CN114186031A - System fault prediction method, device, computer equipment and storage medium - Google Patents
System fault prediction method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114186031A CN114186031A CN202111532573.5A CN202111532573A CN114186031A CN 114186031 A CN114186031 A CN 114186031A CN 202111532573 A CN202111532573 A CN 202111532573A CN 114186031 A CN114186031 A CN 114186031A
- Authority
- CN
- China
- Prior art keywords
- event
- fault
- predicted
- events
- probability
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3346—Query execution using probabilistic model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/02—Banking, e.g. interest calculation or account maintenance
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Technology Law (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Debugging And Monitoring (AREA)
Abstract
The application relates to a system fault prediction method, a system fault prediction device, computer equipment and a storage medium, which can be used for predicting fault events of bank systems in the financial field and can also be used in any fields except the financial field. The method comprises the following steps: performing primary fault prediction on the bank system based on a fault tree analysis algorithm and operation data of the bank system to obtain a predicted fault event of the bank system; predicting fault events comprising a top event, all intermediate events corresponding to the top event and all bottom events corresponding to the top event; determining the occurrence probability of each top event, the occurrence probability of each middle event and the occurrence probability of each bottom event, and determining a reference fault event from the predicted fault events based on the event occurrence probabilities; a fault prediction result for the banking system is determined based on the reference fault event. By adopting the method, the accuracy of system fault prediction can be improved.
Description
Technical Field
The present application relates to the field of finance, and in particular, to a system fault prediction method, apparatus, computer device, and storage medium.
Background
The bank system has strict requirements on safety because the bank system relates to sensitive information such as accounting information, basic information of customers, transaction information and the like, so that the safety of the bank system can be evaluated to monitor potential safety risks of the bank system and timely control events with safety risks.
At present, Fault Tree Analysis (FTA) and Fault Mode and Effects Analysis (FMEA) are mainly used for evaluating system security. FTA is a fault reason analysis method from top to bottom based on a tree structure, which is to trace the reason causing the top event downwards step by step from the top event (i.e. fault event or event needing analysis) to the bottom event (i.e. cause event or basic event causing only other events). FMEA is a bottom-up analysis method, which is a generalized analysis method that analyzes each component or process constituting a system one by one, finds out all potential failure modes, analyzes all possible influences of each failure mode on the system, and classifies the difficulty and frequency of occurrence according to the severity of each failure mode.
The FTA can explicitly show the logical relationship between the failure and the cause of the failure, but is prone to the occurrence of a missed fail event. The FMEA can fully analyze the causes of faults causing the fault event, but cannot fully explain the logical relationship between the causes of faults.
Disclosure of Invention
The application provides a system fault prediction method, a system fault prediction device, computer equipment and a storage medium, which can improve the accuracy of bank system fault prediction.
In a first aspect, the present application provides a system failure prediction method. The method comprises the following steps:
performing primary fault prediction on the bank system based on a fault tree analysis algorithm and operation data of the bank system to obtain a predicted fault event of the bank system; predicting fault events comprising a top event, all intermediate events corresponding to the top event and all bottom events corresponding to the top event;
determining the occurrence probability of each top event, the occurrence probability of each middle event and the occurrence probability of each bottom event, and determining a reference fault event from the predicted fault events based on the event occurrence probabilities;
a fault prediction result for the banking system is determined based on the reference fault event.
In one embodiment, determining the probability of occurrence of each top event, the probability of occurrence of each middle event, and the probability of occurrence of each bottom event comprises: determining a logical relationship between predicted fault events of the banking system, and determining a conditional probability of each predicted fault event based on the logical relationship; and determining the occurrence probability of the predicted fault event according to the conditional probability of the predicted fault event and the prior probability of the predicted fault event.
In one embodiment, determining the probability of occurrence of the predicted failure event according to the conditional probability of the predicted failure event and the prior probability of the predicted failure event comprises: substituting the conditional probability and the prior probability into a formula containing the following calculation formula to calculate the occurrence probability of the predicted fault event;
wherein A is used for representing a predicted failure event A, B is used for representing a predicted failure event B, P (A) is the prior probability of the predicted failure event A, and P (B) is the prior probability of the predicted failure event B; p (B | a) is the conditional probability of predicting failure event a; p (a | B) is the probability of occurrence of the predicted failure event a.
In one embodiment, determining a reference fault event from the predicted fault events based on the event occurrence probability includes: and determining the predicted fault events with the occurrence probability larger than a first preset threshold value in the predicted fault events as reference fault events.
In one embodiment, determining a fault prediction result for a banking system based on a reference fault event includes: determining related events of the reference fault events based on the fault modes and the influence analysis algorithm, wherein the related events are events caused by the reference fault events; and determining the fault event of the bank system according to the related event.
