Fault root cause dynamic prediction method and system based on probability propagation reasoning

Abstract

The invention provides a fault root cause dynamic prediction method and system based on probability propagation reasoning, and relates to the technical field of fault positioning prediction, and the method comprises the steps: constructing a directed graph structure, associating each node with a dynamic fault probability, and constructing a fault state expression system; based on the fault state expression system, calculating and dynamically updating an edge weight, and constructing a dynamic propagation graph model; generating fault occurrence probabilities of the monitoring data, and fusing the fault occurrence probabilities to obtain aligned unified probability data; on the basis of a dynamic propagation graph model, on-graph probability propagation reasoning is carried out by using unified probability data, a final root cause is determined, and rapid fault positioning is realized; an intelligent self-healing and strategy optimization algorithm based on reinforcement learning is introduced, a repair strategy is automatically generated and executed, a decision is continuously optimized through online learning, and a self-evolution safety operation and maintenance system is formed. According to the invention, accurate and rapid prediction and positioning of system faults are realized.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of fault location prediction, in particular to a fault root cause dynamic prediction method and system based on probabilistic propagation reasoning. BACKGROUND

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

[0003] With the deepening of the digitization process in the government field, the internal logic of the information system supporting business operation is becoming increasingly complex, and the dependency relationship between components presents a highly dynamic and meshed characteristic. In such an environment, the abnormality of any component state can quickly spread through the dependency chain, resulting in a large area of business function being damaged. The existing mainstream fault analysis scheme usually relies on centralized analysis of multi-dimensional monitoring indicators and log data. However, these methods have the following inherent limitations in the face of complex and dynamic system environments from the perspective of data analysis: (1) Consistency and reliability of multi-source data. The state data used for analysis comes from multiple independent collection processes or computing engines, and these data have inherent differences in generation time, collection period and calculation logic. When directly aggregated and analyzed, the data itself has internal contradictions due to time offset, non-uniform dimension and unknown confidence, resulting in a distorted system state view based on contradictory data.

[0004] (2) Insufficient root cause quantization accuracy. Generally, FTA (Fault Tree Analysis) algorithm is used for cause positioning, but this fault analysis algorithm has defects. On the one hand, it does not verify the authenticity of the fault basic event in combination with multi-source data, which is prone to one-sided information judgment. On the other hand, it lacks a dynamic adjustment mechanism, making it difficult to cope with the impact of system dynamic changes (such as resource scheduling and business iteration) on fault correlation, resulting in insufficient accuracy of root cause judgment.

[0005] (3) Insufficient explainability and quantization accuracy of root cause inference process. Traditional analysis methods often rely on pre-set rules or simple probability statistics when selecting the root cause from a large number of alarm events, lacking a comprehensive model that can quantitatively evaluate the importance of each potential cause. This results in an "black box" inference process, which cannot provide clear and quantitative priority ranking among multiple possible root causes, thereby affecting the efficiency of fault decision-making. SUMMARY

[0006] To solve the above problems, the present disclosure proposes a fault root cause dynamic prediction method and system based on probabilistic propagation reasoning, which constructs a dynamic propagation graph model that can perceive system state changes, integrates multi-source heterogeneous data, and performs quantifiable probabilistic propagation reasoning, ultimately achieving accurate and dynamic positioning and prediction of root causes.

[0007] According to some embodiments, the present disclosure adopts the technical solutions as follows: A fault root cause dynamic prediction method based on probabilistic propagation reasoning, comprising: establishing a globally unique identifier for each component and obtaining its dependency relationship; based on the dependency relationship, defining node types and constructing a directed graph structure, associating each node with a dynamic fault probability, and constructing a fault state expression system; based on the fault state expression system, introducing a dynamic factor reflecting the real-time state of the system, calculating and dynamically updating the edge weight, and constructing a dynamic propagation graph model; obtain multi-dimensional monitoring data, convert the original data into standardized fault probability through a pre-defined index-probability mapping function, and process multi-source data using a fusion strategy to obtain aligned unified probability data; based on the dynamic propagation graph model, using the unified probability data to perform graph probability propagation calculation, deducing the fault probability of each component, and extracting a root cause candidate set; introducing a key importance weighted model to multi-dimensionally quantify and sort the root cause candidate set, and predicting and positioning the final root cause according to the sorting result; introducing an intelligent self-healing and strategy optimization algorithm based on reinforcement learning, automatically generating a repair strategy based on the final root cause and executing it, while continuously optimizing the decision through online learning, forming a self-evolving operation and maintenance closed loop.

