AIOps multi-task scheduling method and system cooperatively driven by large and small models

Abstract

The invention relates to the technical field of artificial intelligence operation and maintenance, in particular to an AIOps multi-task scheduling method and system cooperatively driven by large and small models. The method comprises the steps of obtaining a heterogeneous operation and maintenance time sequence data set, performing data consistency calibration on the heterogeneous operation and maintenance time sequence data set, and determining a multi-source standardized operation and maintenance data stream; analyzing the multi-source standardized operation and maintenance data flow, determining operation and maintenance index dynamic causal information, and determining optimized target event information according to the operation and maintenance index dynamic causal information; determining a real-time operation and maintenance task chain according to the optimized target event information, and determining a large and small model collaborative scheduling strategy according to the real-time operation and maintenance task chain; and performing real-time operation and maintenance adjustment on the system state according to the large and small model collaborative scheduling strategy, and determining and outputting a collaborative operation and maintenance report. According to the method, the problem of over-optimization traps existing in the operation and maintenance process by using the AIOps technology is effectively solved, and the operation and maintenance process is highly matched with the high dynamic response requirement of the system.

Description

Technical Field

[0001] This application relates to the technical field of artificial intelligence operation and maintenance, and in particular to an AIOps multi-task scheduling method and system driven by collaborative large and small models. Background Art

[0002] With the wide application of technologies such as cloud computing, containerization, and microservices, operation and maintenance work has become increasingly complex. Traditional operation and maintenance methods are difficult to meet the increasingly complex operation and maintenance requirements. AIOps (Artificial Intelligence for IT Operations) as a technology to improve operation and maintenance efficiency through data analysis and machine learning methods has become the focus of attention in the operation and maintenance industry.

[0003] However, existing AIOps technologies usually use a single model and preset optimization goals to uniformly process different operation and maintenance tasks, which easily ignores potential over-optimization traps and is difficult to make effective real-time operation and maintenance responses to high-dynamic scenarios. As a result, during the operation and maintenance process based on AIOps technology, frequent human intervention and adjustment are still required, and the response speed is difficult to meet the high-dynamic operation and maintenance requirements. Summary of the Invention

[0004] This application provides an AIOps multi-task scheduling method and system driven by collaborative large and small models to solve the above technical problems.

[0005] In a first aspect, this application provides an AIOps multi-task scheduling method driven by collaborative large and small models, and the method includes: Obtain a heterogeneous operation and maintenance time series data set, perform data consistency calibration on the heterogeneous operation and maintenance time series data set, and determine a multi-source standardized operation and maintenance data stream; Analyze the multi-source standardized operation and maintenance data stream, determine operation and maintenance index dynamic causal information, and determine over-optimization target event information according to the operation and maintenance index dynamic causal information; Determine a real-time operation and maintenance task chain according to the over-optimization target event information, and determine a collaborative scheduling strategy for large and small models according to the real-time operation and maintenance task chain; Perform real-time operation and maintenance adjustment on the system state according to the collaborative scheduling strategy for large and small models, and determine and output a collaborative operation and maintenance report.

[0006] Through this solution, data consistency calibration is performed on the heterogeneous operation and maintenance time series dataset to determine the multi-source standardized operation and maintenance data stream. On this basis, the dynamic causal information of operation and maintenance metrics used to characterize the dynamic causal relationships of various operation and maintenance metrics is analyzed, so as to determine the over-optimization target event information. According to the over-optimization target event information, a real-time operation and maintenance task chain required to solve the over-optimization event is formed. Based on the principle of cooperation between large and small models, a collaborative scheduling strategy for large and small models is determined, so as to perform real-time operation and maintenance adjustment on the system state and provide the corresponding collaborative operation and maintenance report to the operation and maintenance personnel, effectively solving the over-optimization trap problem existing in the operation and maintenance process using AIOps technology, making the operation and maintenance process highly match the high-dynamic response requirements of the system, significantly improving the response speed of the operation and maintenance process while ensuring the operation and maintenance effect, and ensuring the system stability and user experience in real time.

[0007] Optionally, the data consistency calibration of the heterogeneous operation and maintenance time series dataset to determine the multi-source standardized operation and maintenance data stream includes: Extract the operation and maintenance time series data corresponding to different types of operation and maintenance metrics according to the heterogeneous operation and maintenance time series dataset; According to a number of the operation and maintenance time series data, determine the service node to which each operation and maintenance time series data belongs, and thereby determine the network communication hop count between any two service nodes; According to the network communication hop count, determine the topological weights of different data nodes in any two operation and maintenance time series data at the corresponding time nodes; Analyze a number of the operation and maintenance time series data, extract the timestamps corresponding to different data nodes in each operation and maintenance time series data, and determine the time difference impact factor according to the timestamps; Based on a number of the operation and maintenance time series data, determine the minimum alignment cost between any two operation and maintenance time series data according to the topological weights and the time difference impact factor; According to the minimum alignment cost, perform unified alignment processing on different data nodes in a number of the operation and maintenance time series data to construct the multi-source standardized operation and maintenance data stream.

[0008] Through this solution, starting from two dimensions of network structure and time, according to the network communication hop count between different service nodes and the timestamps of different data nodes reflected in the operation and maintenance time series data, the topological weight used to characterize the impact of the communication distance between service nodes on data consistency and the time difference impact factor used to characterize the impact of the timestamp difference of different operation and maintenance time series data on data alignment are respectively analyzed. Furthermore, the minimum alignment cost required to achieve data time series alignment is comprehensively evaluated from two dimensions of network structure and time, and according to the minimum alignment cost, unified alignment processing is performed on different data nodes in a number of operation and maintenance time series data to construct the multi-source standardized operation and maintenance data stream, significantly improving the data alignment speed while ensuring the alignment accuracy.

[0009] Optionally, based on a plurality of the operation and maintenance time series data, according to the topology weight and the time difference impact factor, determine the minimum alignment cost between any two of the operation and maintenance time series data, specifically as the following formula: ; Wherein, is the minimum alignment cost, is the topology weight, is the observation value of the data node of the operation and maintenance time series data at the time node , is the observation value of the data node of the operation and maintenance time series data at the time node , is the time difference impact factor.

[0010] Through this solution, by using mathematical analysis means, based on a plurality of operation and maintenance time series data, according to the topology weight and the time difference impact factor, quantify the minimum alignment cost between any two operation and maintenance time series data, reduce the interference of multi-hop node data deviation through the topology weight mechanism, make the aligned data truly reflect the state association of adjacent service nodes, and through the time difference impression factor, effectively suppress the pseudo-event sequence matching caused by clock asynchrony, and improve the accuracy of subsequent operation and maintenance event chain reconstruction.

[0011] Optionally, according to the number of network communication hops, determine the topology weight of different data nodes in any two of the operation and maintenance time series data at the corresponding time nodes, specifically as the following formula: ; Wherein, is the topology weight, is the network communication hop number between service node and service node , is a preset attenuation coefficient; The method for determining the time difference impact factor according to the time stamp is specifically as the following formula: ; Wherein, is the time difference impact factor, is the time stamp of the data node of the operation and maintenance time series data at the time node , is the time stamp of the data node of the operation and maintenance time series data at the time node , is a preset time offset threshold.

[0012] Through this solution, by means of mathematical analysis, based on the network communication hop count and time stamps, the topological weight and the time difference impact factor are respectively quantified to clarify the mathematical characteristics of the topological weight and the time difference impact factor, improve the scientificity and accuracy of the topological weight and the time difference impact factor, and further improve the accuracy of the minimum alignment cost.

