Microservice system root cause positioning method and system based on space-time diagram neural network

Abstract

The invention belongs to the technical field of big data information processing, and provides a micro-service system root cause positioning method and system based on a space-time diagram neural network, and the method comprises the steps: obtaining calling data information and monitoring index data of a micro-service system, constructing a micro-service time sequence calling topological graph stack, and combining a topological graph and monitoring index information to obtain a micro-service time sequence calling topological graph stack; learning time sequence features of the topological graph by using a long-short-term memory artificial neural network model, and learning space structure features of the topological graph by using a graph convolutional neural network model; performing spatio-temporal feature fusion on the learned time sequence feature information and spatial structure feature information, and introducing an attention mechanism during spatio-temporal feature fusion; and based on the fused space-time fusion features of each topological graph node, determining the probability that each node is a root cause by using a root cause positioning model, and obtaining a final result of root cause positioning. According to the invention, spatial-temporal characteristic information in the topological graph can be fully mined, effective root cause positioning is carried out, and the accuracy of root cause positioning is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of big data information processing, and specifically relates to a root cause location method and system for a microservice system based on a spatiotemporal graph neural network. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] With the development of software development technology, microservice architecture has been widely used in online service systems as a new design concept. Microservice architecture can decompose online service systems into smaller and more reusable components, with high flexibility, which can speed up software development. In traditional monolithic architecture, applications can run in a single process, and it is easy to maintain the availability of applications. However, due to its unique characteristics, microservice architecture requires reusable components to collaborate with each other. When a single service fails, a cascading effect will occur between services, which will in turn affect the application. Therefore, fault location in microservice systems is crucial.

[0004] With the continuous development of artificial intelligence technology, more and more research works combine artificial intelligence technology with root cause location methods to enable more accurate root cause location. In recent years, root cause location methods based on topology graphs have been widely proposed. This method mainly constructs a topology graph based on the call and attribution relationship between microservices in the system, and obtains the root cause service by exploring the root cause of the topology graph. However, the indicator data of microservices and between microservices show time series. How to learn spatial structure features and time series features simultaneously in the topology structure based on artificial intelligence methods has become the focus of research. Summary of the invention

[0005] In order to solve the above problems, the present invention proposes a root cause location method and system for a microservice system based on a spatiotemporal graph neural network. The present invention can fully mine the spatiotemporal feature information in the topological graph and perform effective root cause location, thereby improving the accuracy of root cause location.

[0006] According to some embodiments, the present invention adopts the following technical solutions:

[0007] A root cause location method for a microservice system based on a spatiotemporal graph neural network includes the following steps:

[0008] Obtain call data information and monitoring indicator data of the microservice system;

[0009] Preprocessing the acquired data, and constructing a microservice timing call topology stack based on the preprocessed data, wherein the microservice timing call topology stack includes multiple topology graphs;

[0010] Combining the topological map and monitoring indicator information, a long short-term memory artificial neural network model is used to learn the time series characteristics of the topological map, and a graph convolutional neural network model is used to learn the spatial structure characteristics of the topological map;

[0011] The learned time series feature information and spatial structure feature information are fused with time and space features, and the attention mechanism is introduced during the fusion of time and space features to calculate the attention weights of time series and spatial structure features;

[0012] Based on the spatiotemporal fusion features of each topological map node after fusion, the root cause location model is used to determine the probability of each node being the root cause, and the final result of the root cause location is obtained.

[0013] As an optional implementation, the call data information includes the call relationship between microservices, the monitoring indicator data includes the monitoring indicators of the microservices and the monitoring indicator information between microservices, the monitoring indicators include some of CPU utilization, memory usage, response time, number of requests and error rate, and the monitoring indicator information includes some of call delay, call frequency and failure rate.

[0014] As an optional implementation, the process of preprocessing the acquired data includes: data cleaning and missing data completion, and normalizing the monitoring indicator data to obtain a feature representation vector.

