Packet desensitization method and device based on FPGA, equipment and medium

Abstract

The application discloses a kind of troubleshooting methods, device, equipment and medium of fault root cause node.It includes: obtaining target fault report and analyzing target fault report, obtaining target fault event and the fault attribute matched with target fault event;Based on each node attribute, the root cause probability of each root cause node is calculated, and each root cause node is sorted based on each root cause probability, and the root cause sequence is obtained;Through bayesian algorithm, according to the fault attribute of target fault event, the node attribute and root cause probability of each root cause node, each root cause node in root cause sequence is sequentially calculated, and the final probability of each root cause node is obtained, and according to each final probability, the target fault node matched with target fault report is obtained.Through the technical scheme of the application, the troubleshooting and positioning of fault root cause node can be realized, and the efficiency of fault root cause node troubleshooting work and the accuracy of troubleshooting result are improved.

Description

Technical Field

[0001] This invention relates to the field of computer operation and maintenance, and in particular to a method, apparatus, equipment and medium for troubleshooting root cause nodes of faults. Background Technology

[0002] In the field of computer operations and maintenance, root cause analysis is a crucial step in ensuring stable system operation. As information systems grow larger and more complex, faults often involve multiple subsystems and service components, making traditional manual troubleshooting methods insufficient for efficient operations and maintenance.

[0003] In existing technologies, root cause analysis of faults primarily relies on the personal experience and intuitive judgment of operations engineers. When a fault occurs, engineers need to manually analyze the fault report described in natural language, select from multiple possible fault directions based on their own experience, and then log into different monitoring systems, log platforms, database management tools, etc., to verify and investigate one by one. This method has significant drawbacks: First, the investigation direction is unclear, and engineers are prone to wasting time on incorrect paths, repeatedly verifying low-probability fault hypotheses; second, cross-system verification is time-consuming and laborious, and frequent switching of tools and interfaces severely slows down the investigation progress; third, it relies too heavily on the personal experience of experts, and inexperienced operations personnel cannot quickly locate problems, resulting in uneven overall investigation capabilities within the team. In addition, existing technologies are insufficient in terms of probability quantification and evidence integration of fault root causes. During the fault investigation process, the probability assessment of each candidate root cause lacks multi-dimensional data support, often relying solely on single historical statistics or subjective judgments, which is difficult to accurately reflect the real-time fault status; at the same time, for new evidence obtained during the verification process, existing technologies lack an effective probability update mechanism, failing to promptly transform verification results into guidance for subsequent investigations, resulting in low accuracy in root cause localization.

[0004] In summary, existing methods for identifying root causes of failures suffer from low efficiency and low accuracy in both the identification process and the results. Summary of the Invention

[0005] This invention provides a method, apparatus, equipment, and medium for troubleshooting root cause nodes, which can solve the problems of low efficiency and low accuracy of troubleshooting results in existing root cause node troubleshooting methods.

[0006] In a first aspect, embodiments of the present invention provide a method for diagnosing root cause nodes of faults, the method comprising: Obtain the target fault report and analyze the target fault report to obtain the target fault event and the fault attributes that match the target fault event; Obtain at least one pre-configured root cause node and the node attributes of each root cause node, calculate the root cause probability of each root cause node based on the node attributes, and sort each root cause node based on the root cause probability to obtain the root cause sequence. Using the Bayesian algorithm, the root cause nodes in the root cause sequence are sequentially calculated based on the fault attributes of the target fault event, the node attributes of each root cause node, and the root cause probability to obtain the final probability of each root cause node. Based on each final probability, the target fault node that matches the target fault report is obtained.

[0007] Secondly, embodiments of the present invention provide a device for diagnosing root cause nodes of faults, the device comprising: The report analysis module is used to acquire target fault reports and analyze the target fault reports to obtain target fault events and fault attributes that match the target fault events; The node sorting module is used to obtain at least one pre-configured root cause node and the node attributes of each root cause node, calculate the root cause probability of each root cause node based on the node attributes, and sort each root cause node based on the root cause probability to obtain the root cause sequence. The probability calculation module is used to sequentially calculate the root cause nodes in the root cause sequence based on the fault attributes of the target fault event, the node attributes of each root cause node, and the root cause probability using a Bayesian algorithm, to obtain the final probability of each root cause node, and to obtain the target fault node that matches the target fault report based on each final probability.