[0013] Optionally, analyzing the multi-source standardized operation and maintenance data stream, determining the dynamic causal information of the operation and maintenance indicators, and based on the dynamic causal information of the operation and maintenance indicators, determining the over-optimization target event information includes: Analyzing the multi-source standardized operation and maintenance data stream, determining the change amount of different operation and maintenance indicators at different time points, thereby determining the change rate corresponding to each operation and maintenance indicator, and based on the change rate, determining the dynamic lag time window corresponding to each operation and maintenance indicator; Based on the change amount of each operation and maintenance indicator at different time points and the dynamic lag time window, determining the lag impact factor between any two operation and maintenance indicators; According to the preset index level attribution information, analyzing the multi-source standardized operation and maintenance data stream, determining the level correlation index between any two operation and maintenance indicators and the collaborative impact weight of each operation and maintenance indicator; Based on the level correlation index and the collaborative impact weight, according to the dynamic lag time window and the lag impact factor, determining the causal correlation index between any two operation and maintenance indicators; Analyzing the multi-source standardized operation and maintenance data stream, determining a number of obvious abnormal operation and maintenance indicators; Based on the causal correlation index, analyzing a number of the obvious abnormal operation and maintenance indicators, determining a number of hidden root cause indicators, and based on the number of the obvious abnormal operation and maintenance indicators and the corresponding number of the hidden root cause indicators, determining whether there is an over-optimization event; If there is the over-optimization event, then taking the corresponding number of the obvious abnormal operation and maintenance indicators and the hidden root cause indicators as the over-optimization target event information.

[0014] Through this solution, the dynamic causal relationship of different operation and maintenance indicators is analyzed from multiple dimensions of time series change, hierarchical structure, and collaborative impact. By evaluating the causal correlation index between different operation and maintenance indicators and combining with the current obvious abnormal operation and maintenance indicators, the root cause operation and maintenance indicators corresponding to the obvious abnormal operation and maintenance indicators are determined, thereby determining whether there is an over-optimization event, and taking the corresponding number of obvious abnormal operation and maintenance indicators and hidden root cause indicators as the over-optimization target event information, making the judgment of the over-optimization event more comprehensive and accurate, and at the same time providing a scientific data basis for the subsequent operation and maintenance task analysis based on the optimization target event information.

[0015] Optionally, based on the hierarchical association index and the collaborative influence weight, and according to the dynamic lag time window and the lag influence factor, determine the causal association index between any two operation and maintenance metrics, specifically as the following formula: ; where, is the current time point for the operation and maintenance metric and the operation and maintenance metric the causal association index therebetween, is the preset data dimension conversion coefficient, is the hierarchical association index between the operation and maintenance metric and the operation and maintenance metric therebetween, is the collaborative influence weight of the operation and maintenance metric ; is the dynamic lag time window, is the change amount of the operation and maintenance metric at the time point ; is the current time point for the operation and maintenance metric and the operation and maintenance metric the lag influence factor therebetween.

[0016] Through this solution, by using mathematical analysis means, based on the hierarchical association index and the collaborative influence weight, and according to the dynamic lag time window and the lag influence factor, comprehensively quantify the causal association index used to characterize the dynamic causal association strength between operation and maintenance metrics from three dimensions of hierarchical influence, collaborative influence, and lag influence, improve the comprehensiveness and accuracy of the causal association index, and further improve the judgment accuracy of over-optimization events.

[0017] Optionally, based on the change amount of each operation and maintenance metric at different time points, determine the lag influence factor between any two operation and maintenance metrics, specifically as the following formula: ; where, is the current time point for the operation and maintenance metric and the operation and maintenance metric the lag influence factor therebetween, is the preset maximum lag time, is the covariance calculation function, is the dynamic lag time window, is the change amount of the operation and maintenance metric at the time point ; is the operation and maintenance metric The change amount at the time point .

[0018] Through this solution, by means of mathematical analysis, based on the change amounts of each operation and maintenance index at different time points, the overall lag effect shown by the current operation and maintenance index under the influence of different moments within the dynamic lag time window is described. Furthermore, the lag time window is normalized to quantify the lag impact factor, improving the scientificity and accuracy of the lag impact factor.

[0019] Optionally, the determining the real-time operation and maintenance task chain according to the over-optimization target event information and determining the collaborative scheduling strategy of the large and small models according to the real-time operation and maintenance task chain includes: Analyze several of the explicit abnormal operation and maintenance indexes and the implicit root cause indexes. Taking each implicit root cause index as the starting task node and several corresponding explicit abnormal operation and maintenance indexes as the chain nodes, construct several operation and maintenance target data chains; Based on the starting task node, analyze the operation and maintenance target data chain to determine the path depth of each chain node; According to the preset operation and maintenance knowledge graph, analyze several of the operation and maintenance target data chains, extract the operation and maintenance tasks corresponding to each starting task node or chain node and the dependency index between each node, construct several target task chains, and determine the event complexity of each target task chain and the task importance index of each target task in each target task chain; According to the path depth, the dependency index, the event complexity, and the task importance index, determine the dynamic scheduling mapping index of each target task in each target task chain; According to the dynamic scheduling mapping index of each target task, determine the large model target task set and the small model target task set, and construct the collaborative scheduling strategy of the large and small models.

[0020] Through this solution, starting from two dynamic dimensions of depth and breadth, and at the same time combining two static dimensions of the absolute complexity and importance of the operation and maintenance task itself, according to the path depth, the dependency index, the event complexity, and the task importance index, comprehensively evaluate the complexity of the operation and maintenance task, obtain the dynamic scheduling mapping index corresponding to different target tasks to accurately measure the actual complexity of the operation and maintenance task. On this basis, integrate to obtain the large model target task set and the small model target task set respectively, and then construct the collaborative scheduling strategy of the large and small models, so that different target tasks are highly matched with the corresponding execution model scale.

[0021] Optionally, determining the dynamic scheduling mapping index of each target task in each target task chain according to the path depth, the dependency index, the event complexity, and the task importance index is specifically the following formula: ; Wherein, is the dynamic scheduling mapping index of the -th target task in the current target task chain, is the preset depth influence weight, is the path depth corresponding to the current target task, is the preset dependency influence weight, is the set of target tasks in the current target task chain that have a dependency relationship with the current target task, is the -th target task in the target task set, is the -th target task and the -th target task The dependency index between them, is the preset resource influence weight, is the event complexity of the target task chain corresponding to the current target task, is the task importance index corresponding to the current target task.

[0022] Through this solution, by using mathematical analysis means, according to the path depth, the dependency index, the event complexity, and the task importance index, the influence of each parameter on the complexity evaluation of the target task is clarified, and the dynamic scheduling mapping index reflecting the overall complexity of the target task is quantitatively obtained to accurately reflect the complexity of the target task and provide an accurate scientific data basis for the collaborative scheduling of large and small models.

[0023] In a second aspect, the present application provides an AIOps multi-task scheduling system driven by collaborative large and small models. The system includes: A data processing module, configured to obtain a heterogeneous operation and maintenance time series data set, perform data consistency calibration on the heterogeneous operation and maintenance time series data set, and determine a multi-source standardized operation and maintenance data stream; an over-optimization analysis module, configured to analyze the multi-source standardized operation and maintenance data stream, determine operation and maintenance index dynamic causal information, and determine over-optimization target event information according to the operation and maintenance index dynamic causal information; a scheduling analysis module, configured to determine a real-time operation and maintenance task chain according to the over-optimization target event information, and determine a collaborative scheduling strategy for large and small models according to the real-time operation and maintenance task chain; an operation and maintenance output module, configured to perform real-time operation and maintenance adjustment on the system state according to the collaborative scheduling strategy for large and small models, and determine and output a collaborative operation and maintenance report. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0025] Figure 1 A schematic diagram of an application scenario provided by an embodiment of the present application; Figure 2 A flowchart of a large and small model collaborative-driven AIOps multi-task scheduling method provided by an embodiment of the present application; Figure 3 A schematic structural diagram of a large and small model collaborative-driven AIOps multi-task scheduling system provided by an embodiment of the present application. Detailed implementation manners

[0026] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0027] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the associated objects before and after, unless otherwise specified.

[0028] The following will further describe the embodiments of the present application in detail with reference to the accompanying drawings of the specification.

[0029] Existing AIOps technologies usually use a single model and preset optimization objectives to uniformly process different operation and maintenance tasks, which easily ignores potential over-optimization traps and is difficult to make effective real-time operation and maintenance responses to highly dynamic scenarios. As a result, during the operation and maintenance process based on AIOps technology, frequent personnel intervention and adjustment are still required, and the response speed is difficult to meet the requirements of highly dynamic operation and maintenance.

