directed graph, which improves the accuracy of the cloud network characterization, solves the problems of difficulty and computational efficiency in fault location caused by cross-layer and cross-domain, and can achieve more accurate and faster fault location.

[0106] FIG7 shows a layer-domain directed graph according to an embodiment of the present application.

[0107] As shown in Figure 7, the cloudified network includes layers 601, 602, and 603. Layer 601 includes domain 610, layer 602 includes domains 621 and 622, and layer 603 includes domains 631, 632, and 633. Bidirectional edges exist between domains 621 and 622 in the same layer. There is an edge pointing to domain 621 between domains 610 and 621, an edge pointing to domain 622 between domains 610 and 622, an edge pointing to domain 622 between domains 621 and 631, an edge pointing to domain 631 between domains 621 and 632, and an edge pointing to domain 632 between domains 622 and 633.

[0108] As shown in Figure 6, entity nodes G1, G2, and G3 belong to domain 610 of layer 601. Entity nodes G4, G5, G6, and G7 belong to domain 621 of layer 602. Entity nodes G8, G9, G10, and G11 belong to domain 622 of layer 602. Entity nodes G12, G13, G14, and G15 belong to domain 631 of layer 603. Entity nodes G16, G17, and G18 belong to domain 632 of layer 603. Entity nodes G19, G20, and G21 belong to domain 633 of layer 603.

[0109] Furthermore, in the embodiment shown in FIG5 , S400 , S411 , and S412 are executed each time fault location is performed. In another embodiment, characteristic data of the cloud network used to perform S411 and S412 is obtained before fault location is performed, S411 and S412 are performed, and the entity undirected graph and layer-domain directed graph of the cloud network are saved. When fault location is performed, the saved entity undirected graph and layer-domain directed graph are called to obtain characteristic data of the cloud network used for fault location, and subsequent fault location operations are performed.

[0110] S421 , the entity node vectorized representation unit 321 performs representation learning on the entity nodes in the entity undirected graph based on the initial features of the entity nodes, and generates entity node vectorized representations of the entity nodes.

[0111] In S421 , representation learning is performed on the entity undirected graph based on a Spectral Graph Transformer (SGT) model.

[0112] FIG8 is a schematic diagram showing the SGT model calculation process according to an embodiment of the present application.

[0113] As shown in FIG8 , during the calculation process of each layer of the SGT model, S710 is first executed.

[0114] S710: Decompose the input features of each entity node into multiple sub-features of different frequencies using graph spectral filtering.

[0115] Specifically, in one embodiment, during the calculation process of each layer, let the matrix Represents the entity node features of the layer input.

[0116] Each row of X i,: Representative node v i The eigenvector of each column X :,j Represents the value distribution of the jth feature dimension on different nodes, N is the number of nodes in the graph, and H is the number of dimensions of the node features.

[0117] Furthermore, in one embodiment, for the eigendecomposition in S710, the specific calculation process is as follows:

[0118] (1) Each column feature X of the node feature matrix X :,j As a graph signal, it is decomposed into components of different frequencies z using filters based on polynomials such as Chebyshev and Bernstein k,j , taking the filter based on K-order Bernstein polynomial as an example, the calculation method is shown in the following formula 1:

[0119] In Formula 1, k represents the kth Bernstein basis function, indicating the frequency order corresponding to the feature, I is the N×N identity matrix, and L is the Laplace matrix calculated based on the adjacency matrix of the entity undirected graph.

[0120] (2) Rearrange the components of different frequencies corresponding to all column features to obtain the feature matrix Z of different frequencies k , refer to the following formula 2:

[0121] (3) Extract the sub-features of different frequencies corresponding to each node from the feature matrix of different frequencies Refer to the following formula 3:

[0122] Furthermore, in S710, the Laplacian matrix corresponding to the graph adjacency matrix is ​​required in the decomposition process of the sub-features. Therefore, the topological information and feature information, that is, the structural information of the graph, have been considered at the same time in the above steps. In the feature decomposition stage, it has been integrated into the sub-features of different frequencies of each node.

[0123] After S710 , S720 is executed.

[0124] S720: Perform feature transformation on the input feature of the entity node and the sub-features of different frequencies through a cross-attention mechanism to obtain a feature representation of the entity node after transformation.

[0125] In S720 , after the graph filtering is completed, for feature transformation, a cross-attention mechanism based on focusing on sub-features of different frequencies is used to transform and learn the node features.