[0008] Thirdly, embodiments of the present invention provide an electronic device, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform a method for troubleshooting root causes of faults as described in any embodiment of the present invention.

[0009] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute and implement a method for identifying root cause nodes of a fault as described in any embodiment of the present invention.

[0010] The technical solution of this invention involves acquiring and analyzing a target fault report to obtain a target fault event and fault attributes matching the target fault event. Then, it acquires at least one pre-configured root cause node and the node attributes of each root cause node. Based on the node attributes, it calculates the root cause probability of each root cause node and sorts the root cause nodes based on their probabilities to obtain a root cause sequence. Finally, using a Bayesian algorithm, it sequentially calculates the root cause nodes in the root cause sequence based on the fault attributes of the target fault event, the node attributes of each root cause node, and the root cause probability to obtain the final probability of each root cause node. Based on these final probabilities, it obtains the target fault node matching the target fault report. This solution addresses the problem of low efficiency and accuracy in existing root cause node investigation methods, achieving root cause node investigation and location, and improving the efficiency and accuracy of root cause node investigation.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a flowchart of a method for troubleshooting root cause nodes according to Embodiment 1 of the present invention; Figure 2 This is a flowchart of a method for troubleshooting root cause nodes according to Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of a fault root cause node investigation device provided in Embodiment 3 of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device that implements a method for investigating the root cause of a fault according to an embodiment of the present invention. Detailed Implementation

[0014] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0015] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, any variations of the terms "comprising" and "having" are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0016] Example 1 Figure 1 This is a flowchart of a method for troubleshooting root cause nodes according to Embodiment 1 of the present invention. This embodiment is applicable to troubleshooting root cause nodes based on fault reports. The method can be executed by a root cause node troubleshooting device, which can be implemented in hardware and / or software. The root cause node troubleshooting device can be configured in a terminal or server with root cause node troubleshooting function.

[0017] like Figure 1 As shown, the method includes: S110. Obtain the target fault report and analyze the target fault report to obtain the target fault event and the fault attributes that match the target fault event.

[0018] The fault attributes include at least one fault description; the node attributes include: node identifier, node importance, at least one root cause symptom, total number of node symptoms, verification method, node reliability, node health, and node historical fault probability.

[0019] Furthermore, the fault description information is a symptom description that matches the target fault report, obtained based on a preset symptom dimension table. The symptom dimension table includes at least one symptom description and keyword information that matches the symptom description. For example, if the symptom description is: transaction abnormality, then the corresponding keyword information can be "payment failure".

[0020] For example, if the original text of a target fault report is: "Starting from 14:30 today, users reported payment failures with a network error message; please try again. The failure rate has increased from 0.5% to 3.2%. This mainly affects payments through application software channels," in this embodiment, keywords can be extracted from the original text using a keyword extraction method. The keywords obtained are: payment failure, network error, and all users. Then, by using the symptom dimension table containing: transaction error - payment failure, network problem - network error, and global impact - all users, the fault description information corresponding to the target fault report can be determined to be: transaction error, network problem, and global problem.

[0021] Furthermore, the node identifier is a unique code that identifies the root cause node; the node importance includes the influence strength of the root cause node and the verification time of the root cause node, and the influence strength includes three levels: high, medium, and low; the root cause symptoms are used to identify the typical set of symptoms that the current node may cause, such as network problems, connection timeouts, and sudden increases corresponding to node 1; the verification method is used to represent the standard verification operation procedure for the root cause node; the node reliability is used to characterize the credibility of the verification results obtained by the verification method of the root cause node.

[0022] It should be noted that in the above steps, the criteria and number of keywords extracted from the original text, as well as the node attributes matched by each root node, can be set by the user according to the actual implementation scenario. This embodiment does not limit the specific content of these settings.

[0023] S120. Obtain at least one pre-configured root cause node and the node attributes of each root cause node, calculate the root cause probability of each root cause node based on the node attributes, and sort each root cause node based on the root cause probability to obtain the root cause sequence.