[0008] According to some embodiments, the present disclosure adopts the technical solutions as follows: A fault root cause dynamic prediction system based on probabilistic propagation reasoning, comprising: an initialization module for establishing a globally unique identifier for each component and obtaining its dependency relationship; a fault dependency modeling module for defining node types and constructing a directed graph structure based on the dependency relationship, associating each node with a dynamic fault probability, and constructing a fault state expression system; based on the fault state expression system, introducing a dynamic factor reflecting the real-time state of the system, calculating and dynamically updating the edge weight, and constructing a dynamic propagation graph model; a multi-source data alignment module for obtaining multi-dimensional monitoring data, converting the original data into standardized fault probability through a pre-defined index-probability mapping function, and processing multi-source data using a fusion strategy to obtain aligned unified probability data; a reasoning and root cause positioning module for based on the dynamic propagation graph model, using the unified probability data to perform graph probability propagation calculation, deducing the fault probability of each component, and extracting a root cause candidate set; introducing a key importance weighted model to multi-dimensionally quantify and sort the root cause candidate set, and predicting and positioning the final root cause according to the sorting result; The reinforcement learning optimization module is used for introducing a reinforcement learning-based intelligent self-recovery and strategy optimization algorithm, automatically generating a repair strategy based on a final root cause and executing the repair strategy, and continuously optimizing decisions through online learning to form a self-evolving operation and maintenance closed loop.

[0009] According to some embodiments, the present disclosure adopts the technical scheme as follows: A non-transitory computer-readable storage medium is used to store computer instructions, which are executed by a processor to implement the fault root cause dynamic prediction method based on probabilistic propagation reasoning.

[0010] According to some embodiments, the present disclosure adopts the technical scheme as follows: An electronic device includes a processor, a memory, and a computer program; the processor is connected with the memory, and the computer program is stored in the memory; when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to implement the fault root cause dynamic prediction method based on probabilistic propagation reasoning.

[0011] Compared with the prior art, the present disclosure has the beneficial effects that: The fault root cause dynamic prediction method based on probabilistic propagation reasoning of the present disclosure significantly improves the accuracy and reliability of fault root cause positioning in a complex dependent environment by constructing a dynamic propagation graph model that fuses real-time state factors and converting multi-source heterogeneous data into unified probabilistic input; further introducing a key importance quantitative ranking and an intelligent self-recovery mechanism driven by reinforcement learning not only realizes accurate and rapid positioning of faults, but also forms an autonomous closed loop from diagnosis to repair, effectively reduces the mean time to recovery (MTTR) of the system, and improves the continuity and overall operation and maintenance resilience of the government business system.

[0012] The fault root cause dynamic prediction method based on probabilistic propagation reasoning of the present disclosure upgrades the system state from a static snapshot to a dynamic image, making the simulation of the fault propagation path more consistent with the real operating conditions of the complex system, and effectively overcoming the problem of insufficient root cause judgment accuracy caused by the inability of traditional static models to perceive internal dynamic changes of the system.

[0013] The fault root cause dynamic prediction method based on probabilistic propagation reasoning of the present disclosure adopts a multi-source data alignment strategy based on a probabilistic time window and a confidence decay mechanism, which can effectively reconcile the differences in time and credibility from different data sources, solve the analysis distortion caused by internal contradictions in the data, and provide high-quality and consistent probabilistic input for subsequent reasoning, thereby guaranteeing the reliability of the fault determination result from the source.

[0014] The fault root cause dynamic prediction method based on probabilistic propagation reasoning of the present disclosure can quantitatively evaluate the cumulative and diffusion effects of the fault on the complex dependency link by performing probabilistic propagation reasoning on the multi-element aligned fault probability data on the dynamic propagation graph, thereby revealing the root cause hidden behind the local phenomenon systematically rather than treating the alarm of a single node in isolation, and greatly improving the ability to predict the real fault source in the complex components.

[0015] The fault root cause dynamic prediction method based on probabilistic propagation reasoning of the present disclosure introduces a key importance weighting model to perform multi-dimensional quantitative sorting of the root cause candidate set by fusing cut set probability, node influence range and data credibility, thereby providing clear and quantitative decision basis for the operation and maintenance personnel, avoiding one-sidedness of judgment based on probability level or experience, and realizing accurate screening of the root cause and effective differentiation of the priority.