[0126] Specifically, in one embodiment, for each node v i , the input feature X of each layer i,: As the Q of Transformer, the sub-features of different frequencies obtained by decomposition As K and V of Transformer, adaptively learn node v i The degree of attention paid to different frequency sub-features allows each node to focus on the frequency band it needs to focus on, and the weighted sum of different frequency sub-features is used as the output feature of the corresponding node after transformation.

[0127] Based on the above process of S720, the attention range of each node changes from all nodes in the graph to its own sub-features of different frequencies, and the computational complexity of each layer changes from O(N 2 ) is reduced to O(KN), K<<N (O(KN), K<<N is a linear complexity). At the same time, the optimization space of each layer is also O(KN), which can reduce the possibility of model overfitting.

[0128] Combining the feature decomposition and feature transformation stages of S710 and S720 forms the core functional block of the SGT model. By continuously stacking these functional blocks, the module can be deepened while maintaining low computational complexity and preventing overfitting.

[0129] According to the method of the embodiment of the present application, graph filtering and Transformer are combined, and the graph structure and node features are integrated into Transformer. While ensuring the model representation capability, the computational complexity is reduced to linear complexity, thereby improving computational efficiency.

[0130] S422 , the domain node representation unit 322 performs representation learning on the domain nodes in the layer domain directed graph based on the entity node vectorized representation of the entity node, and generates a domain node vectorized representation of the domain node.

[0131] In S422 , domain nodes in the layer-domain directed graph are represented based on a message passing mechanism of a hierarchical structure.

[0132] FIG9 is a schematic diagram of a domain node representation process according to an embodiment of the present application.

[0133] As shown in FIG9 , when performing domain node representation, S810 is first executed.

[0134] S810 uses a multi-layer perceptron (MLP) to transform the vectorized representations of entity nodes in the entity undirected graph, and performs sum pooling or mean pooling on the entity node vectorized representations of the entity nodes corresponding to the domain nodes based on the correspondence between the domain nodes in the layer-domain directed graph and the entity nodes in the entity undirected graph, to obtain the domain node initial vectorized representation of the domain node, namely:

[0135] In formula 4: v i is a domain node in the layer domain directed graph, For domain node v i The initial vectorized representation, M(v i ) is the domain node v i The corresponding entity node set, Entity node v output by the SGT model j The entity node vector representation of MLP is a multi-layer perceptron neural network.

[0136] S820, based on the initial vectorized representation of the domain node obtained in S810, according to the hierarchical structure in the layer-domain directed graph, the domain node representation is updated from top to bottom layer by layer in a manner similar to a recurrent neural network (RNN) to obtain a vectorized representation of the domain node.

[0137] That is, in the process of updating the domain node representation, the representation of each domain node is only related to the domain nodes pointing to it in the previous layer and the same layer, and the representation of the domain node in the kth layer is updated after the representation of the domain node in the k-1th layer is updated.

[0138] Specifically, to update the domain node v at the kth layer i As an example, the following steps are mainly included:

[0139] (1) Construct a pointer to v in the k-1th layer i The domain node set S k-1 (v i ) and points to v in the kth layer i The domain node set S k (v i ), these domain nodes are used as v i Adjacent domain nodes are used to update domain node v i Vectorized representation of .

[0140] (2) Apply a shared linear transformation to v i and its adjacent domain nodes, and calculate v i and the attention score between adjacent domain nodes.

[0141] During the calculation process, for the domain nodes in the k-1th layer, since their domain node representations have been updated, their updated representations are used; for the domain nodes in the kth layer, their initial vectorized representations are used, that is:

[0142] In formulas 5 and 6: e ij For domain node v i For adjacent domain node v j 's attention score, W' and W are the parameter matrices of the linear transformation, CONCAT(a,b) represents the concatenation operation of vector a and vector b. For domain node v j The updated vectorized representation.

[0143] (3) Use the softmax function to calculate all e ij Normalize:

[0144] (4) Use the normalized weight coefficients above to calculate S(v i ) is weighted summed up as the domain node v i Updated vectorized representation:

[0145] S430 , the fault classification module 330 uses the entity node vectorized representation and the domain node vectorized representation as feature inputs, constructs corresponding classifiers, and obtains the first entity node failure probability and the domain node failure probability.