[0024] The process of sorting root cause nodes based on their root cause probabilities to obtain a root cause sequence includes: filtering root cause nodes with root cause probabilities less than a preset skip threshold to obtain a set of candidate root cause nodes; obtaining the node importance of each candidate root cause node in the set of candidate root cause nodes; calculating the sorting priority of each candidate root cause node based on the node importance and the root cause probability; and sorting the candidate root cause nodes in the set of candidate root cause nodes in descending order according to the sorting priority to obtain the root cause sequence.

[0025] Furthermore, the importance of each candidate root cause node in the candidate root cause node set is obtained, and the ranking priority of each candidate root cause node is calculated based on the node importance and the root cause probability. This includes: calculating the cost-effectiveness of each candidate root cause node, where the cost-effectiveness is the ratio of the root cause probability of the root cause node to the verification time; obtaining the influence strength of the node, and when the influence strength is high, adjusting the cost-effectiveness using a time-sensitive factor, where the time-sensitive factor is the reciprocal of the verification time; and multiplying the adjusted cost-effectiveness by the importance of the node to obtain the ranking priority. This design enables the system to prioritize root cause nodes with fast verification speeds and the ability to quickly eliminate or confirm them in emergency fault scenarios, thereby shortening the mean time to recovery.

[0026] S130. Using the Bayesian algorithm, each root cause node in the root cause sequence is sequentially calculated based on the fault attributes of the target fault event, the node attributes of each root cause node, and the root cause probability to obtain the final probability of each root cause node. Based on each final probability, the target fault node that matches the target fault report is obtained.

[0027] Specifically, using the Bayesian algorithm, the root cause nodes in the root cause sequence are sequentially calculated based on the fault attributes of the target fault event, the node attributes of each root cause node, and the root cause probability to obtain the final probability of each root cause node. This includes: obtaining the root cause node at the beginning of the root cause sequence as the target root cause node; performing confidence verification on the target root cause node according to the verification method of the target root cause node to obtain the verification result and the confidence level of the verification result; calculating the posterior probability of the target root cause node based on the verification result and the node reliability of the target root cause node using the Bayesian formula; and further calculating the posterior probability of the target root cause node based on the... The confidence level, the posterior probability, and the root cause probability of the target root cause node are used to calculate the final probability of the target root cause node based on a pre-configured final probability calculation formula, wherein the final probability formula is: final probability = confidence level × posterior probability + (1 - confidence level) × root cause probability; it is determined whether the final probability is greater than a preset stopping threshold; if it is not greater than the stopping threshold, the root cause node located one position after the target root cause node in the root cause sequence is updated as a new target root cause node, and the operation of performing confidence verification on the target root cause node according to the verification method of the target root cause node is returned.

[0028] The Bayesian algorithm is a statistical inference method based on conditional probability, used to update the probability of a hypothesis after obtaining new evidence. In this embodiment, the hypothesis is "the current root cause node is the true cause of the target failure," and the evidence is the verification result obtained through the verification method.

[0029] Furthermore, the confidence verification refers to performing actual operations according to the verification method corresponding to the root cause node to obtain the real state data of the root cause node. The verification result includes two states: "normal" or "abnormal". The confidence level is used to characterize the credibility of the verification result, and the value range is 0-1. The higher the confidence level, the more reliable the verification result. It can be set by the user according to the actual implementation scenario.

[0030] For example, based on the above steps, if the node number of the target root cause node is N001, the corresponding target root cause node verification method is: client Ping test, after execution, the verification result is "normal", with a confidence level of 0.95. The posterior probability is calculated according to Bayes' theorem; specifically, the Bayes' theorem is: P(hypothesis|evidence) = [P(evidence|hypothesis) × P(hypothesis)] / P(evidence), where P(hypothesis) is the root cause probability, set to 0.475 in this example; P(evidence|hypothesis) is the probability of observing normal evidence when the hypothesis is true, set to 0.2; P(evidence|hypothesis) is the probability of observing normal evidence when the hypothesis is false, set to 0.8; then P(evidence) = 0.2 × 0.475 + 0.8 × 0.525 = 0.515; posterior probability = (0.2 × 0.475) / 0.515 = 0.184.