[0016] The fault root cause dynamic prediction method based on probabilistic propagation reasoning of the present disclosure introduces an intelligent self-healing and strategy optimization algorithm based on reinforcement learning to construct a complete autonomous closed loop from fault diagnosis to repair execution, and the system can automatically select and execute the optimal recovery strategy based on historical experience, and continuously optimize the decision through online learning, thereby forming a self-evolving safe operation and maintenance system, significantly reducing the dependence on manual intervention, and improving the system resilience and business continuity. BRIEF DESCRIPTION OF DRAWINGS

[0017] The accompanying drawings, which form a part of this disclosure, are intended to provide further understanding of the present disclosure and are incorporated herein for illustrative purposes. The schematic embodiments of the present disclosure and the description thereof are used to explain the present disclosure and do not constitute an improper limitation on the present disclosure.

[0018] Figure 1 The flowchart of the fault root cause dynamic prediction method based on probabilistic propagation reasoning of the present disclosure. DETAILED DESCRIPTION

[0019] The present disclosure will be further described below in conjunction with the accompanying drawings and embodiments.

[0020] It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the present disclosure. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as generally understood by those skilled in the art to which the present disclosure belongs.

[0021] It is to be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments consistent with the present disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and / or "comprising," when used in this specification, specify the presence of stated features, steps, operations, elements, components, and / or groups thereof, but do not preclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof.

[0022] Embodiment 1 In one embodiment of the present disclosure, a fault root cause dynamic prediction method based on probabilistic propagation reasoning is provided, and the method steps include: Step 1: Establish a globally unique identifier for each component and obtain its dependency relationship; Step 2: Based on the dependency relationship, define component types and construct a directed graph structure, associate a dynamic failure probability with each node in the graph, and construct a fault state expression system; Step 3: Based on the fault state expression system, introduce a dynamic factor reflecting the real-time state of the system, calculate and continuously update the weight of the edges in the graph, and construct a dynamic propagation graph model; Step 4: Obtain monitoring data, generate fault occurrence probability of monitoring data through a set of index-probability mapping functions, and process multi-source data using a fusion strategy to obtain aligned unified probability data; Step 5: Based on the dynamic propagation graph model, use the unified probability data to perform graph probability propagation calculation, deduce the failure probability of all components in the system, extract the root cause candidate set, introduce a key importance weighted model to multi-dimensionally quantify and sort each root cause candidate set, and predict and locate the final root cause according to the sorting result; Step 6: Introduce an intelligent self-healing and strategy optimization algorithm based on reinforcement learning, automatically generate a repair strategy based on the final root cause and execute it, and continuously optimize the decision through online learning to form a self-evolving operation and maintenance closed loop.

[0023] As an embodiment, the fault root cause dynamic prediction method based on probabilistic propagation reasoning of the present disclosure combines a multi-source data cross-validation method to solve the inherent contradictions of multi-source data, and further constructs a dynamic fault propagation graph model, calculates a minimum cut set, quantifies key importance, and updates dynamically to achieve accurate and rapid prediction and positioning of complex system failures. The specific implementation process is as follows: Step 1: Establish a globally unique identifier for each component and obtain its dependency relationship; Specifically, configuration management technology is used to establish a globally unique identifier for each logical component in the system and obtain its dependency relationship; The configuration management library, serving as the core carrier of component dependencies, assigns unique asset numbers to all monitored objects and records their dependencies. This provides accurate node, edge, and topology data support for the subsequent construction of a dynamic propagation graph model. The process includes: The monitoring targets cover all logical components of the business system, including application services, data middleware, and computing instances. Each monitored object is assigned a globally unique asset number, which serves as a unique identifier during fault reasoning. Dynamic dependencies between components are acquired and recorded, ultimately forming a continuously updated configuration item library containing unique asset numbers and dependencies, as detailed below: Step 11: Asset Unified Coding and Registration.

[0024] It covers the entire stack of business system resources, including application services (such as order services), middleware (such as Redis clusters), and host instances (such as DC01-SVR-001). Each monitored object (component) is assigned a globally unique asset number (such as BE001, NET002), which serves as its unique identifier (event_id) in the subsequent fault reasoning process.

[0025] Step 12: Dependency storage and graphing.

[0026] The configuration management repository not only stores the static properties of components, but more importantly, it records the dynamic dependencies between components (such as "order service depends on Redis cluster" and "data processing task runs on Spark executor"). These dependencies form a directed graph, where nodes are components and edges represent the direction of dependency (such as "depends on" and "runs on"). This graph forms the structural basis for building a fault propagation graph.