[0030] Based on this, the present application provides an AIOps multi-task scheduling method and system driven by collaborative large and small models. Data consistency calibration is performed on heterogeneous operation and maintenance time series datasets to determine multi-source standardized operation and maintenance data streams. On this basis, operation and maintenance metric dynamic causal information for characterizing the dynamic causal relationships of various operation and maintenance metrics is analyzed, and over-optimization target event information is determined accordingly. According to the over-optimization target event information, a real-time operation and maintenance task chain required to solve the over-optimization event is formed. Based on the principle of collaborative large and small models, a collaborative scheduling strategy for large and small models is determined, and the system state is adjusted for real-time operation and maintenance accordingly. The corresponding collaborative operation and maintenance report is provided to the operation and maintenance personnel, effectively solving the over-optimization trap problem existing in the operation and maintenance process using AIOps technology, making the operation and maintenance process highly match the high-dynamic response requirements of the system, significantly improving the response speed of the operation and maintenance process while ensuring the operation and maintenance effect, and real-time guaranteeing system stability and user experience.

[0031] Figure 1 This is a schematic diagram of an application scenario provided by the present application. In the process of automated operation and maintenance, by applying the method provided by the present application, the over-optimization trap problem existing in the operation and maintenance process using AIOps technology is effectively solved, and the operation and maintenance process highly matches the high-dynamic response requirements of the system.

[0032] Specifically, the method of the present application is applied to any server. The server communicates with a log monitoring component, obtains and analyzes the heterogeneous operation and maintenance time series datasets provided by the log monitoring component through the server, performs data consistency calibration on the heterogeneous operation and maintenance time series datasets to determine multi-source standardized operation and maintenance data streams. On this basis, operation and maintenance metric dynamic causal information for characterizing the dynamic causal relationships of various operation and maintenance metrics is analyzed, and over-optimization target event information is determined accordingly. According to the over-optimization target event information, a real-time operation and maintenance task chain required to solve the over-optimization event is formed. Based on the principle of collaborative large and small models, a collaborative scheduling strategy for large and small models is determined, and the system state is adjusted for real-time operation and maintenance accordingly. The corresponding collaborative operation and maintenance report is provided to the operation and maintenance personnel, effectively solving the over-optimization trap problem existing in the operation and maintenance process using AIOps technology, making the operation and maintenance process highly match the high-dynamic response requirements of the system, significantly improving the response speed of the operation and maintenance process while ensuring the operation and maintenance effect, and real-time guaranteeing system stability and user experience.

[0033] The specific implementation manner can refer to the following embodiments.

[0034] Figure 2 This is a flowchart of an AIOps multi-task scheduling method driven by collaborative large and small models provided by an embodiment of the present application. The method of this embodiment can be applied to the server in the above scenario. As Figure 2 shown, the method includes: S201. Obtain the heterogeneous operation and maintenance time series data set, perform data consistency calibration on the heterogeneous operation and maintenance time series data set, and determine the multi-source standardized operation and maintenance data stream.

[0035] The heterogeneous operation and maintenance time series data set can be a collection of operation and maintenance monitoring metric data from different sources and in different formats, such as time series data of server CPU utilization, network throughput, database connection count, etc. The heterogeneous operation and maintenance time series data set can be obtained through the log monitoring component in the target operation and maintenance system.

[0036] The multi-source standardized operation and maintenance data stream can be a standardized operation and maintenance data stream that has been processed by time alignment, format unification, and value normalization.

[0037] Specifically, in modern distributed IT systems, there are problems such as differences in sampling frequencies, time stamp offsets, and inconsistent measurement units in the operation and maintenance data collected by various monitoring tools. By using automated mathematical analysis means, the spatio-temporal deviation between cross-source data is eliminated through data consistency calibration, and a standardized data stream with a unified time reference and numerical dimension is constructed to provide high-quality input for subsequent causal reasoning.

[0038] S202. Analyze the multi-source standardized operation and maintenance data stream, determine the dynamic causal information of operation and maintenance metrics, and determine the over-optimization target event information based on the dynamic causal information of operation and maintenance metrics.

[0039] The dynamic causal information of operation and maintenance metrics can be information that reflects the time-varying causal relationship and intensity between metrics.

[0040] The over-optimization target event information can be operation and maintenance event information that currently exists due to the over-optimization of a certain operation and maintenance metric, which has a negative impact on some operation and maintenance metrics.

[0041] Specifically, in the process of using AIOps technology for automated operation and maintenance of distributed systems, since a distributed system consists of multiple microservices and these microservices are all in a highly dynamic change process, while the operation and maintenance goals set by the operation and maintenance team are often static, it leads to a mismatch between some working stages of some microservices and the operation and maintenance goals, resulting in over-optimization. That is, the current microservice state does not require the high-level indicators in the operation and maintenance goals. Affected by the operation and maintenance goals, the automated operation and maintenance process over-pursues the optimization of the current operation and maintenance indicators, resulting in unbalanced performance, loss of redundancy or reduced reliability of some system components or the whole, thus causing events such as failures, delays or degraded user experience. Such events are called "over-optimization events". The determination of over-optimization events cannot be simply concluded by measuring whether there are abnormalities in the operation and maintenance indicators. Because when an over-optimization event occurs, the "over-optimization indicators" that trigger the over-optimization event are usually normal under the measurement system of the operation and maintenance goals, and other abnormal operation and maintenance indicators are often not caused by the abnormalities of their affiliated components. It is necessary to clarify the causal relationship between different operation and maintenance indicators in the current system working state to quickly judge whether there is an over-optimization event. Through mathematical analysis means, the causal relationship of each operation and maintenance indicator represented in the current multi-source standardized operation and maintenance data stream is automatically sorted out, and the dynamic causal information of the operation and maintenance indicators is integrated to judge whether there is an over-optimization event and determine the over-optimization target event information.

[0042] S203. Determine the real-time operation and maintenance task chain according to the over-optimization target event information, and determine the collaborative scheduling strategy of the large and small models according to the real-time operation and maintenance task chain.

[0043] The real-time operation and maintenance task chain can be an operation and maintenance operation sequence organized according to the causal path between operation and maintenance indicators.

[0044] The collaborative scheduling strategy of the large and small models can be a task allocation scheme formed by combining the semantic understanding ability of the large language model and the real-time reasoning ability of the lightweight model.

[0045] Specifically, after determining the over-optimization target event information, since the over-optimization target event usually involves multiple operation and maintenance metrics, and the optimization and stability of different operation and maintenance metrics correspond to different operation and maintenance tasks, the solution of the over-optimization event requires the execution of multiple different operation and maintenance tasks. By extracting the operation and maintenance tasks to which several different operation and maintenance metrics in the over-optimization target event information belong, a real-time operation and maintenance task chain is constructed. Existing AIOps technologies usually uniformly execute different operation and maintenance tasks through an overall single model. Although this method reduces the overall complexity of the system, due to the lack of strong pertinence to different operation and maintenance tasks, the overall operation and maintenance efficiency is not high, making it difficult to meet systems with high response requirements. Therefore, after obtaining the real-time operation and maintenance task chain, through mathematical analysis means, the complexity of different tasks in the real-time operation and maintenance task chain is quantified respectively. The operation and maintenance tasks with high complexity are assigned to the large model, and the operation and maintenance tasks with low complexity are assigned to the small model to construct a collaborative scheduling strategy for the large and small models. Through the collaborative operation and maintenance scheduling of the large and small models, while ensuring the operation and maintenance effect, fast operation and maintenance response is achieved.

[0046] S204. According to the collaborative scheduling strategy of the large and small models, perform real-time operation and maintenance adjustment on the system state, and determine and output a collaborative operation and maintenance report.

[0047] The collaborative operation and maintenance report can be report information containing the change trends of various operation and maintenance metrics during the collaborative operation and maintenance of the large and small models.