[0031] Those skilled in the art should understand that, given the confidence level and root cause probability of the target root cause node, using the Bayesian algorithm to calculate the posterior probability of the target root cause node is a mature mathematical algorithm. This embodiment only introduces its calculation process, without elaborating on its underlying principles.

[0032] Furthermore, the stop threshold is used to determine whether the target fault node has been located, and is typically set to 0.9. When the final probability is greater than or equal to this threshold, it indicates that the root cause node has a very high probability of being the true root cause, and subsequent verification can be stopped to save investigation time.

[0033] Optionally, after determining whether the final probability is greater than a preset stopping threshold, the method further includes: if the final probability is greater than or equal to the stopping threshold, then the target root cause node is output as the target fault node.

[0034] The technical solution of this invention involves acquiring and analyzing a target fault report to obtain a target fault event and fault attributes matching the target fault event. Then, it acquires at least one pre-configured root cause node and the node attributes of each root cause node. Based on the node attributes, it calculates the root cause probability of each root cause node and sorts the root cause nodes based on their probabilities to obtain a root cause sequence. Finally, using a Bayesian algorithm, it sequentially calculates the root cause nodes in the root cause sequence based on the fault attributes of the target fault event, the node attributes of each root cause node, and the root cause probability to obtain the final probability of each root cause node. Based on these final probabilities, it identifies the target fault node matching the target fault report, thus achieving the investigation and location of fault root cause nodes and improving the efficiency and accuracy of the investigation results.

[0035] Example 2 Figure 2 This is a flowchart of a method for troubleshooting root cause nodes according to Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiment. Specifically, this embodiment refines the method for calculating the root cause probability of each root cause node based on the attributes of each node.

[0036] like Figure 2 As shown, the method includes: S210. Obtain the target fault report and analyze the target fault report to obtain the target fault event and the fault attributes that match the target fault event.

[0037] S220. Obtain at least one pre-configured root cause node and the node attributes of each root cause node.

[0038] S230. Obtain the fault description information of each target fault event, and calculate the symptom matching degree of each root cause node based on the fault description information, the root cause symptoms of each root cause node, and the total number of symptoms of each node.

[0039] The symptom matching degree is used to characterize the degree of agreement between the fault description information and the root cause symptoms. The value ranges from 0 to 1. The higher the value, the stronger the correlation between the root cause node and the target fault event.

[0040] The process involves calculating the symptom matching degree for each root cause node based on the fault description information, the root cause symptoms of each root cause node, and the total number of symptoms in each node. This includes: matching each fault description information with each root cause symptom of each root cause node to obtain the target symptom count for each root cause node; and calculating the symptom matching degree for each root cause node based on the target symptom count and the total number of symptoms in each node, using a preset symptom matching degree formula. The symptom matching degree formula is: Symptom matching degree = Target symptom count / Total number of symptoms in each node.

[0041] Furthermore, the step of matching each fault description information with each root cause symptom of each root cause node includes: comparing each fault description information with each root cause symptom one by one; when the fault description information and the root cause symptom are completely consistent, it is determined that the root cause symptom is successfully matched; and counting the number of successfully matched root cause symptoms as the target symptom count.

[0042] For example, if the fault description information of the target fault event is transaction anomaly, network problem, or global problem, and the root cause symptoms of root cause node N001 are network problem, connection timeout, transaction anomaly, and surge, the total number of symptoms for the node is 4. Comparing the fault description information with the root cause symptoms one by one: transaction anomaly matches, network problem matches, global problem, connection timeout, and surge do not match. Therefore, the number of target symptoms is 2, and the symptom matching degree = 2 / 4 = 0.50.

[0043] S240. Based on the node health of each root cause node, the node correlation of each root cause node is calculated according to the preset formula: node correlation = 1 - node health.

[0044] The health status of the root cause node is used to represent the degree of correlation between the current state of the root cause node and the occurrence of the fault, and can be set and modified by the user based on the historical data of the root cause node.