[0015] As an optional implementation method, the process of constructing a microservice timing call topology stack based on the preprocessed data includes: dividing the abnormal time period into multiple time intervals, and constructing a service call topology graph based on the call information between microservices in each time interval. The service call topology graph consists of a set of microservice nodes V = {v1, v2, ..., v s}, during the abnormal period, when the microservice v i Towards Microservices j When sending a call request, add a microservice v i Point to v j A service call topology graph G = (V, E, A) is constructed in each time interval, where V represents the node of the graph, which is a set of microservices, E represents the edge, and A represents the adjacency matrix; in the abnormal time period, the n service call topology graphs constructed constitute the microservice timing call topology stack n is the number of time intervals.

[0016] As a further step, in the microservice timing call topology stack, It is used to represent the feature matrix of microservices in a time interval, where S represents the number of nodes and C represents the number of microservice monitoring indicators;

[0017] Will It is used to represent the adjacency matrix within a time interval. The adjacency matrix in the service call topology graph is expressed as:

[0018]

[0019] Based on call delay between microservices Call frequency and failure rate Calculate the edge weight matrix W t , Microservices i and v j The weight matrix between It is expressed as:

[0020]

[0021] Among them, α, β and γ are weight parameters.

[0022] As an optional implementation, in the process of learning the spatial structural features of the topological graph using the graph convolutional neural network model, the weight W of the edge between microservices is used t Update the adjacency matrix A t ,get

[0023] The adjacency matrix will be updated And microservice node monitoring indicator characteristics X t As input, a graph convolutional neural network model is used to learn spatial structure feature representation

[0024] Among them, σ is the sigmoid function, W GCN are the learnable weights of the graph convolutional neural network model.

[0025] As an optional implementation, the process of performing spatiotemporal feature fusion on the learned time series feature information and spatial structure feature information includes: performing feature alignment operation on the time series feature and the spatial structure feature using linear transformation;

[0026] Based on the aligned time series feature matrix, query, key and value vectors are generated respectively, and the attention weight of time series features is calculated using the attention mechanism;

[0027] Based on the aligned spatial structure feature matrix, query, key, and value vectors are generated respectively, and the attention weight of the spatial structure feature is calculated using the attention mechanism;

[0028] The spatiotemporal feature weighted value is calculated based on the obtained spatiotemporal feature attention weights, and multiple attention heads are used to perform spatiotemporal feature fusion.

[0029] As an optional implementation, the root cause location model is a binary classification model, based on the spatiotemporal fusion features of each topological map node. The output node is at t n The probability of being the root cause node in the time interval

[0030]

[0031] in, and b are both learnable parameters, σ is the sigmoid function;

[0032] The node v i In all time intervals t={t1,t2,...,t n The final root cause node probability is obtained by superimposing the probabilities in}:

[0033] The root cause probabilities of all nodes are ranked to obtain the final root cause microservice.

[0034] A root cause location system for a microservice system based on a spatiotemporal graph neural network, comprising:

[0035] Data acquisition module, used to obtain call data information and monitoring indicator data of the microservice system;

[0036] A timing call topology stack construction module is used to preprocess the acquired data and construct a microservice timing call topology stack based on the preprocessed data, wherein the microservice timing call topology stack includes multiple topology graphs;

[0037] The spatiotemporal feature learning module is used to combine the topological map and monitoring indicator information, use the long short-term memory artificial neural network model to learn the time series features of the topological map, and use the graph convolutional neural network model to learn the spatial structure features of the topological map;

[0038] The spatiotemporal feature fusion module is used to perform spatiotemporal feature fusion on the learned time series feature information and spatial structure feature information, and introduce the attention mechanism during spatiotemporal feature fusion to calculate the attention weights of the time series and spatial structure features;

[0039] The root cause location module is used to determine the probability of each node being the root cause based on the spatiotemporal fusion features of each topology map node after fusion and use the root cause location model to obtain the final result of the root cause location.

[0040] A computer-readable storage medium is used to store computer instructions, and when the computer instructions are executed by a processor, the steps in the above method are completed.