[0048] Specifically, according to the operation and maintenance tasks responsible for by different models in the system scheduling strategy of the large and small models, through the collaborative execution of the large model and the small model for different operation and maintenance tasks, perform real-time operation and maintenance adjustment on the system state, record the change data of different operation and maintenance metrics during the execution of different operation and maintenance tasks, and through data visualization technology, visually integrate and process the change data of different operation and maintenance metrics to construct a collaborative operation and maintenance report, and provide the corresponding collaborative operation and maintenance report to the operation and maintenance personnel through a human-computer interaction device, such as a high-definition display screen, so that the operation and maintenance personnel can effectively master the current operation and maintenance state.

[0049] Through this solution, data consistency calibration is performed on heterogeneous operation and maintenance time series datasets to determine multi-source standardized operation and maintenance data streams. On this basis, operation and maintenance index dynamic causal information used to characterize the dynamic causal relationships of various operation and maintenance indicators is analyzed, so as to determine over-optimization target event information. According to the over-optimization target event information, a real-time operation and maintenance task chain required to solve over-optimization events is formed. Based on the basic principle of large and small model collaboration, a large and small model collaborative scheduling strategy is determined, so as to perform real-time operation and maintenance adjustment on the system state and provide the corresponding collaborative operation and maintenance report to operation and maintenance personnel, effectively solving the over-optimization trap problem existing in the operation and maintenance process using AIOps technology, making the operation and maintenance process highly match the high-dynamic response requirements of the system, significantly improving the response speed of the operation and maintenance process while ensuring the operation and maintenance effect, and ensuring system stability and user experience in real time.

[0050] In some embodiments, according to the heterogeneous operation and maintenance time series datasets, the operation and maintenance time series data corresponding to different types of operation and maintenance indicators are extracted; according to a number of operation and maintenance time series data, the service node to which each operation and maintenance time series data belongs is determined, and based on this, the number of network communication hops between any two service nodes is determined; according to the number of network communication hops, the topological weights of different data nodes in any two operation and maintenance time series data at the corresponding time nodes are determined; a number of operation and maintenance time series data are analyzed, the timestamps corresponding to different data nodes in each operation and maintenance time series data are extracted, and based on the timestamps, the time difference impact factor is determined; based on a number of operation and maintenance time series data, according to the topological weights and the time difference impact factor, the minimum alignment cost between any two operation and maintenance time series data is determined; according to the minimum alignment cost, unified alignment processing is performed on different data nodes in a number of operation and maintenance time series data to construct a multi-source standardized operation and maintenance data stream.

[0051] The operation and maintenance time series data can be the values corresponding to different operation and maintenance indicators at different time points.

[0052] The service node can be the microservice node to which the operation and maintenance indicator belongs.

[0053] The number of network communication hops can be the number of intermediate nodes required for data transmission between two service nodes The topological weight can be a quantitative indicator reflecting the impact of the communication distance between service nodes on data consistency.

[0054] The time difference impact factor can be a quantitative indicator used to characterize the impact of the timestamp difference of different operation and maintenance time series data on data alignment.

[0055] The minimum alignment cost can be the minimum adjustment cost required to achieve the time series alignment processing of different data nodes.

[0056] Specifically, in the operation and maintenance scenario of a distributed system, due to the network architecture differences and clock synchronization errors of different service nodes, there are two core problems in the heterogeneous operation and maintenance time series data set collected: one is the mismatch in the spatial dimension: traditional data calibration methods only focus on timestamp alignment, but ignore the impact of network topology on data transmission delay. For example, for the metric data between service A and service B that span multiple levels of nodes, due to the long network transmission path, the collected time series data actually reflects the states of different service node positions, and direct alignment will introduce spatial deviation; the other is the distortion in the time dimension: existing timestamp alignment algorithms usually assume that the clocks of each node are completely synchronized, while in the actual system, there are clock offsets of milliseconds or even seconds between nodes. If only aligned according to the original timestamps, it will misassociate operation and maintenance events with different time bases, resulting in the failure of subsequent causal reasoning. Therefore, this solution adopts a "network-time two-dimensional calibration mechanism" for the time series calibration of the heterogeneous operation and maintenance time series data set. Through mathematical analysis, according to the network communication hops between different service nodes and the timestamps of different data nodes reflected in the operation and maintenance time series data, the topological weight used to characterize the impact of the communication distance between service nodes on data consistency and the time difference impact factor used to characterize the impact of the timestamp differences of different operation and maintenance time series data on data alignment are respectively quantified. Furthermore, the minimum alignment cost required to achieve data time series alignment is comprehensively evaluated from the two dimensions of network structure and time, and according to the minimum alignment cost, the different data nodes in several operation and maintenance time series data are uniformly aligned to construct a multi-source standardized operation and maintenance data stream, significantly improving the data alignment speed while ensuring the alignment accuracy.

[0057] Through this solution, starting from the two dimensions of network structure and time, according to the network communication hops between different service nodes and the timestamps of different data nodes reflected in the operation and maintenance time series data, the topological weight used to characterize the impact of the communication distance between service nodes on data consistency and the time difference impact factor used to characterize the impact of the timestamp differences of different operation and maintenance time series data on data alignment are respectively analyzed. Furthermore, the minimum alignment cost required to achieve data time series alignment is comprehensively evaluated from the two dimensions of network structure and time, and according to the minimum alignment cost, the different data nodes in several operation and maintenance time series data are uniformly aligned to construct a multi-source standardized operation and maintenance data stream, significantly improving the data alignment speed while ensuring the alignment accuracy.

[0058] In some embodiments, based on several operation and maintenance time series data, the minimum alignment cost between any two operation and maintenance time series data is determined according to the topological weight and the time difference impact factor, specifically as the following formula (1): (1) where, is the minimum alignment cost, is the topological weight, is the operation and maintenance time series data The observed value of the data node at the time node is the operation and maintenance time series data The observed value of the data node at the time node is the time difference impact factor. Specifically, the single-step alignment cost between two data nodes is described by in formula (1). This cost is determined by the topological weight and the distance between nodes. The distance measurement standard can adopt the Euclidean distance. At the same time,

[0059] describes the cumulative minimum alignment cost between two data nodes, and the time difference impact factor is introduced in the process of measuring the minimum alignment cost to clarify the impact of timestamp differences, and then the minimum alignment cost between two data nodes is comprehensively quantified. Through this solution, by using mathematical analysis means, based on a number of operation and maintenance time series data, according to the topological weight and the time difference impact factor, the minimum alignment cost between any two operation and maintenance time series data is quantified. The interference of multi-hop node data deviation is reduced through the topological weight mechanism, so that the aligned data truly reflects the state correlation of adjacent service nodes. Through the time difference impact factor, the matching of pseudo-event sequences caused by clock asynchrony is effectively suppressed, and the accuracy of subsequent operation and maintenance event chain reconstruction is improved.

[0060] In some embodiments, according to the number of network communication hops, the topological weights of different data nodes in any two operation and maintenance time series data at the corresponding time nodes are determined, specifically as the following formula (2):

[0061] (2) where the topological weight is the number of network communication hops between service node and service node and is a preset attenuation coefficient; according to the timestamps, the time difference impact factor is determined, specifically as the following formula (3): (3) where the time difference impact factor is the timestamp of the data node of the operation and maintenance time series data at the time node , the timestamp of the data node of the operation and maintenance time series data at the time node , is a preset time offset threshold.

[0062] Specifically, the topological weight is used to reflect the communication influence strength between two service nodes in the network at a certain time node. Its quantization principle is based on the network communication hop count. The larger the hop count, the higher the delay and cost of data communication, and the smaller the weight. Conversely, the smaller the hop count, the more direct the connection between nodes, and the larger the weight. Through the exponential decay function in formula (3), as the hop count increases, its weight needs to decrease rapidly to show the weakening of the influence of distant nodes. At the same time, the attenuation degree needs to be adjustable to adapt to the objectively existing non-linear dependence relationship between different nodes in the actual network topology. The time difference influence factor is used to quantify the impact of the time stamp difference between two different data nodes at different time points on the matching cost. If the time stamps of two time series data are exactly the same at two time nodes, the time difference influence factor should be 0 because they are synchronized in time. If the time stamps are inconsistent, that is, there is a difference, the greater the difference, the higher the time difference influence factor, thus imposing a greater penalty on the cost of the data alignment process. By measuring the absolute time difference between two data nodes, and then through normalizing the time difference to quantitatively obtain the time difference influence factor.