[0045] S250. The symptom matching degree, node historical failure probability and node correlation are weighted and summed according to the pre-set weights to obtain the root cause probability of each root cause node, and the root cause nodes are sorted according to each root cause probability to obtain the root cause sequence.

[0046] The pre-set weights include symptom matching weight, historical probability weight, and correlation weight, the sum of which is 1. Furthermore, the root cause probability is calculated as follows: root cause probability = symptom matching weight × symptom matching degree + historical probability weight × node historical failure probability + correlation weight × node correlation.

[0047] S260. Using the Bayesian algorithm, each root cause node in the root cause sequence is sequentially calculated based on the fault attributes of the target fault event, the node attributes of each root cause node, and the root cause probability to obtain the final probability of each root cause node. Based on each final probability, the target fault node that matches the target fault report is obtained.

[0048] The technical solution of this invention involves acquiring and analyzing a target fault report to obtain a target fault event and fault attributes matching the target fault event. Then, it acquires at least one pre-configured root cause node and the node attributes of each root cause node, and obtains fault description information for each target fault event. Based on the fault description information, the root cause symptoms of each root cause node, and the total number of node symptoms, it calculates the symptom matching degree of each root cause node. Then, based on the node health of each root cause node, it calculates the node correlation of each root cause node using a preset formula. Finally, it assigns weights to each root cause node according to a preset formula. The symptom matching degree, the historical failure probability of the node, and the node correlation are weighted and summed to obtain the root cause probability of each root cause node. Based on the root cause probability, the root cause nodes are sorted to obtain the root cause sequence. Finally, the Bayesian algorithm is used to sequentially calculate the root cause nodes in the root cause sequence according to the failure attributes of the target failure event, the node attributes of each root cause node, and the root cause probability to obtain the final probability of each root cause node. Based on the final probability, the target failure node matching the target failure report is obtained, realizing the investigation and location of the root cause node, improving the efficiency of the root cause node investigation work and the accuracy of the investigation results.

[0049] Example 3 Figure 3 This is a schematic diagram of a fault root cause node investigation device provided in Embodiment 3 of the present invention.

[0050] like Figure 3 As shown, the device includes: The report analysis module 310 is used to acquire target fault reports and analyze the target fault reports to obtain target fault events and fault attributes that match the target fault events; The node sorting module 320 is used to obtain at least one pre-configured root cause node and the node attributes of each root cause node, calculate the root cause probability of each root cause node based on the node attributes, and sort each root cause node based on the root cause probability to obtain the root cause sequence. The probability calculation module 330 is used to perform sequential calculations on each root cause node in the root cause sequence using a Bayesian algorithm based on the fault attributes of the target fault event, the node attributes of each root cause node, and the root cause probability, to obtain the final probability of each root cause node, and to obtain the target fault node that matches the target fault report based on each final probability.

[0051] The technical solution of this invention involves acquiring and analyzing a target fault report to obtain a target fault event and fault attributes matching the target fault event. Then, it acquires at least one pre-configured root cause node and the node attributes of each root cause node. Based on the node attributes, it calculates the root cause probability of each root cause node and sorts the root cause nodes based on their probabilities to obtain a root cause sequence. Finally, using a Bayesian algorithm, it sequentially calculates the root cause nodes in the root cause sequence based on the fault attributes of the target fault event, the node attributes of each root cause node, and the root cause probability to obtain the final probability of each root cause node. Based on these final probabilities, it identifies the target fault node matching the target fault report, thus achieving the investigation and location of fault root cause nodes and improving the efficiency and accuracy of the investigation results.

[0052] Based on the above embodiments, the node sorting module 320 includes: The matching degree calculation unit is used to obtain the fault description information of the target fault event, and calculate the symptom matching degree of each root cause node based on the fault description information, the root cause symptoms of each root cause node and the total number of symptoms of the node. The correlation calculation unit is used to calculate the node correlation of each root cause node based on the node health of each root cause node and the preset formula: node correlation = 1 - node health. The root cause probability calculation unit is used to perform a weighted summation of the symptom matching degree, the historical failure probability of the node, and the node correlation according to the pre-set weights to obtain the root cause probability of each root cause node.