[0027] Step 13: Data health and real-time synchronization mechanism.

[0028] To ensure the reliability of the configuration management database data, a health status monitoring and real-time synchronization mechanism has been established, including: (1) Health monitoring: The configuration management library service is checked every minute. If it fails 3 times in a row, a high-level alarm is triggered and the most recent dependency snapshot cached in each data receiving module is enabled to ensure that the inference process is not interrupted.

[0029] (2) Automatic Synchronization: Integrated with Infrastructure as Code (IaC) tools (such as Terraform) and service discovery systems (such as Consul). Any infrastructure or application deployment changes will be automatically synchronized to the configuration management repository within 5 minutes, ensuring the timeliness of the dependency graph. All change records are timestamped to distinguish between missing data and normal maintenance in step 3.

[0030] Ultimately, a continuously updated configuration item library containing unique asset IDs and dependencies is obtained, providing a complete set of nodes (V), edges (E), and topology for the subsequent construction of a dynamic propagation graph model.

[0031] Step 2: Based on the aforementioned dependencies, define node types and construct a directed graph structure, associating each node with a dynamic fault probability to build a fault state representation system; based on the fault state representation system, introduce dynamic factors reflecting the real-time state of the system, calculate and dynamically update edge weights, and construct a dynamic propagation graph model, specifically including: Step 21: Graph structure construction and node definition.

[0032] Based on the asset dependencies and business logic registered in the configuration management database in step 1, a directed graph G = (V, E) is constructed. Through weekly loop detection (using the Tarjan algorithm to identify strongly connected components (SCCs), if a loop dependency is found, the SCCs are merged into a super node or a virtual node is inserted to break the loop, ensuring convergence of the inference process. Here, the node set V represents all possible failure events in the system, and the edge set E represents the propagation relationships between failures.

[0033] Furthermore, nodes are divided into three types: root nodes correspond to basic components in the configuration management library, and their status is directly driven by monitoring data; propagation nodes represent logical entities such as services and middleware, and have the ability to receive and forward faults; and aggregation nodes represent system-level business faults and are the endpoints of fault propagation. Each node is associated with a dynamic fault probability. This probability changes over time and is affected by multi-source monitoring data, forming a complete fault state expression system.

[0034] Step 22: Dynamic edge weights and dynamic propagation graph model.

[0035] Side Indicates a fault from node Towards The path of propagation, and its weight It is a dynamic variable, determined by the structure weights learned from historical fault data, real-time load, and call or processing latency. The weight calculation formula is as follows:

[0036] in, It is a structural weight learned from historical fault data, reflecting the inherent tendency of fault propagation; It is a node The load rate at the current moment; It is a node Maximum load; Is currently from Towards Network latency; This is the latency sensitivity factor, typically ranging from 50 to 100 ms. It is the Sigmoid function, used to map the load factor to an influence factor between [0,1].

[0037] By weighting Dynamic monitoring can capture the impact of load and latency during fault propagation in real time. It can calculate and dynamically update edge weights within a set time period, thereby updating the propagation graph model and obtaining a dynamic propagation graph model, overcoming the shortcomings of traditional static models.

[0038] Step 23: Online learning and dynamic adjustment.

[0039] To adapt to changes in the system environment, a robust online learning mechanism was established. Edge weights were calculated and dynamically updated over a set time period.

[0040] As one example, the edge weights are updated every 5 minutes. It reflects the latest network status and load conditions; every day at midnight, based on the fault data of the past 24 hours, the structural weights are updated using the maximum likelihood estimation method. Weekly reassessment of data source credibility weights This ensures the accuracy of multi-source data fusion.

[0041] Step 3: Acquire multi-dimensional monitoring data, convert the raw data into standardized fault probabilities through a predefined indicator-probability mapping function, and use a fusion strategy to process multi-source data to obtain aligned unified probability data; Specifically, in the complex system architecture of this disclosure, the monitoring data collected from various data sources exhibit time skew and confidence level differences. To achieve high-precision fault reasoning, this disclosure proposes a multi-source data alignment method based on probabilistic time windows to provide standardized input for the dynamic propagation graph model. This method achieves unified processing of multi-source monitoring data through time window alignment, probabilistic fusion calculation, and confidence level decay mechanism, as detailed below: Step 31: The probability of failure in the monitoring data is calculated based on the monitoring indicators, which is generated through a predefined indicator-probability mapping function.