[0063] Through this solution, by using mathematical analysis means, based on the network communication hop count and time stamp, the topological weight and the time difference influence factor are respectively quantitatively obtained to clarify the mathematical characteristics of the topological weight and the time difference influence factor, improve the scientificity and accuracy of the topological weight and the time difference influence factor, and further improve the accuracy of the minimum alignment cost.

[0064] In some embodiments, analyze the multi-source standardized operation and maintenance data stream, determine the change amount of different operation and maintenance indicators at different time points, and thereby determine the change rate corresponding to each operation and maintenance indicator. According to the change rate, determine the dynamic lag time window corresponding to each operation and maintenance indicator. Based on the change amount of each operation and maintenance indicator at different time points and the dynamic lag time window, determine the lag influence factor between any two operation and maintenance indicators. According to the preset indicator hierarchy attribution information, analyze the multi-source standardized operation and maintenance data stream to determine the hierarchy association index between any two operation and maintenance indicators and the collaborative influence weight of each operation and maintenance indicator. Based on the hierarchy association index and the collaborative influence weight, according to the dynamic lag time window and the lag influence factor, determine the causal association index between any two operation and maintenance indicators. Analyze the multi-source standardized operation and maintenance data stream to determine a number of obvious abnormal operation and maintenance indicators. Based on the causal association index, analyze the number of obvious abnormal operation and maintenance indicators to determine a number of hidden root cause indicators. According to the number of obvious abnormal operation and maintenance indicators and the corresponding number of hidden root cause indicators, determine whether there is an over-optimization event. If there is an over-optimization event, then use the corresponding number of obvious abnormal operation and maintenance indicators and hidden root cause indicators as the over-optimization target event information.

[0065] The dynamic lag time window can be a quantitative time range that reflects the impact of the change rate of operation and maintenance metrics on the timeliness of causal associations. The faster the change rate of an operation and maintenance metric, the shorter the corresponding time window.

[0066] The lag impact factor can be a quantitative metric used to characterize the cross-time dimension impact relationship between two operation and maintenance metrics.

[0067] The change amount can be the numerical difference of an operation and maintenance metric between the current time point and the previous sampling point.

[0068] The preset index hierarchy attribution information can be preset information used to describe the hierarchical structure relationship between different operation and maintenance metrics.

[0069] The hierarchy association index can be a quantitative weight of the subordination relationship between operation and maintenance metrics determined based on the preset index hierarchy attribution information.

[0070] The collaborative impact weight can be a quantitative parameter used to characterize the influence of a single operation and maintenance metric in a collaborative operation and maintenance scenario.

[0071] The obvious abnormal operation and maintenance metric can be an operation and maintenance metric with an obviously abnormal value (such as CPU usage > 90%).

[0072] The implicit root cause metric can be a potential operation and maintenance metric that does not directly show abnormalities but has a significant impact on the obvious abnormal operation and maintenance metric through causal associations.

[0073] Specifically, during the real-time operation and maintenance of a distributed system, since most operation and maintenance metrics are in a state of real-time change and there are differences in the change rates of different operation and maintenance metrics, in the process of analyzing the causal relationships of operation and maintenance metrics, if a fixed time window is adopted, the accuracy and efficiency of analyzing the causal relationships of operation and maintenance metrics with different change rates will be greatly reduced. It is necessary to determine the dynamic lag time window corresponding to each operation and maintenance metric according to the change rate corresponding to each operation and maintenance metric, following the principle that the faster the change rate, the shorter the time window. Then, based on the dynamic lag time window and the change amount corresponding to each operation and maintenance metric, through mathematical analysis means, analyze the cross-time dimension influence relationships between different operation and maintenance metrics, and quantitatively obtain the lag influence factor. At the same time, because the hierarchical relationships and collaborative influence weights defined in the system architecture design stage between different operation and maintenance metrics directly affect the degree of dynamic causal relationships shown by different operation and maintenance metrics during the system operation process, through mathematical analysis means, according to the dynamic lag time window and the lag influence factor, combined with the hierarchical correlation index and the collaborative influence weight, comprehensively analyze the causal relationships between different operation and maintenance metrics to quantitatively obtain the causal correlation index reflecting the causal correlation degree between different operation and maintenance metrics. On this basis, analyze the multi-source standardized operation and maintenance data stream, adopt numerical verification methods such as threshold verification method, and screen out a number of obvious abnormal operation and maintenance metrics. These obvious abnormal operation and maintenance metrics may be caused by "over-optimization events". Further, according to the causal correlation index, extract the root cause operation and maintenance metrics corresponding to the obvious abnormal operation and maintenance metrics. If there are root cause operation and maintenance metrics at a high level within their corresponding ranges among the extracted root cause operation and maintenance metrics, it indicates that there is an over-optimization event, and the corresponding obvious abnormal operation and maintenance metrics and hidden root cause metrics are used as over-optimization target event information.

[0074] Through this solution, analyze the dynamic causal relationships of different operation and maintenance metrics from multiple dimensions of time series change, hierarchical structure, and collaborative influence. By evaluating the causal correlation index between different operation and maintenance metrics and combining the current obvious abnormal operation and maintenance metrics, determine the root cause operation and maintenance metrics corresponding to the obvious abnormal operation and maintenance metrics, thereby judging whether there is an over-optimization event, and using the corresponding obvious abnormal operation and maintenance metrics and hidden root cause metrics as over-optimization target event information, making the judgment of over-optimization events more comprehensive and accurate, and at the same time providing a scientific data basis for subsequent operation and maintenance task analysis based on the optimization target event information.

[0075] In some embodiments, based on the hierarchical correlation index and the collaborative influence weight, according to the dynamic lag time window and the lag influence factor, determine the causal correlation index between any two operation and maintenance metrics, specifically as the following formula (4): (4) Wherein, is the current time point for the operation and maintenance metric The causal association index with operation and maintenance metrics is the preset data dimension conversion coefficient, is the preset data dimension conversion coefficient, is an operation and maintenance metric The hierarchical association index between operation and maintenance metrics is the hierarchical association index between operation and maintenance metrics is an operation and maintenance metric The collaborative impact weight of the operation and maintenance metric is the dynamic lag time window, is an operation and maintenance metric At the time point The change amount of the operation and maintenance metric is the current time point The lag impact factor between the operation and maintenance metric and the operation and maintenance metric is the lag impact factor between the operation and maintenance metric

[0076] The preset data dimension conversion coefficient can be a quantitative value used to uniformly scale the causal association impact of each parameter.

[0077] Specifically, through the in formula (4) to describe the collaborative impact of other operation and maintenance metrics on the two operation and maintenance metrics being currently measured, through to describe the contribution of the fluctuations of different operation and maintenance metrics in the dynamic time lag window to the current collaborative impact. Through the collaborative impact, combined with the hierarchical association index used to describe the hierarchical impact and the lag impact factor used to describe the time lag impact, the causal association index is comprehensively quantified.

[0078] Through this solution, by using mathematical analysis means, based on the hierarchical association index and the collaborative impact weight, according to the dynamic lag time window and the lag impact factor, the causal association index used to characterize the dynamic causal association strength between operation and maintenance metrics is comprehensively quantified from three dimensions: hierarchical impact, collaborative impact, and lag impact, improving the comprehensiveness and accuracy of the causal association index, and further improving the judgment accuracy of over-optimization events.

[0079] In some embodiments, based on the change amount of each operation and maintenance metric at different time points, the lag impact factor between any two operation and maintenance metrics is determined, specifically as the following formula (5): (5) Wherein, is the lag impact factor between the operation and maintenance metric at the current time point and the operation and maintenance metric is the lag impact factor between the operation and maintenance metric is the preset maximum lag time, is a covariance calculation function, is a dynamic lag time window, is an operation and maintenance metric At time point The change amount under is an operation and maintenance metric At time point The change amount under

[0080] The preset maximum lag time is the maximum data delay time allowed for the service corresponding to the current operation and maintenance metric.