[0041] An electronic device comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps in the above method are completed.

[0042] Compared with the prior art, the present invention has the following beneficial effects:

[0043] (1) The present invention fully considers the timing between monitoring indicators, collects and processes the call information and monitoring indicator data of the microservice system, sets a specific time interval, and constructs a microservice system timing call topology stack.

[0044] (2) The present invention fully learns the time series and spatial structure feature information in the topological graph through the long-term and short-term neural network model and the graph neural network, and introduces the attention mechanism to fuse the spatiotemporal features to improve the accuracy of root cause location.

[0045] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0047] Figure 1 The figure is an overall flow chart of a root cause location method for a microservice system based on a spatiotemporal graph neural network in an embodiment;

[0048] Figure 2 A diagram of a data flow processing process in one embodiment;

[0049] Figure 3 A flowchart of a method execution in an embodiment;

[0050] Figure 4 Schematic diagram of the structure of a root cause location system for a microservice system based on a spatiotemporal graph neural network in an embodiment. DETAILED DESCRIPTION

[0051] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0052] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0053] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0054] In the absence of conflict, the embodiments in this application and the features in the embodiments may be combined with each other.

[0055] Embodiment 1

[0056] like Figure 3 As shown, this embodiment provides a method for locating the root cause of a microservice system based on a spatiotemporal graph neural network, comprising the following steps:

[0057] Step 1: Obtain the call information and monitoring indicator data of the microservice system;

[0058] In this embodiment, the collection of call information and monitoring indicator data of the microservice system uses Prometheus to collect call information and monitoring indicator information between microservices when the system is running, and performs data preprocessing, including data cleaning, missing data completion, data definition and storage.

[0059] Of course, in other embodiments, the monitoring tool is not limited to the examples given above, such as Figure 1 As shown, the call information and monitoring indicator data of the microservice system can be directly obtained from the relevant data source.

[0060] Similarly, in some embodiments, call information and monitoring indicator data may also be obtained from other channels.

[0061] In this embodiment, the call information of the microservice system is the call relationship between microservices, and the monitoring indicator information is divided into monitoring indicators of microservices and monitoring indicator information between microservices. The monitoring indicators of microservices include but are not limited to CPU utilization, memory usage, response time, number of requests, error rate, etc., and the monitoring indicator information between microservices includes but is not limited to call delay, call frequency, failure rate, etc.

[0062] Step 2: Preprocess the collected microservice system monitoring data to obtain a feature representation vector;

[0063] In step 2, the microservice system monitoring indicator data is preprocessed, specifically including:

[0064] Since the monitoring indicators of the microservice system have different dimensions and dimensional units, it will affect the subsequent root cause location. Therefore, in order to unify the dimensions of the monitoring indicators of the microservice system, the min-max normalization method is used to normalize the monitoring indicator data:

[0065]

[0066] Among them, x represents a monitoring indicator data in the microservice system, min() represents the minimum value of the indicator data x, max() represents the maximum value of the indicator data x, and ε is a very small constant to avoid the situation where the denominator is 0. The value range of the final monitoring indicator data is [0,1].

[0067] Step 3: Based on the call information between microservices, build a microservice timing call topology stack according to the time interval;

[0068] Step 301: In this embodiment, the abnormal time period t is divided into n time intervals, t = {t1, t2, ..., t n}.

[0069] In each time interval, a service call topology graph is constructed based on the call information between microservices. The service call topology graph consists of a set of microservice nodes V = {v1, v2, ..., v s}, in the time period t, when microservice v i Towards Microservices j When sending a call request, add a microservice v i Point to v j Finally, a service call topology graph G = (V, E, A) is constructed in each time interval, where V represents the nodes of the graph, a set of microservices, E represents the edges, and A represents the adjacency matrix. In the abnormal time period, the n service call topology graphs constructed constitute the microservice timing call topology stack

[0070] Step 302: In the microservice timing call topology stack, It is used to represent the feature matrix of microservices within a time interval, where S represents the number of nodes and C represents the number of microservice monitoring indicators.