[0042] Monitoring data is stored in the `multi_source_data` table, whose structure includes the following fields: `event_id` (asset ID), `source_node` (source node), `timestamp` (time stamp), `status` (status), `raw_data` (raw data), `probability` (probability of failure), and `confidence` (confidence level). The `probability` field represents the probability of a failure occurring, calculated based on monitoring metrics, and is generated using a predefined metric-probability mapping function.

[0043] (1) For continuous monitoring metrics (such as CPU utilization, memory utilization, network latency, etc.), a piecewise function is used for mapping:

[0044] in, To monitor indicator values, This represents the lower limit of the normal range for the indicator. This represents the upper limit of the abnormal threshold for the indicator. The intermediate threshold, This is the curve steepness coefficient, which controls the rate of probability growth.

[0045] (2) For discrete monitoring metrics (such as service status, port status, etc.), a direct mapping method is used:

[0046] Step 32: Merge the failure occurrence probabilities to obtain unified probability data.

[0047] Specifically, time alignment uses a dynamic sliding window mechanism. The earliest acquisition time is used as the criterion. Set a time window as a baseline. (Default 5 seconds), window size dynamically adjusts based on network latency. For monitoring data of the same asset number, if its timestamp meets the requirements... If the data sources are not identical, they are included in the same processing window. Within the window period, the probability values ​​of fault occurrence reported by each data source are aggregated and calculated. The overall fault probability is calculated using the following formula:

[0048] in, The probability of failure after fusion. This represents the total number of data sources that reported valid data during this window period. For the first k The original probability of failure occurrence calculated by each data source based on its monitoring metrics; weights For the first kThe confidence weights of each data source are set in the range of [0,1], with the initial values ​​based on the historical accuracy of the data source.

[0049] Furthermore, the missing data handling employs an exponential decay model, where the confidence weight of a data source decays exponentially when it fails to report data for an extended period.

[0050] in, The weight at the current moment, As the initial weights, This is the attenuation coefficient (default value is 0.1 / minute). To determine the duration of continuous data loss, we queried the CMDB configuration change records to rule out data loss due to system maintenance.

[0051] Furthermore, the final output data format includes the following fields: event_id (asset ID), timestamp (aligned timestamp), probability (fusion probability), confidence (overall confidence level), and data_source_count (number of valid data sources). The overall confidence level is calculated as follows, reflecting the overall credibility of the multi-source data fusion results:

[0052] in, This represents the overall confidence level, reflecting the credibility of the multi-source data fusion results.

[0053] Step 4: Based on the dynamic propagation graph model, perform graph-based probability propagation calculations using unified probability data to deduce the failure probability of each component and extract a root cause candidate set; introduce a key importance weighted model to perform multi-dimensional quantitative ranking of the root cause candidate set, and predict and locate the final root cause based on the ranking results, as follows: Step 41: Propagation reasoning of fault probability on the graph.

[0054] Based on the constructed dynamic propagation graph model, the unified probability data output in step 32 is used as the initial failure probability input for the root node (basic component) in the graph. Subsequently, probability propagation calculations are performed on the graph to deduce the real-time failure probabilities of all components (all nodes in the graph) in the system. The propagation process employs a hybrid strategy combining backward reasoning and forward propagation. Backward reasoning starts from the business node (convergence node) where anomalies have been observed, tracing back along dependency edges to identify possible root causes of failures; forward propagation starts from the root node identified as having a high probability of failure, simulating the path and impact of the failure spreading downstream along the dependency chain. This hybrid strategy simultaneously considers the bottom-up propagation path of the failure and the top-down impact range of business dependencies, ensuring the comprehensiveness of the reasoning.

[0055] Each node Failure probability Through all its upstream nodes Fault probability and edge weight The calculation shows that:

[0056] in, Represents a node The set of all upstream nodes, The dynamic edge weights are calculated in step 22. upstream node The formula represents the probability of failure. It reflects the cumulative effect of failure propagation in the system and can accurately reflect the failure state under complex dependencies.

[0057] Step 42: Extract the root cause candidate set.

[0058] Based on the dynamic propagation graph model constructed in step 2, the convergence node of interest (i.e., system-level business failure) is regarded as the top event of the fault tree, and the propagation path from the convergence node to all its reachable root nodes is logically regarded as a fault tree. Based on this fault tree view, combined with the real-time failure probability of each node calculated in step 41, all minimum cut sets corresponding to the current top event are extracted as root cause candidate sets.