[0081] Specifically, during the operation and maintenance process, some operation and maintenance metrics are usually not completely independent. The change of the target metric may be caused by a certain fluctuation of the metric within the lag time point (such as in a previous period of time). Therefore, the lag effect between different metrics is evaluated by the contribution of the change at the historical time point of the metric to the current change. Through the in formula (5), it describes the overall lag effect shown by the current operation and maintenance metric under the influence of different moments within the dynamic lag time window. The lag effect will cause large numerical fluctuations due to different selections of the dynamic lag time window. Therefore, in order to ensure the comparability of the results of the lag impact factor in different scenarios, it is necessary to normalize the lag time window. Through to achieve data normalization, and then accurately quantify the lag impact factor.

[0082] Through this solution, using mathematical analysis means, based on the change amount of each operation and maintenance metric at different time points, it describes the overall lag effect shown by the current operation and maintenance metric under the influence of different moments within the dynamic lag time window. Then, it normalizes the lag time window, quantifies the lag impact factor, and improves the scientificity and accuracy of the lag impact factor.

[0083] In some embodiments, analyze a number of explicit abnormal operation and maintenance metrics and implicit root cause metrics. Taking each implicit root cause metric as the starting task node, and taking the corresponding number of explicit abnormal operation and maintenance metrics as the chain nodes, construct a number of operation and maintenance target data chains; based on the starting task node, analyze the operation and maintenance target data chains to determine the path depth of each chain node; according to the preset operation and maintenance knowledge graph, analyze a number of operation and maintenance target data chains, extract the operation and maintenance tasks corresponding to each starting task node or chain node and the dependency index between each node, construct a number of target task chains, and determine the event complexity of each target task chain and the task importance index of each target task in each target task chain; according to the path depth, dependency index, event complexity and task importance index, determine the dynamic scheduling mapping index of each target task in each target task chain; according to the dynamic scheduling mapping index of each target task, determine the large model target task set and the small model target task set, and construct a collaborative scheduling strategy for the large and small models.

[0084] The operation and maintenance target data chain can be a series of operation and maintenance indicators composed of implicit root cause indicators and explicit anomaly indicators, which are used to characterize the operation and maintenance indicators pointed to by the current over-optimization problem.

[0085] The path depth can be the number of levels between the current task node and the root cause node.

[0086] The preset operation and maintenance knowledge graph can be the knowledge graph information used to characterize the corresponding relationship between operation and maintenance indicators and operation and maintenance work. The operation and maintenance knowledge graph can be obtained through the analysis of historical operation and maintenance data and the evaluation of professional operation and maintenance personnel.

[0087] The operation and maintenance task can be the operation and maintenance work required to optimize the corresponding operation and maintenance indicators.

[0088] The dependency index can be the quantitative data used to characterize the mutual dependency relationship between operation and maintenance tasks.

[0089] The event complexity can be the quantitative index reflecting the overall resources required to process the current task chain, and the event complexity can be obtained through the estimation of the execution time scale of different operation and maintenance tasks.

[0090] The task importance index can be the index used to characterize the importance degree of the current operation and maintenance task in the overall operation and maintenance work, and the task importance index can be obtained through the estimation of the influence range of the operation and maintenance task.

[0091] The dynamic scheduling mapping index can be the core decision parameter used to determine whether a task is assigned to a large model or a small model.

[0092] The large model target task set can be the set of operation and maintenance tasks responsible for execution by the large model.

[0093] The small model target task set can be the set of operation and maintenance tasks responsible for execution by the small model.

[0094] Specifically, in the process of collaborative scheduling analysis of large and small models, the basic principle is that high-complexity operation and maintenance tasks are handled by large models, and low-complexity operation and maintenance tasks are handled by small models. This requires accurate assessment of the complexity of operation and maintenance tasks. First of all, the operation and maintenance tasks closer to the root cause node (which can be regarded as the main node) have higher complexity because the scope of influence of their operation and maintenance process spreads outwards is larger. On the contrary, the operation and maintenance tasks farther away from the root cause node have relatively lower complexity (which can be regarded as the branch and leaf nodes) because their operation and maintenance processes are relatively independent. In addition, the more the number of other operation and maintenance tasks associated with an operation and maintenance task, the higher the complexity of this operation and maintenance task because when maintaining it, more other operation and maintenance indicators need to be concerned simultaneously. Therefore, it is necessary to start from two dynamic dimensions of depth and breadth, and at the same time combine two static dimensions of the absolute complexity and importance of the operation and maintenance task itself to comprehensively evaluate the complexity of the operation and maintenance task, so as to accurately measure the actual complexity of the operation and maintenance task, and then provide accurate data basis for the collaborative scheduling analysis of large and small models. Through mathematical analysis means, according to the path depth, dependence index, event complexity and task importance index, scientifically quantify the dynamic scheduling mapping index used to reflect the comprehensive complexity of the operation and maintenance task. The larger the dynamic scheduling mapping index, the more the operation and maintenance task corresponding to this dynamic scheduling mapping index tends to use a large model. On the contrary, it means that the operation and maintenance task corresponding to this dynamic scheduling mapping index tends to use a small model. According to the comparison results between different dynamic scheduling mapping indexes and the mapping index threshold obtained by fitting historical data, determine the delivery model object of the corresponding operation and maintenance task, so as to respectively integrate and obtain the model target task set and the small model target task set, and then construct the collaborative scheduling strategy of large and small models.

[0095] Through this solution, starting from two dynamic dimensions of depth and breadth, and at the same time combining two static dimensions of the absolute complexity and importance of the operation and maintenance task itself, according to the path depth, dependence index, event complexity and task importance index, comprehensively evaluate the complexity of the operation and maintenance task, and obtain the dynamic scheduling mapping index corresponding to different target tasks, so as to accurately measure the actual complexity of the operation and maintenance task. On this basis, respectively integrate and obtain the model target task set and the small model target task set, and then construct the collaborative scheduling strategy of large and small models, so that different target tasks are highly matched with their corresponding execution model scales.

[0096] In some embodiments, according to the path depth, dependence index, event complexity and task importance index, determine the dynamic scheduling mapping index of each target task in each target task chain, specifically as the following formula (6): (6) Wherein, is the The dynamic scheduling mapping index of a target task, is the preset depth influence weight, is the path depth corresponding to the current target task, is the preset dependency influence weight, is the set of target tasks in the current target task chain that have a dependency relationship with the current target task, is the th target task in the set of target tasks, is the th target task and the th target task, and the dependency index between them, is the preset resource influence weight, is the event complexity of the target task chain corresponding to the current target task, is the task importance index corresponding to the current target task.

[0097] The preset depth influence weight can be a quantization weight used to represent the proportion of the influence of the path depth of the current target task on the dynamic scheduling mapping index.

[0098] The preset dependency influence weight is a quantization weight used to represent the proportion of the influence of the dependency relationship of the current target task on the dynamic scheduling mapping index.

[0099] The preset resource influence weight is a quantization weight used to standardize the proportion of the influence of the complexity and importance of the current target task itself on the dynamic scheduling mapping index.

[0100] The above influence weights can all be set based on the experience of professional operation and maintenance personnel, or can be obtained by fitting experimental data.

[0101] Specifically, through in formula (6) to describe the influence of the path depth of the target task on the dynamic scheduling mapping index, using is to reflect the inverse relationship between the dynamic scheduling mapping index and the path depth. The smaller the path depth, the closer the current target task is to the root cause node, and the larger the corresponding dynamic scheduling mapping index; through to describe the situation where the current target task is restricted by other operation and maintenance tasks that have a dependency relationship with it. The more restricted it is, the higher the overall complexity of the current target task, and the larger the corresponding dynamic scheduling mapping index; through to describe the linear relationship between the current target task and the event complexity and task importance index. The larger the event complexity and task importance index, the larger the corresponding dynamic scheduling mapping index; combining the above influence relationships, the dynamic scheduling mapping index is quantitatively obtained.