[0071] Will It is used to represent the adjacency matrix within a time interval. The adjacency matrix in the service call topology graph can be expressed as:

[0072]

[0073] Step 303: The correlation strength of the monitoring indicator data between microservices determines the correlation weight. The higher the weight, the stronger the correlation. Call frequency and failure rate Calculate the edge weight matrix W t . Microservices i and v j The weight matrix between can be expressed as:

[0074]

[0075] Among them, α, β and γ are weight parameters.

[0076] Step 4: Based on the microservice timing call topology stack, learn the timing feature information in each topology graph, such as Figure 2 As shown;

[0077] In this embodiment, the topology graph G of the topology stack at time interval t is called in the microservice timing sequence. t As an example, we use the Long Short-Term Memory (LSTM) network to learn G t The specific steps are as follows:

[0078] i t =σ(W i ·[h t-1 ,X t ]+b i )

[0079] f t =σ(W f ·[h t-1 ,X t ]+b f )

[0080]

[0081]

[0082] o t =σ(W o ·[h t-1 ,X t ]+b o )

[0083] h t =o t ⊙tanh(c t )

[0084] Among them, h t is the hidden state, c t is the cell state, f t 、i t , o tThey represent the forget gate, input gate and output gate respectively. represents the candidate unit, σ is the sigmoid function, ⊙ represents element-by-element multiplication, W f , W i , W c , W o Both represent learnable weights, b i 、b f 、b c 、b o represents the bias vector.

[0085] The above steps can be simplified as follows:

[0086] H t =LSTM(X t )

[0087] Finally, the time series feature representation of the topological graph is obtained d T It is the feature dimension of LSTM output, indicating the dimension of time feature.

[0088] Step 5: Learn the spatial structural feature information in each topology graph based on the microservice timing call topology stack;

[0089] In step 5, the topology graph G of the t time interval in the topology stack is called in the microservice timing sequence. t For example, using graph convolutional network GCN to learn the spatial structure feature representation in the topological graph includes:

[0090] Step 501: In order to fully capture the spatial structure information of the topology graph, based on the weight W of the edge between microservices t Update the adjacency matrix A t ,get

[0091]

[0092] Step 502: Update the adjacency matrix And microservice node monitoring indicator characteristics X t As input, we use graph convolutional network (GCN) to learn spatial structure feature representation.

[0093]

[0094] Among them, σ is the sigmoid function, W GCN represents the learnable weight, d S Represents the dimension of spatial features.

[0095] Step 6: Based on the spatiotemporal feature information, the attention mechanism is used to fuse the spatiotemporal features to obtain the spatiotemporal fusion feature vector;

[0096] In step 6, the learned time series features and spatial structural characteristics Feature fusion includes:

[0097] Step 601: Since the time series features and the spatial structure features may have different feature dimensions, linear transformation is used to perform feature alignment on the spatiotemporal features:

[0098]

[0099]

[0100] in, They are all parameter matrices, and finally the feature alignment is obtained and d F Represents the feature dimension after alignment.

[0101] Step 602: Generate query Q based on the aligned time series feature matrix t , key K t , value vector V t , use the attention mechanism to calculate the time series feature attention weight α T :

[0102]

[0103]

[0104]

[0105]

[0106] in, represents the weight parameter matrix, d K Represents the attention dimension.

[0107] Step 603: Based on the aligned spatial structure feature matrix, generate query, key, and value vectors respectively, and use the attention mechanism to calculate the spatial structure feature attention weight α S :

[0108]

[0109]

[0110]

[0111]

[0112] in, Represents the weight parameter matrix.

[0113] Step 604: Calculate the spatiotemporal feature weighted value based on the obtained spatiotemporal feature attention weights, and use h attention heads to perform spatiotemporal feature fusion:

[0114] T at =α T ·V t

[0115] S at =α S ·V s

[0116]

[0117] Among them, T at and S at are the weighted values ​​of time series features and spatial structure features, respectively, at is the projection matrix, F at It is the final spatiotemporal feature after fusion.