[0059] The minimal cut set refers to the smallest set of basic events that can lead to the top event; each cut set represents a possible combination of failures. The specific process is as follows: First, starting from the top event, the fault tree is traversed layer by layer downwards to identify all basic event combinations that led to the top event. Second, a dynamic update mechanism is used to ensure that the cut set is consistent with the current system state. For each cut set... Calculate their joint failure probability:

[0060] in, For cut set The basic events included (i.e., the bottom events in the fault tree, corresponding to the root node in the dynamic propagation graph model). For basic events The current failure probability (this probability value has been calculated and updated during the full-graph probability propagation in step 41), this joint probability This reflects the possibility that the top event is caused by the combination of these basic events.

[0061] Step 43: Introduce a key importance weighted model to perform multi-dimensional quantitative ranking of each root cause candidate set.

[0062] To improve the accuracy of root cause localization, a key importance weighted model is introduced to perform multi-dimensional quantitative ranking of each root cause candidate set.

[0063] Key importance Taking into account factors such as cut set probability, node influence factor, and data source credibility, the calculation formula is as follows:

[0064] in, For cut set The combined failure probability; The number of basic events in the cut set; For nodes The impact factor represents the scope of the system's impact from the node's failure. For nodes The confidence level of multi-source data fusion reflects the reliability of the node's failure probability.

[0065] This formula comprehensively evaluates the root cause probability of each cut set from three dimensions: probability, scope of influence, and data credibility, thereby achieving accurate ranking of root causes.

[0066] Step 44: Final root cause prediction and output.

[0067] Based on the ranking results by importance, select the top-ranked... K The cut set as the root cause candidate set ( K Configurable (default is 3), and final confirmation is performed using a multi-source data cross-validation mechanism. The validation rules are as follows: If all basic events in a cut set are simultaneously identified as faulty by multiple data sources, then the cut set is identified as the root cause. If multiple cut sets satisfy the conditions, the cut set with the highest criticality is selected as the final root cause. The output includes a list of root cause cutsets, the critical importance of each cutset, and the multi-source data identifiers supporting the determination. The final output format is shown in Table 1.

[0068] Table 1 Final Output Format

[0069] Step 5: Introduce a reinforcement learning-based intelligent self-healing and strategy optimization algorithm to automatically generate and execute repair strategies based on the root cause, while continuously optimizing decisions through online learning to form a self-evolving operation and maintenance closed loop.

[0070] This disclosure introduces an intelligent self-healing and strategy optimization module based on reinforcement learning to achieve a closed loop from "rapid fault location" to "autonomous fault repair" and improve the overall resilience of complex systems. This module receives the root cause cut set output from step 4, automatically generates and executes repair strategies, and continuously optimizes its decisions through online learning, forming a self-evolving security operation and maintenance system. Details are as follows: Step 51: Self-healing strategy knowledge base and action generation.

[0071] Construct a strategy knowledge base for fault self-healing, in which each strategy includes: applicable root cause pattern (e.g., MCS001: database master node failure), execution action (e.g., "restart database service", "switch to standby node"), pre-execution conditions (e.g., "standby node has sufficient resources"), expected recovery time, historical success rate, and other information.

[0072] Once the intelligent decision-making module confirms the root cause cut set, it automatically triggers strategy retrieval: based on the root cause cut set ID (e.g., MCS001) and the current system status (e.g., load, resource utilization), it matches the Top-N most suitable repair strategies from the knowledge base. If there is no complete match in the knowledge base, a strategy recommendation based on graph similarity is adopted: the similarity between the current fault propagation graph and historical case graphs is calculated, and historical strategies with a similarity higher than a threshold (e.g., 0.85) are recommended.

[0073] Step 52: Reinforcement learning-driven strategy decision-making and execution.

[0074] (1) First, construct the reinforcement learning model framework: State (S): A state vector composed of the output root cause cut set list, node failure probability, system real-time load, network quality indicators, etc.

[0075] Action (A): A set of remediation strategies that can be executed in the knowledge base (e.g., action a1: restart service, action a2: traffic switching).

[0076] Reward (R): Designing a multi-dimensional reward function: Used to encourage rapid recovery; Used to encourage low-cost operations; Used to encourage low-risk operations; .

[0077] (2) Online decision-making and learning: The PPO (Proximal Policy Optimization) algorithm is used to train the RL agent so that it can select the optimal action A in the current state S.

[0078] The reward R is calculated based on the final recovery result (whether it was successful, the time taken, and the resource consumption), and the agent's policy network is updated accordingly to achieve experience accumulation and policy optimization.