[0102] Through this solution, by means of mathematical analysis, based on path depth, dependence index, event complexity, and task importance index, the impact of each parameter on the complexity evaluation of the target task is clarified, and a dynamic scheduling mapping index reflecting the overall complexity of the target task is quantitatively obtained to accurately reflect the complexity of the target task, providing an accurate scientific data basis for the collaborative scheduling of large and small models.

[0103] Figure 3 FIG. 4 is a schematic structural diagram of an AIOps multi-task scheduling system driven by collaboration between large and small models provided by an embodiment of the present application. As Figure 3 shown, an AIOps multi-task scheduling system 300 driven by collaboration between large and small models in this embodiment includes: a data processing module 301, an over-optimization analysis module 302, a scheduling analysis module 303, and an operation and maintenance output module 304.

[0104] The data processing module 301 is configured to obtain a heterogeneous operation and maintenance time series data set, perform data consistency calibration on the heterogeneous operation and maintenance time series data set, and determine a multi-source standardized operation and maintenance data stream. The over-optimization analysis module 302 is configured to analyze the multi-source standardized operation and maintenance data stream, determine dynamic causal information of operation and maintenance metrics, and determine over-optimization target event information according to the dynamic causal information of the operation and maintenance metrics. The scheduling analysis module 303 is configured to determine a real-time operation and maintenance task chain according to the over-optimization target event information, and determine a collaborative scheduling strategy for large and small models according to the real-time operation and maintenance task chain. The operation and maintenance output module 304 is configured to perform real-time operation and maintenance adjustment on the system state according to the collaborative scheduling strategy for large and small models, and determine and output a collaborative operation and maintenance report.

[0105] Optionally, the data processing module 301 is specifically configured to: extract operation and maintenance time series data corresponding to different types of operation and maintenance metrics according to the heterogeneous operation and maintenance time series data set; determine the service nodes to which each operation and maintenance time series data belongs according to several pieces of the operation and maintenance time series data, and thereby determine the network communication hops between any two service nodes; determine the topological weights of different data nodes in any two pieces of the operation and maintenance time series data at corresponding time nodes according to the network communication hops; analyze several pieces of the operation and maintenance time series data, extract the timestamps corresponding to different data nodes in each piece of the operation and maintenance time series data, and determine the time difference impact factor according to the timestamps; based on several pieces of the operation and maintenance time series data, determine the minimum alignment cost between any two pieces of the operation and maintenance time series data according to the topological weights and the time difference impact factor; and perform unified alignment processing on different data nodes in several pieces of the operation and maintenance time series data according to the minimum alignment cost to construct the multi-source standardized operation and maintenance data stream.

[0106] Optionally, when determining the minimum alignment cost between any two of the operation and maintenance time series data based on a plurality of the operation and maintenance time series data according to the topological weight and the time difference impact factor, the data processing module 301 specifically uses the following formula: ; wherein, is the minimum alignment cost, is the topological weight, is the operation and maintenance time series data at the time node the observed value of the data node at, is the operation and maintenance time series data at the time node the observed value of the data node at, is the time difference impact factor.

[0107] Optionally, when determining the topological weight of different data nodes in any two of the operation and maintenance time series data at corresponding time nodes according to the network communication hop count, the data processing module 301 specifically uses the following formula: ; wherein, is the topological weight, is the service node and the service node the network communication hop count between, is a preset attenuation coefficient; When determining the time difference impact factor according to the time stamp, the following formula is specifically used: ; wherein, is the time difference impact factor, is the operation and maintenance time series data at the time node the time stamp of the data node at, the operation and maintenance time series data at the time node the time stamp of the data node at, is a preset time offset threshold.

[0108] Optionally, the over-optimization analysis module 302 is specifically configured to: analyze the multi-source standardized operation and maintenance data stream, determine the change amount of different operation and maintenance metrics at different time points, thereby determining the change rate corresponding to each operation and maintenance metric, and determine the dynamic lag time window corresponding to each operation and maintenance metric according to the change rate; based on the change amount of each operation and maintenance metric at different time points and the dynamic lag time window, determine the lag impact factor between any two operation and maintenance metrics; according to the preset index level attribution information, analyze the multi-source standardized operation and maintenance data stream, determine the level correlation index between any two operation and maintenance metrics and the collaborative impact weight of each operation and maintenance metric; based on the level correlation index and the collaborative impact weight, determine the causal correlation index between any two operation and maintenance metrics according to the dynamic lag time window and the lag impact factor; analyze the multi-source standardized operation and maintenance data stream, determine a number of obvious abnormal operation and maintenance metrics; based on the causal correlation index, analyze a number of the obvious abnormal operation and maintenance metrics, determine a number of hidden root cause metrics, and judge whether there is an over-optimization event according to a number of the obvious abnormal operation and maintenance metrics and the corresponding number of hidden root cause metrics; if there is the over-optimization event, use the corresponding number of the obvious abnormal operation and maintenance metrics and the hidden root cause metrics as the over-optimization target event information.

[0109] Optionally, when the over-optimization analysis module 302 determines the causal correlation index between any two operation and maintenance metrics based on the level correlation index and the collaborative impact weight, according to the dynamic lag time window and the lag impact factor, it is specifically the following formula: ; Wherein, is the current time point for the operation and maintenance metric and the operation and maintenance metric the causal correlation index therebetween, is the preset data dimension conversion coefficient, is the operation and maintenance metric and the operation and maintenance metric the level correlation index therebetween, is the collaborative impact weight of the operation and maintenance metric , is the dynamic lag time window, is the operation and maintenance metric at the time point the change amount thereunder, is the current time point for the operation and maintenance metric and the operation and maintenance metric the lag impact factor therebetween.

[0110] Optionally, when determining the lag impact factor between any two operation and maintenance metrics based on the change amount of each operation and maintenance metric at different time points, the over-optimization analysis module 302 specifically uses the following formula: ; Wherein, is the current time point under the operation and maintenance metric and the operation and maintenance metric the lag impact factor therebetween, is the preset maximum lag time, is the covariance calculation function, is the dynamic lag time window, is the operation and maintenance metric at the time point the change amount thereunder, is the operation and maintenance metric at the time point the change amount thereunder.

[0111] Optionally, the scheduling analysis module 303 is specifically configured to: analyze a plurality of the explicit abnormal operation and maintenance metrics and the implicit root cause metrics, use each of the implicit root cause metrics as a starting task node, and use a plurality of the explicit abnormal operation and maintenance metrics corresponding thereto as chain nodes to construct a plurality of operation and maintenance target data chains; based on the starting task node, analyze the operation and maintenance target data chains to determine the path depth of each chain node; according to the preset operation and maintenance knowledge graph, analyze the plurality of operation and maintenance target data chains, extract the operation and maintenance tasks corresponding to each starting task node or chain node and the dependency index between each node, construct a plurality of target task chains, and determine the event complexity of each target task chain and the task importance index of each target task in each target task chain; according to the path depth, the dependency index, the event complexity, and the task importance index, determine the dynamic scheduling mapping index of each target task in each target task chain; according to the dynamic scheduling mapping index of each target task, determine the large model target task set and the small model target task set, and construct the collaborative scheduling strategy for the large and small models.

[0112] Optionally, when determining the dynamic scheduling mapping index of each target task in each target task chain according to the path depth, the dependency index, the event complexity, and the task importance index, the scheduling analysis module 303 specifically uses the following formula: ; Wherein, is the dynamic scheduling mapping index of the th target task in the current target task chain, is the preset depth impact weight, is the path depth corresponding to the current target task, is the preset dependency impact weight, is the set of target tasks in the current target task chain that have a dependency relationship with the current target task, is the th target task in the set of target tasks, is the th target task and the th target task, the dependency index therebetween, is the preset resource impact weight, is the event complexity of the target task chain corresponding to the current target task, is the task importance index corresponding to the current target task.

[0113] The system of this embodiment can be used to execute the method of any of the above embodiments, and its implementation principle and technical effects are similar, which will not be elaborated here.