[0146] S440: The fault classification module 330 uses the domain node's fault probability to bias the first entity node's fault probability to obtain a domain-biased second entity node fault probability. (See S304)

[0147] Specifically, FIG10 shows a schematic diagram of a failure probability calculation process according to an embodiment of the present application.

[0148] The fault classification module 330 executes the following steps as shown in FIG10 .

[0149] S910: Calculate a failure probability of a first physical node.

[0150] Specifically, in one embodiment, the vectorized representation of the entity node output by the SGT model in S421 is used as input to construct an MLP-based entity node classifier to calculate the failure probability of each entity node (the first entity node failure probability):

[0151] In formula 9: For entity node v i The probability of failure of the first entity node, For entity node v i feature representation.

[0152] S920, calculate domain node failure probability.

[0153] The domain node representation output by S422 is used as input to build an MLP-based domain node classifier to calculate the failure probability of each domain node:

[0154] In formula 10: For domain node v i The probability of failure, For domain node v i feature representation.

[0155] S930: Combine the first entity node failure probability and the domain node failure probability to generate a second entity node failure probability. (See S303)

[0156] In one embodiment, the bias is performed using a multiplication method:

[0157] In formula 11: For entity node v iFailure probability after bias (failure probability of the second entity node), D(v i ) represents the entity node v i The corresponding domain node.

[0158] During the S910's physical node classifier training process, the binary cross entropy between the predicted physical node failure probability and the physical node failure label is used as a loss function to optimize the trained (learned) parameters of the entire physical node classifier model through gradient descent. This allows for optimization of the trained (learned) parameters of the entire physical node classifier model by using gradient descent. This allows for optimization of the physical node's failure probability to be high, but the failure probability of its domain is low. Due to the bias in the domain failure probability, the physical node's final failure probability remains low, thus reducing the frequency of false positives.

[0159] S440: Locate the failed entity node and / or domain node based on the second entity node failure probability and / or domain node failure probability. (See S304)

[0160] Furthermore, in one embodiment, when a fault occurs in the cloud network, S400 and subsequent steps are triggered to locate the fault.

[0161] In another embodiment, when it is not confirmed whether a fault exists in the cloud network, S400 and subsequent steps are triggered to determine whether a fault exists, and to locate the fault if a fault exists.

[0162] In another embodiment, S400 and subsequent steps are triggered periodically to determine whether a fault exists, and to locate the fault if one exists.

[0163] In the description of the embodiments of the present application, for the convenience of description, the device is described as being divided into various modules according to their functions. The division of each module is merely a division of logical functions. When implementing the embodiments of the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0164] Specifically, the device proposed in the embodiment of the present application can be fully or partially integrated into a physical entity during actual implementation, or it can be physically separated. And these modules can all be implemented in the form of software calling through processing elements; or they can all be implemented in the form of hardware; or some modules can be implemented in the form of software calling through processing elements, and some modules can be implemented in the form of hardware. For example, the detection module can be a separately established processing element, or it can be integrated in a chip of an electronic device. The implementation of other modules is similar. In addition, these modules can be fully or partially integrated together, or they can be implemented independently. During the implementation process, each step of the above method or each of the above modules can be completed by the hardware integrated logic circuit in the processor element or the instructions in the form of software.

[0165] For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs). For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0166] An embodiment of the present application further provides an electronic device.

[0167] FIG11 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

[0168] As shown in Figure 11, the electronic device 1000 includes a memory 1002 for storing computer program instructions and a processor 1001 for executing program instructions, wherein when the computer program instructions are executed by the processor 1001, the electronic device 1000 is triggered to execute the method steps described in the embodiment of the present application.

[0169] Specifically, in one embodiment of the present application, the above-mentioned one or more computer programs are stored in the above-mentioned memory 1002, and the above-mentioned one or more computer programs include instructions. When the above-mentioned instructions are executed by the above-mentioned electronic device 1000, the above-mentioned electronic device 1000 executes the method steps described in the embodiment of the present application.

[0170] It is understood that the structural description of the electronic device 1000 in the embodiment of the present application does not constitute a specific limitation on the electronic device 1000. In other embodiments of the present application, the electronic device 1000 may include other components besides the processor 1001 and the memory 1002.

[0171] The processor 1001 may be a device on a chip (SOC), and the processor 1001 may include a central processing unit (CPU), and may further include other types of processors.