[0118] Step 7: Train the root cause location model to obtain the root cause location results of the microservice system.

[0119] In this embodiment, the root cause location is designed as a binary classification model, and the spatiotemporal fusion features of each topological map node obtained in step 6 are input. The output node is at t n The probability of being the root cause node in the time interval

[0120]

[0121] in, and b are learnable parameters.

[0122] Since the time-series call topology stack is constructed in step 3, the node v i In all time intervals t={t1,t2,...,t n The final root cause node probability is obtained by superimposing the probabilities in}:

[0123]

[0124] Finally, the root cause probabilities of all nodes are ranked to obtain the final root cause microservice.

[0125] Embodiment 2

[0126] like Figure 4 As shown, this embodiment provides a microservice system root cause location system based on spatiotemporal graph neural network, including:

[0127] Data acquisition module, used to obtain call data information and monitoring indicator data of the microservice system;

[0128] The timing call topology stack construction module is used to build the microservice timing call topology stack based on the call data information and monitoring indicator data of the microservice system;

[0129] Time series feature learning module, used to learn the time series feature information of monitoring indicators in the topology graph based on LSTM;

[0130] Spatial feature learning module, used to learn the spatial structural feature information of monitoring indicators in the topological graph based on GCN;

[0131] The spatiotemporal feature fusion module is used to fuse spatiotemporal features based on the attention mechanism and learn the fused features for subsequent root cause location.

[0132] The root cause location module is used to obtain the root cause location result by using the root cause location model.

[0133] Embodiment 3

[0134] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the steps in a method for root cause location of a microservice system based on a spatiotemporal graph neural network as provided in Embodiment 1 are implemented.

[0135] Embodiment 4

[0136] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the root cause location method for a microservice system based on a spatiotemporal graph neural network provided in the first embodiment are implemented.

[0137] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0138] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0139] These computer program instructions may also be stored in a computer-readable memory capable of directing 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 an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0140] 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, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0141] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principle of the present invention without creative labor shall be included in the protection scope of the present invention.

Claims

1. A root cause location method for a microservice system based on a spatiotemporal graph neural network, characterized in that: The following steps are involved: Obtain call data information and monitoring indicator data of the microservice system; Preprocessing the acquired data, and constructing a microservice timing call topology stack based on the preprocessed data, wherein the microservice timing call topology stack includes multiple topology graphs; Combining the topological map and monitoring indicator information, a long short-term memory artificial neural network model is used to learn the time series characteristics of the topological map, and a graph convolutional neural network model is used to learn the spatial structure characteristics of the topological map; The learned time series feature information and spatial structure feature information are fused with time and space features, and the attention mechanism is introduced during the fusion of time and space features to calculate the attention weights of time series and spatial structure features; Based on the spatiotemporal fusion features of each topological map node after fusion, the root cause location model is used to determine the probability of each node being the root cause, and the final result of the root cause location is obtained.

2. The root cause location method of a microservice system based on a spatiotemporal graph neural network as claimed in claim 1, characterized in that: The call data information includes the call relationship between microservices, the monitoring indicator data includes the monitoring indicators of microservices and the monitoring indicator information between microservices, the monitoring indicators include some of CPU utilization, memory utilization, response time, number of requests and error rate, and the monitoring indicator information includes some of call delay, call frequency and failure rate.

3. The root cause location method of a microservice system based on a spatiotemporal graph neural network as claimed in claim 1, characterized in that: The process of preprocessing the acquired data includes: data cleaning and missing data completion, as well as normalizing the monitoring indicator data to obtain the feature representation vector.