[0079] The final output is a fault self-healing execution dashboard, as shown in Table 2.

[0080] Table 2 Example of Fault Self-Healing Execution Kanban

[0081] Example 2 One embodiment of this disclosure provides a dynamic fault root cause prediction system based on probability propagation reasoning, including: The initialization module is used to establish globally unique identifiers for each component and obtain its dependencies. The fault dependency modeling module is used to define node types and construct a directed graph structure based on the dependency relationship, associate each node with a dynamic fault probability, and construct a fault state expression system; based on the fault state expression system, a dynamic factor reflecting the real-time state of the system is introduced, the edge weights are calculated and dynamically updated, and a dynamic propagation graph model is constructed. The multi-source data alignment module is used to acquire multi-dimensional monitoring data. It converts the raw data into standardized fault probabilities through a predefined indicator-probability mapping function, and uses a fusion strategy to process the multi-source data to obtain aligned unified probability data. The reasoning and root cause localization module is used to perform graph probability propagation calculations based on the dynamic propagation graph model and the unified probability data, to infer the failure probability of each component and extract the root cause candidate set; a key importance weighting model is introduced to perform multi-dimensional quantitative ranking of the root cause candidate set, and the final root cause is predicted and located based on the ranking results. The reinforcement learning optimization module introduces intelligent self-healing and strategy optimization algorithms based on reinforcement learning. It automatically generates and executes repair strategies based on the root cause, and continuously optimizes decisions through online learning, forming a self-evolving operation and maintenance closed loop.

[0082] Example 3 One embodiment of this disclosure provides a non-transitory computer-readable storage medium for storing computer instructions, which, when executed by a processor, implement the aforementioned dynamic prediction method for root causes of faults based on probability propagation reasoning.

[0083] Example 4 One embodiment of this disclosure provides an electronic device, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to perform the aforementioned dynamic prediction method for root causes of faults based on probability propagation reasoning.

[0084] This disclosure is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create a machine for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0085] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0086] While the specific embodiments of this disclosure have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of this disclosure. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of this disclosure are still within the scope of protection of this disclosure.

Claims

1. A dynamic prediction method for root causes of failures based on probability propagation reasoning, characterized in that, include: Establish globally unique identifiers for each component and obtain its dependencies; Based on the aforementioned dependencies, node types are defined and a directed graph structure is constructed, with each node associated with a dynamic fault probability, thus building a fault state representation system. Based on the fault state representation system, a dynamic factor reflecting the real-time state of the system is introduced, the edge weights are calculated and dynamically updated, and a dynamic propagation graph model is constructed. Acquire multi-dimensional monitoring data, convert the raw data into standardized fault probabilities through a predefined indicator-probability mapping function, and use a fusion strategy to process multi-source data to obtain aligned unified probability data; Based on the dynamic propagation graph model, the unified probability data is used to perform graph-based probability propagation calculations to deduce the failure probability of each component and extract a root cause candidate set; a key importance weighting model is introduced to perform multi-dimensional quantitative ranking of the root cause candidate set, and the final root cause is predicted and located based on the ranking results. We introduce an intelligent self-healing and strategy optimization algorithm based on reinforcement learning. Based on the root cause, we automatically generate and execute repair strategies. At the same time, we continuously optimize decisions through online learning, forming a self-evolving operation and maintenance closed loop.

2. The fault root cause dynamic prediction method based on probability propagation reasoning as described in claim 1, characterized in that, The process of establishing globally unique identifiers for each component and obtaining its dependencies includes: The monitored objects cover all logical components of the business system, including application services, data middleware, and computing instances; Each monitored object is assigned a globally unique asset number, which serves as a unique identifier during the fault reasoning process. The system acquires and records the dynamic dependencies between components, forming a continuously updated configuration item library containing unique asset IDs and dependencies.

3. The fault root cause dynamic prediction method based on probability propagation reasoning as described in claim 1, characterized in that, Based on the aforementioned dependencies, node types are defined and a directed graph structure is constructed. Each node is associated with a dynamic fault probability, thus building a fault state representation system, including: Based on a configuration item library with global asset dependencies, a directed graph structure is constructed, where the nodes of the directed graph structure are assets. Nodes are divided into three types: root nodes correspond to infrastructure layer assets in the configuration item library, and their status is directly driven by monitoring data; propagation nodes represent service and middleware logical entities, and have the ability to receive and forward faults; and aggregation nodes represent system-level business faults and are the endpoints of fault propagation. Each node is associated with a dynamic failure probability, which changes over time and is affected by multi-source monitoring data, forming a complete failure state expression system.