[0053] Based on the above embodiments, the matching degree calculation unit includes: The symptom matching unit is used to match each fault description information with each root cause symptom of each root cause node to obtain the number of target symptoms for each root cause node. The node matching degree calculation unit is used to calculate the symptom matching degree of each root cause node based on the number of target symptoms and the total number of node symptoms, according to a preset symptom matching degree formula; wherein, the symptom matching degree formula is: symptom matching degree = number of target symptoms / total number of node symptoms.

[0054] Based on the above embodiments, the node sorting module 320 includes: The node filtering unit is used to filter root cause nodes whose root cause probability is less than a preset skip threshold to obtain a set of candidate root cause nodes. The priority calculation unit is used to obtain the node importance of each candidate root cause node in the candidate root cause node set, and calculate the sorting priority of each candidate root cause node based on the node importance and the root cause probability. The sorting unit is used to sort each candidate root cause node in the candidate root cause node set in descending order according to the sorting priority, so as to obtain the root cause sequence.

[0055] Based on the above embodiments, the probability calculation module 330 includes: The target node acquisition unit is used to acquire the root cause node located at the beginning of the root cause sequence as the target root cause node. The confidence verification unit is used to perform confidence verification on the target root cause node according to the verification method of the target root cause node, and obtain the verification result and the confidence level of the verification result. The posterior probability calculation unit is used to calculate the posterior probability of the target root cause node based on the verification result and the node reliability of the target root cause node, using Bayes' theorem. The final probability calculation unit is used to calculate the final probability of the target root cause node based on the confidence level, the posterior probability and the root cause probability of the target root cause node, according to a pre-configured final probability calculation formula, wherein the final probability formula is: final probability = confidence level × posterior probability + (1 - confidence level) × root cause probability; A stop determination unit is used to determine whether the final probability is greater than a preset stop threshold; The execution unit is returned to update the root cause node located one position below the target root cause node in the root cause sequence to a new target root cause node if the value is not greater than the stopping threshold, and then returns to perform confidence verification of the target root cause node according to the verification method of the target root cause node.

[0056] Based on the above embodiments, the stop determination unit is further configured to: determine whether the final probability is greater than a preset stop threshold, and if the final probability is greater than or equal to the stop threshold, output the target root cause node as the target fault node.

[0057] The fault root cause node investigation device provided in this embodiment of the invention can execute the fault root cause node investigation method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0058] Example 4 Figure 4A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0059] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded into the RAM 13 from storage unit 18. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0060] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0061] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as a method for troubleshooting root cause nodes of a fault.

[0062] Accordingly, the method includes: Obtain the target fault report and analyze the target fault report to obtain the target fault event and the fault attributes that match the target fault event; Obtain at least one pre-configured root cause node and the node attributes of each root cause node, calculate the root cause probability of each root cause node based on the node attributes, and sort each root cause node based on the root cause probability to obtain the root cause sequence. Using the Bayesian algorithm, the root cause nodes in the root cause sequence are sequentially calculated based on the fault attributes of the target fault event, the node attributes of each root cause node, and the root cause probability to obtain the final probability of each root cause node. Based on each final probability, the target fault node that matches the target fault report is obtained.

[0063] In some embodiments, a method for identifying root cause nodes of a fault may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for identifying root cause nodes of a fault described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform a method for identifying root cause nodes of a fault by any other suitable means (e.g., by means of firmware).

[0064] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0065] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0066] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0067] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0068] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0069] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0070] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

Claims

1. A method for diagnosing root cause nodes of a fault, characterized in that, include: Obtain the target fault report and analyze the target fault report to obtain the target fault event and the fault attributes that match the target fault event; Obtain at least one pre-configured root cause node and the node attributes of each root cause node, calculate the root cause probability of each root cause node based on the node attributes, and sort each root cause node based on the root cause probability to obtain the root cause sequence. Using the Bayesian algorithm, the root cause nodes in the root cause sequence are sequentially calculated based on the fault attributes of the target fault event, the node attributes of each root cause node, and the root cause probability to obtain the final probability of each root cause node. Based on each final probability, the target fault node that matches the target fault report is obtained.