Claims

1. An AIOps multi-task scheduling method driven by large and small models, characterized in that: include: Obtaining a heterogeneous operation and maintenance time series data set, performing data consistency calibration on the heterogeneous operation and maintenance time series data set, and determining a multi-source standardized operation and maintenance data stream; Analyze the multi-source standardized operation and maintenance data stream to determine dynamic causal information of operation and maintenance indicators, and determine over-optimization target event information based on the dynamic causal information of operation and maintenance indicators; Determine a real-time operation and maintenance task chain according to the over-optimization target event information, and determine a large and small model collaborative scheduling strategy according to the real-time operation and maintenance task chain; According to the large and small model collaborative scheduling strategy, real-time operation and maintenance adjustments are made to the system status, and a collaborative operation and maintenance report is determined and output.

2. The method according to claim 1, characterized in that The step of performing data consistency calibration on the heterogeneous operation and maintenance time series data set to determine a multi-source standardized operation and maintenance data stream includes: Extracting operation and maintenance time series data corresponding to different types of operation and maintenance indicators according to the heterogeneous operation and maintenance time series data set; According to the plurality of operation and maintenance time series data, determining the service node to which each operation and maintenance time series data belongs, and thereby determining the number of network communication hops between any two service nodes; Determine the topological weights of different data nodes in any two of the operation and maintenance time series data at corresponding time nodes according to the network communication hop count; Analyze the plurality of operation and maintenance time series data, extract timestamps corresponding to different data nodes in each of the operation and maintenance time series data, and determine a time difference influencing factor according to the timestamps; Based on the plurality of operation and maintenance time series data, determining the minimum alignment cost between any two of the operation and maintenance time series data according to the topology weight and the time difference impact factor; According to the minimum alignment cost, a unified alignment process is performed on different data nodes in a number of the operation and maintenance time series data to construct the multi-source standardized operation and maintenance data stream.

3. The method according to claim 2, characterized in that The minimum alignment cost between any two of the operation and maintenance time series data is determined based on the plurality of operation and maintenance time series data according to the topology weight and the time difference impact factor, specifically as follows: ； in, is the minimum alignment cost, is the topological weight, The operation and maintenance time series data At the time point The observation value of the data node at The operation and maintenance time series data At the time point The observation value of the data node at is the time difference influencing factor.

4. The method according to claim 2, characterized in that: The topological weights of any two different data nodes in the operation and maintenance time series data at corresponding time nodes are determined according to the network communication hop count, specifically as follows: ； in, The topological weight, For service nodes With service node The number of network communication hops between is the preset attenuation coefficient; The time difference influencing factor is determined according to the timestamp, specifically as follows: ； in, is the time difference influencing factor, The operation and maintenance time series data At the time point The timestamp of the data node at The operation and maintenance time series data At the time point The timestamp of the data node at is the preset time offset threshold.

5. The method according to claim 3, characterized in that: The analyzing the multi-source standardized operation and maintenance data stream to determine the dynamic causal information of the operation and maintenance indicators, and determining the optimized target event information according to the dynamic causal information of the operation and maintenance indicators, includes: Analyze the multi-source standardized operation and maintenance data streams to determine the changes of different operation and maintenance indicators at different time points, thereby determining the change rate corresponding to each operation and maintenance indicator, and determine the dynamic lag time window corresponding to each operation and maintenance indicator according to the change rate; Determine the hysteresis impact factor between any two operation and maintenance indicators based on the change amount of each operation and maintenance indicator at different time points and the dynamic hysteresis time window; According to the preset indicator hierarchical attribution information, the multi-source standardized operation and maintenance data stream is analyzed to determine the hierarchical correlation index between any two operation and maintenance indicators and the synergistic impact weight of each operation and maintenance indicator; Based on the hierarchical association index and the synergistic influence weight, determining a causal association index between any two operation and maintenance indicators according to the dynamic hysteresis time window and the hysteresis influence factor; Analyze the multi-source standardized operation and maintenance data streams to determine several explicit abnormal operation and maintenance indicators; Based on the causal correlation index, analyzing the plurality of explicit abnormal operation and maintenance indicators, determining a plurality of implicit root cause indicators, and judging whether an over-optimization event exists according to the plurality of explicit abnormal operation and maintenance indicators and the corresponding plurality of implicit root cause indicators; If the over-optimization event exists, the corresponding plurality of explicit abnormal operation and maintenance indicators and the implicit root cause indicators are used as the over-optimization target event information.

6. The method according to claim 5, characterized in that The causal correlation index between any two operation and maintenance indicators is determined based on the hierarchical correlation index and the synergistic influence weight according to the dynamic lag time window and the lag influence factor, specifically as follows: ； in, For the current time point Operation and maintenance indicators and operation and maintenance indicators The causal association index between is the preset data dimension conversion coefficient, Operation and maintenance indicators and operation and maintenance indicators The hierarchical correlation index between Operation and maintenance indicators The synergistic impact weights, is the dynamic hysteresis time window, Operation and maintenance indicators At the point in time The amount of change under For the current time point Operation and maintenance indicators and operation and maintenance indicators The lag influence factor between .

7. The method according to claim 5, characterized in that The lag impact factor between any two operation and maintenance indicators is determined based on the change amount of each operation and maintenance indicator at different time points, specifically as follows: ； in, For the current time point Operation and maintenance indicators and operation and maintenance indicators The hysteresis effect factor between To preset the maximum delay time, is the covariance calculation function, is the dynamic hysteresis time window, Operation and maintenance indicators At the point in time The amount of change under Operation and maintenance indicators At the point in time The amount of change below.

8. The method according to claim 7, characterized in that Determining a real-time operation and maintenance task chain according to the over-optimization target event information, and determining a large and small model collaborative scheduling strategy according to the real-time operation and maintenance task chain, includes: Analyze the plurality of explicit abnormal operation and maintenance indicators and the implicit root cause indicators, take each implicit root cause indicator as a starting task node, and use the plurality of explicit abnormal operation and maintenance indicators corresponding thereto as chain nodes to construct a plurality of operation and maintenance target data chains; Based on the starting task node, analyzing the operation and maintenance target data chain, and determining the path depth of each chain node; According to the preset operation and maintenance knowledge graph, analyze several operation and maintenance target data chains, extract the operation and maintenance tasks corresponding to each starting task node or chain node and the dependency index between each node, construct several target task chains, and determine the event complexity of each target task chain and the task importance index of each target task in each target task chain; Determining a dynamic scheduling mapping index of each target task in each target task chain according to the path depth, the dependency index, the event complexity and the task importance index; According to the dynamic scheduling mapping index of each target task, a large model target task set and a small model target task set are determined, and the large and small model collaborative scheduling strategy is constructed.

9. The method according to claim 8, characterized in that The dynamic scheduling mapping index of each target task in each target task chain is determined according to the path depth, the dependency index, the event complexity and the task importance index, specifically as follows: ； in, The first task in the current target task chain The dynamic scheduling mapping index of the target task, To preset the depth influence weight, is the path depth corresponding to the current target task, To preset dependency influence weights, is a set of target tasks in the current target task chain that have a dependency relationship with the current target task, is the first target tasks, For the The target task and The dependency index between target tasks, To preset resource impact weights, is the event complexity of the target task chain corresponding to the current target task, is the task importance index corresponding to the current target task.

10. An AIOps multi-task scheduling system driven by large and small models, characterized in that: include: A data processing module is used to obtain a heterogeneous operation and maintenance time series data set, perform data consistency calibration on the heterogeneous operation and maintenance time series data set, and determine a multi-source standardized operation and maintenance data stream; An over-optimization analysis module, used to analyze the multi-source standardized operation and maintenance data stream, determine the dynamic causal information of the operation and maintenance indicators, and determine the over-optimization target event information according to the dynamic causal information of the operation and maintenance indicators; A scheduling analysis module, used to determine a real-time operation and maintenance task chain according to the over-optimization target event information, and determine a large and small model collaborative scheduling strategy according to the real-time operation and maintenance task chain; The operation and maintenance output module is used to perform real-time operation and maintenance adjustments on the system status according to the large and small model collaborative scheduling strategy, and determine and output a collaborative operation and maintenance report.

Images