[0172] The processor involved in processor 1001 may include, for example, a CPU, a DSP, a microcontroller, or a digital signal processor, and may also include a GPU, an embedded neural network processor (Neural-network Process Units, NPU) and an image signal processor (Image Signal Processing, ISP). The processor may also include necessary hardware accelerators or logic processing hardware circuits, such as ASICs, or one or more integrated circuits for controlling the execution of the program of the technical solution of this application. In addition, the processor may have the function of operating one or more software programs, and the software programs may be stored in a storage medium.

[0173] The processor 1001 may include one or more processing units. For example, the processor may include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural-network processing unit (NPU), etc. Different processing units may be independent components or integrated into one or more processors. In some embodiments, the electronic device 1000 may also include one or more processors 1001. The controller may generate an operation control signal based on the instruction opcode and the timing signal to complete the control of instruction fetching and execution.

[0174] In some embodiments, the processor 1001 may include one or more interfaces. The interfaces may include an inter-integrated circuit (I2C) interface, an integrated circuit sound (I2S) interface, a pulse code modulation (PCM) interface, a universal asynchronous receiver / transmitter (UART) interface, a mobile industry processor interface (MIPI), a general-purpose input / output (GPIO) interface, a SIM card interface, and / or a USB interface, etc. Among them, the USB interface is an interface that complies with the USB standard specification, and specifically can be a Mini USB interface, a Micro USB interface, a USB Type C interface, etc. The USB interface can be used to connect a charger to charge the electronic device, and can also be used to transmit data between the electronic device and peripheral devices.

[0175] Electronic device 1000 may also include an external memory interface for connecting an external memory card, such as a Micro SD card, to expand the storage capacity of the electronic device. The external memory card communicates with processor 1001 via the external memory interface to implement data storage. For example, files such as music and videos can be stored on the external memory card.

[0176] Memory 1002 may include a code storage area and a data storage area. The code storage area may store an operating system. The data storage area may store data generated during the use of electronic device 1000. Furthermore, memory 1002 may include high-speed random access memory and non-volatile memory, such as one or more disk storage components, flash memory components, and universal flash storage (UFS).

[0177] The memory 1002 may be a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any computer-readable medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer.

[0178] The processor 1001 and the memory 1002 may be combined into one processing device, or more commonly, they are independent components.

[0179] Furthermore, the devices, apparatuses, and modules described in the embodiments of the present application may be implemented by computer chips or entities, or by products having certain functions.

[0180] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, apparatus, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0181] In the several embodiments provided in this application, if any function 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 this application, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of this application.

[0182] Specifically, an embodiment of the present application further provides a computer-readable storage medium, which stores a computer program. When the computer-readable storage medium is run on a computer, the computer executes the method provided in the embodiment of the present application.

[0183] An embodiment of the present application further provides a computer program product, which includes a computer program. When the computer program product is run on a computer, it enables the computer to execute the method provided in the embodiment of the present application.

[0184] The embodiment description in this application is described with reference to the flow chart and / or block diagram according to the method, equipment (device) and computer program product of embodiment of the present application.It should be understood that each flow process and / or box in the flow chart and / or block diagram and the combination of the flow process and / or box in the flow chart and / or block diagram can be realized by computer program instructions.These computer program instructions can be provided to the processor of general-purpose computer, special-purpose computer, embedded processing machine or other programmable data processing equipment to produce a machine, so that the instruction executed by the processor of computer or other programmable data processing equipment produces the device for realizing the function specified in one flow chart flow chart or multiple flow charts and / or one block or multiple blocks of block diagram.

[0185] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0186] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0187] It should also be noted that, in the embodiments of the present application, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and subsequent associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c or a and b and c, where a, b, c can be single or multiple.

[0188] In the embodiments of the present application, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, method, commodity, or apparatus comprising the element.

[0189] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0190] The various embodiments in this application are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences from other embodiments. In particular, the device embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the partial description of the method embodiments.

[0191] Those skilled in the art will appreciate that the various units and algorithmic steps described in the embodiments of this application can be implemented using a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0192] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices, apparatuses and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0193] The above description is merely a specific embodiment of the present application. Any person skilled in the art may easily conceive of variations or substitutions within the technical scope disclosed in this application, and such variations or substitutions shall be within the scope of protection of this application. The scope of protection of this application shall be subject to the scope of protection of the claims.