2. The method according to claim 1, characterized in that, The fault attributes include: at least one fault description information; The node attributes include: node identifier, node importance, at least one root cause symptom, total number of node symptoms, verification method, node reliability, node health, and node historical failure probability.

3. The method according to any one of claims 1-2, characterized in that, Calculate the root cause probability of each root cause node based on its attributes, including: Obtain the fault description information of each target fault event, and calculate the symptom matching degree of each root cause node based on the fault description information, the root cause symptoms of each root cause node, and the total number of symptoms of each node. Based on the node health of each root cause node, the node correlation of each root cause node is calculated according to the preset formula: Node Correlation = 1 - Node Health. The root cause probability of each root cause node is obtained by weighting and summing the symptom matching degree, the historical failure probability of the node, and the node correlation according to the pre-set weights.

4. The method according to claim 3, characterized in that, Based on the fault description information, the root cause symptoms of each root cause node, and the total number of symptoms for each node, calculate the symptom matching degree for each root cause node, including: The description information of each fault is matched with the root cause symptoms of each root cause node to obtain the number of target symptoms of each root cause node. Based on the number of target symptoms and the total number of symptoms in the nodes, the symptom matching degree of each root cause node is calculated according to a preset symptom matching degree formula. The symptom matching degree formula is: Symptom matching degree = Number of target symptoms / Total number of symptoms in nodes.

5. The method according to any one of claims 1-2, characterized in that, The root cause nodes are sorted based on their root cause probabilities to obtain the root cause sequence, which includes: Root cause nodes whose root cause probability is less than a preset skip threshold are filtered to obtain a set of candidate root cause nodes. Obtain the node importance of each candidate root cause node in the candidate root cause node set, and calculate the sorting priority of each candidate root cause node based on the node importance and the root cause probability. The candidate root cause nodes in the candidate root cause node set are sorted in descending order according to the sorting priority to obtain the root cause sequence.

6. The method according to any one of claims 1-2, characterized in that, Using the Bayesian algorithm, the root cause nodes in the root cause sequence are sequentially calculated based on the fault attributes of the target fault event, the node attributes of each root cause node, and the root cause probability, to obtain the final probability of each root cause node, including: The root cause node located at the beginning of the root cause sequence is selected as the target root cause node. The target root cause node is subjected to confidence verification according to the verification method of the target root cause node, and the verification result and the confidence level of the verification result are obtained. Based on the verification results and the node reliability of the target root cause node, the posterior probability of the target root cause node is calculated using Bayes' theorem. Based on the confidence level, the posterior probability, and the root cause probability of the target root cause node, the final probability of the target root cause node is calculated according to a pre-configured final probability calculation formula, wherein the final probability formula is: final probability = confidence level × posterior probability + (1 - confidence level) × root cause probability; Determine whether the final probability is greater than a preset stopping threshold; If the value is not greater than the stopping threshold, the root cause node in the root cause sequence that is one position below the target root cause node is updated to the new target root cause node, and the operation of performing confidence verification on the target root cause node according to the verification method of the target root cause node is returned.

7. The method according to claim 6, characterized in that, After determining whether the final probability is greater than a preset stopping threshold, the method further includes: If the final probability is greater than or equal to the stopping threshold, then the target root cause node is output as the target fault node.

8. A device for diagnosing root cause nodes of a fault, characterized in that, include: The report analysis module is used to acquire target fault reports and analyze the target fault reports to obtain target fault events and fault attributes that match the target fault events; The node sorting module is used to obtain at least one pre-configured root cause node and the node attributes of each root cause node, calculate the root cause probability of each root cause node based on the node attributes, and sort each root cause node based on the root cause probability to obtain the root cause sequence. The probability calculation module is used to sequentially calculate the root cause nodes in the root cause sequence based on the fault attributes of the target fault event, the node attributes of each root cause node, and the root cause probability using a Bayesian algorithm, to obtain the final probability of each root cause node, and to obtain the target fault node that matches the target fault report based on each final probability.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a method for troubleshooting root cause nodes according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that are used to cause a processor to execute a method for troubleshooting root cause nodes according to any one of claims 1-7.

Images