4. The root cause location method of a microservice system based on a spatiotemporal graph neural network as claimed in claim 1, characterized in that: The process of constructing a microservice timing call topology stack based on the preprocessed data includes: dividing the abnormal time period into multiple time intervals, and constructing a service call topology graph based on the call information between microservices in each time interval. The service call topology graph consists of a set of microservice nodes V = {v1, v2, ..., v s }, during the abnormal period, when the microservice v i Towards Microservices j When sending a call request, add a microservice v i Point to v j A service call topology graph G = (V, E, A) is constructed in each time interval, where V represents the node of the graph, which is a set of microservices, E represents the edge, and A represents the adjacency matrix; in the abnormal time period, the n service call topology graphs constructed constitute the microservice timing call topology stack n is the number of time intervals.

5. The root cause location method of a microservice system based on a spatiotemporal graph neural network as claimed in claim 4 is characterized in that: In the microservice timing call topology stack, It is used to represent the feature matrix of microservices in a time interval, where S represents the number of nodes and C represents the number of microservice monitoring indicators; Will It is used to represent the adjacency matrix within a time interval. The adjacency matrix in the service call topology graph is expressed as: Based on the call delay between microservices Call frequency and failure rate Calculate the edge weight matrix W t , Microservices i and v j The weight matrix between It is expressed as: Among them, α, β and γ are weight parameters.

6. The root cause location method of a microservice system based on a spatiotemporal graph neural network as claimed in claim 1, characterized in that: In the process of using the graph convolutional neural network model to learn the spatial structural features of the topological graph, the weight W of the edge between microservices is used t Update the adjacency matrix A t ,get The adjacency matrix will be updated And microservice node monitoring indicator characteristics X t As input, a graph convolutional neural network model is used to learn spatial structure feature representation Among them, σ is the sigmoid function, W GCN is the learnable weight of the graph convolutional neural network model, d S Represents the dimension of spatial features.

7. The root cause location method of a microservice system based on a spatiotemporal graph neural network as claimed in claim 1, characterized in that: The process of fusing the learned time series feature information and spatial structure feature information with time and space features includes: using linear transformation to perform feature alignment operation on the time series features and spatial structure features; Based on the aligned time series feature matrix, query, key and value vectors are generated respectively, and the attention weight of time series features is calculated using the attention mechanism; Based on the aligned spatial structure feature matrix, query, key, and value vectors are generated respectively, and the attention weight of the spatial structure feature is calculated using the attention mechanism; The spatiotemporal feature weighted value is calculated based on the obtained spatiotemporal feature attention weights, and multiple attention heads are used to perform spatiotemporal feature fusion.

8. The root cause location method of a microservice system based on a spatiotemporal graph neural network as claimed in claim 1, characterized in that: The root cause location model is a binary classification model, based on the spatiotemporal fusion characteristics of each topological node. The output node is at t n The probability of being the root cause node in the time interval in, and b are both learnable parameters, σ is the sigmoid function; The node v i In all time intervals t={t1,t2,...,t n The final root cause node probability is obtained by superimposing the probabilities in}: The root cause probabilities of all nodes are ranked to obtain the final root cause microservice.

9. A root cause location system for microservice systems based on spatiotemporal graph neural networks, characterized in that: include: Data acquisition module, used to obtain call data information and monitoring indicator data of the microservice system; A timing call topology stack construction module is used to preprocess the acquired data and construct a microservice timing call topology stack based on the preprocessed data, wherein the microservice timing call topology stack includes multiple topology graphs; The time series feature learning module is used to combine the topology map and monitoring indicator information and use the long short-term memory artificial neural network model to learn the time series features of the topology map; The spatial feature learning module is used to combine the topology map and monitoring indicator information and use the graph convolutional neural network model to learn the spatial structural features of the topology map; The spatiotemporal feature fusion module is used to perform spatiotemporal feature fusion on the learned time series feature information and spatial structure feature information, and introduce the attention mechanism during spatiotemporal feature fusion to calculate the attention weights of the time series and spatial structure features; The root cause location module is used to determine the probability of each node being the root cause based on the spatiotemporal fusion features of each topology map node after fusion and use the root cause location model to obtain the final result of the root cause location.

10. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps of a root cause location method for a microservice system based on a spatiotemporal graph neural network according to any one of claims 1 to 8 are completed.

Images