4. The fault root cause dynamic prediction method based on probability propagation reasoning as described in claim 1, characterized in that, Based on the fault state representation system, a dynamic factor reflecting the real-time state of the system is introduced, edge weights are calculated and dynamically updated, and a dynamic propagation graph model is constructed, including: Edges are represented as paths through which a fault propagates from one node to other nodes; The weights of the edges are dynamic variables, determined by the structural weights learned from historical fault data and the real-time load, call or processing latency. Calculate and dynamically update edge weights within a set time period to construct a dynamic propagation graph model.

5. The fault root cause dynamic prediction method based on probability propagation reasoning as described in claim 1, characterized in that, Acquire multi-dimensional monitoring data, transform the raw data into standardized fault probabilities using a predefined indicator-probability mapping function, and employ a fusion strategy to process the multi-source data, obtaining aligned unified probability data, including: A multi-source data alignment method based on probabilistic time windows is adopted, which realizes unified processing of multi-source monitoring data through time window alignment, probability fusion calculation, and confidence decay mechanism. The monitoring data is stored in the multi_source_data table, and the structure of the multi_source_data table includes the following fields: asset number event_id, source node, timestamp, status, raw data raw_data, probability of failure, and confidence. Among them, the probability field represents the probability of failure occurrence in the monitoring data calculated based on monitoring indicators, which is generated by a predefined indicator-probability mapping function.

6. The fault root cause dynamic prediction method based on probability propagation reasoning as described in claim 1, characterized in that, Based on the dynamic propagation graph model, probability propagation calculations are performed on the graph using unified probability data to extrapolate the failure probability of each component and extract a root cause candidate set, including: Perform graph-based probability propagation reasoning to calculate the real-time failure probability of each node. Graph-based probability propagation reasoning adopts a combination of backward reasoning and forward propagation, taking into account both the bottom-up propagation path of the failure and the top-down impact range of business dependencies. Based on the real-time failure probability of each node, all minimum cut sets corresponding to the current top event are extracted as root cause candidate sets. The minimum cut set refers to the smallest set of basic events that can lead to the occurrence of the top event, and each cut set represents a possible combination of failures.

7. The fault root cause dynamic prediction method based on probability propagation reasoning as described in claim 1, characterized in that, The introduction of a key importance weighted model involves multi-dimensional quantitative ranking of each root cause candidate set, and determining the final root cause based on the quantitative ranking results, including: Introduce a key importance weighted model; By comprehensively considering factors such as cut set probability, node influence factor, and data source credibility, the root cause probability of each cut set is comprehensively evaluated, thereby achieving accurate ranking of root causes. Based on the ranking of critical importance, the top K cut sets are selected as the final root cause candidate set, and a verification mechanism is used to confirm them.

8. A dynamic prediction system for root causes of failures based on probabilistic propagation reasoning, characterized in that, include: The initialization module is used to establish globally unique identifiers for each component and obtain its dependencies. The fault dependency modeling module is used to define node types and construct a directed graph structure based on the dependency relationship, associate each node with a dynamic fault probability, and construct a fault state expression system. Based on the fault state representation system, a dynamic factor reflecting the real-time state of the system is introduced, the edge weights are calculated and dynamically updated, and a dynamic propagation graph model is constructed. The multi-source data alignment module is used to acquire multi-dimensional monitoring data, convert the raw data into standardized fault probabilities through a predefined indicator-probability mapping function, and process the multi-source data using a fusion strategy to obtain aligned unified probability data. The reasoning and root cause localization module is used to perform graph probability propagation calculations based on the dynamic propagation graph model and the unified probability data, to infer the failure probability of each component and extract the root cause candidate set; a key importance weighting model is introduced to perform multi-dimensional quantitative ranking of the root cause candidate set, and the final root cause is predicted and located based on the ranking results. The reinforcement learning optimization module introduces intelligent self-healing and strategy optimization algorithms based on reinforcement learning. It automatically generates and executes repair strategies based on the root cause, and continuously optimizes decisions through online learning, forming a self-evolving operation and maintenance closed loop.

9. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium is used to store computer instructions, which, when executed by a processor, implement the fault root cause dynamic prediction method based on probability propagation reasoning as described in any one of claims 1-7.

10. An electronic device, characterized in that, include: The device includes a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory to enable the electronic device to perform the fault root cause dynamic prediction method based on probability propagation reasoning as described in any one of claims 1-7.

Images