Claims

1. A fault location method, characterized in that: The method comprises: The entities in the cloud network are regarded as physical nodes; According to the layer domain structure of the cloud network, different domains are used as domain nodes; Obtaining a first entity node failure probability of the entity node, and obtaining a domain node failure probability of the domain node; Using the domain node failure probability to bias the first entity node failure probability to obtain a second entity node failure probability; The failed entity node is located according to the second entity node failure probability.

2. The method according to claim 1, characterized in that: The calculating of the first entity node failure probability of the entity node and the calculating of the domain node failure probability of the domain node include: Obtaining an entity node vectorized representation of the entity node, and obtaining a domain node vectorized representation of the domain node; The entity node vectorized representation and the domain node vectorized representation are respectively used as feature inputs to construct corresponding classifiers to obtain the first entity node failure probability and the domain node failure probability.

3. The method according to claim 2, characterized in that The obtaining of the entity node vectorized representation of the entity node and the obtaining of the domain node vectorized representation of the domain node include: Based on the entity nodes, construct an entity undirected graph, and extract initial features of the entity nodes; Based on the domain nodes, construct a layer domain directed graph; Based on the initial features of the entity nodes, performing representation learning on the entity nodes in the entity undirected graph to generate vectorized representations of the entity nodes; Based on the vectorized representation of the entity node, representation learning is performed on the domain nodes in the layer domain directed graph to generate the vectorized representation of the domain node.

4. The method according to claim 3, characterized in that In the layer-domain directed graph, the edge directions between domain nodes in the same layer are bidirectional, and the edge directions between domain nodes in different layers are from the upper layer domain to the lower layer domain.

5. The method according to claim 3 or 4, characterized in that: The performing representation learning on the entity nodes in the entity undirected graph based on the initial features of the entity nodes to generate vectorized representations of the entity nodes includes: Representation learning is performed on entity nodes in the entity undirected graph based on a spectral domain graph transformer model.

6. The method according to claim 5, characterized in that The performing representation learning on the entity nodes in the entity undirected graph based on the spectral domain graph transformer model comprises: Use graph filtering to decompose the input features of each entity node into multiple sub-features of different frequencies; Feature transformation is performed through a cross-attention mechanism between the input features of the entity node and the sub-features of different frequencies.

7. The method according to any one of claims 3 to 6, characterized in that: The step of performing representation learning on the domain nodes in the layer domain directed graph based on the vectorized representation of the entity nodes to generate the vectorized representation of the domain nodes includes: The entity node vectorized representation is transformed using a multi-layer perceptron, and, according to the correspondence between the domain nodes in the layer-domain directed graph and the entity nodes in the entity undirected graph, the entity node vectorized representation of the entity node corresponding to the domain node is summed and pooled or averaged to obtain an initial vectorized representation of the domain node; On the basis of the initial vectorized representation, the domain node representation is updated layer by layer from top to bottom according to the hierarchical structure in the layer-domain directed graph to obtain the domain node vectorized representation.

8. The method according to any one of claims 2 to 7, characterized in that: The method of taking the entity node vectorized representation and the domain node vectorized representation as feature inputs respectively and constructing corresponding classifiers to obtain the first entity node failure probability and the domain node failure probability includes: Taking the vectorized representation of the entity node as feature input, constructing an entity node classifier based on a multi-layer perceptron, and calculating the failure probability of each entity node; and / or, The vectorized representation of the domain node is used as a feature input, a domain node classifier based on a multi-layer perceptron is constructed, and the failure probability of each domain node is calculated.

9. The method according to claim 8, characterized in that The vectorized representation of the entity node is used as a feature input, an entity node classifier based on a multi-layer perceptron is constructed, and the failure probability of each entity node is calculated, wherein: In the process of training the entity node classifier, the binary cross entropy between the predicted entity node failure probability and the entity node failure label is used as the loss function, and the parameters to be trained in the entity node classifier are optimized by gradient descent.

10. The method according to any one of claims 1 to 9, characterized in that The using the domain node failure probability to bias the first entity node failure probability to obtain a second entity node failure probability includes: The first entity node failure probability is multiplied by the domain node failure probability, and the obtained product is the second entity node failure probability.

11. An electronic device, characterized in that: The electronic device comprises a memory for storing computer program instructions and a processor for executing the computer program instructions, wherein when the computer program instructions are executed by the processor, the electronic device is triggered to execute the method steps as claimed in any one of claims 1 to 10.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed on a computer, enables the computer to execute the method according to any one of claims 1 to 10.

Images