In one embodiment, determining a fault event for a banking system based on the associated event comprises: determining a degree of correlation for each correlated event; the degree of correlation is used for representing the degree of correlation between the related events and core security events of the bank system; and determining the fault event of the banking system according to the related events of which the degree of correlation is greater than a second preset threshold value.
In a second aspect, the present application further provides a system failure prediction apparatus. The device includes:
the prediction module is used for carrying out preliminary fault prediction on the bank system based on a fault tree analysis algorithm and operation data of the bank system to obtain a predicted fault event of the bank system; predicting fault events comprising a top event, all intermediate events corresponding to the top event and all bottom events corresponding to the top event;
the reference fault event determining module is used for determining the occurrence probability of each top event, the occurrence probability of each middle event and the occurrence probability of each bottom event, and determining a reference fault event from the predicted fault events based on the event occurrence probabilities;
and the fault prediction result module is used for determining a fault prediction result of the bank system based on the reference fault event.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor realizes the following steps when executing the computer program:
performing primary fault prediction on the bank system based on a fault tree analysis algorithm and operation data of the bank system to obtain a predicted fault event of the bank system; predicting fault events comprising a top event, all intermediate events corresponding to the top event and all bottom events corresponding to the top event;
determining the occurrence probability of each top event, the occurrence probability of each middle event and the occurrence probability of each bottom event, and determining a reference fault event from the predicted fault events based on the event occurrence probabilities;
a fault prediction result for the banking system is determined based on the reference fault event.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
performing primary fault prediction on the bank system based on a fault tree analysis algorithm and operation data of the bank system to obtain a predicted fault event of the bank system; predicting fault events comprising a top event, all intermediate events corresponding to the top event and all bottom events corresponding to the top event;
determining the occurrence probability of each top event, the occurrence probability of each middle event and the occurrence probability of each bottom event, and determining a reference fault event from the predicted fault events based on the event occurrence probabilities;
a fault prediction result for the banking system is determined based on the reference fault event.
In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:
performing primary fault prediction on the bank system based on a fault tree analysis algorithm and operation data of the bank system to obtain a predicted fault event of the bank system; predicting fault events comprising a top event, all intermediate events corresponding to the top event and all bottom events corresponding to the top event;
determining the occurrence probability of each top event, the occurrence probability of each middle event and the occurrence probability of each bottom event, and determining a reference fault event from the predicted fault events based on the event occurrence probabilities;
a fault prediction result for the banking system is determined based on the reference fault event.
The application provides a system fault prediction method, a system fault prediction device, computer equipment and a storage medium, which can be used for predicting fault events of bank systems in the financial field and can also be used in any fields except the financial field, such as the fields of big data, cloud computing, block chains, artificial intelligence, information safety, the Internet of things and the 5G technology. The method can utilize FTA to construct a fault tree model of the bank system, calculate the occurrence probability of each predicted fault event in the fault tree model, and determine the fault prediction result of the bank system based on the predicted fault event with higher occurrence probability, namely determine the fault event of the bank system. Therefore, the probability of each predicted fault event of the bank system can be calculated, all possible fault events in the bank system are considered comprehensively, and comprehensiveness and integrity of system fault prediction are guaranteed. And the method and the device can further analyze partial predicted fault events in all the predicted fault events based on the occurrence probability, thereby determining the fault prediction result of the bank system and improving the accuracy of system fault prediction.
Drawings
FIG. 1 is a schematic flow chart diagram illustrating a method for system failure prediction in one embodiment;
FIG. 2 is a schematic diagram of a fault tree model of a system fault prediction method in one embodiment;
FIG. 3 is another flow diagram illustrating a method for system failure prediction in one embodiment;
FIG. 4 is a diagram of a Bayesian network model of a system failure prediction method in one embodiment;
FIG. 5 is another flow diagram illustrating a method for system failure prediction in one embodiment;
FIG. 6 is another flow diagram illustrating a method for system failure prediction in one embodiment;
FIG. 7 is a block diagram showing the structure of an apparatus according to the flowchart of one embodiment;
FIG. 8 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In an embodiment, as shown in fig. 1, a system failure prediction method is provided, and this embodiment is illustrated by applying the method to a terminal, it is to be understood that the method may also be applied to a server, and may also be applied to a system including a terminal and a server, and is implemented by interaction between the terminal and the server. In this embodiment, the method includes the steps of:
according to the embodiment of the application, a fault tree model can be established for the bank system based on the FTA, so that fault analysis is carried out on each predicted fault event based on the fault tree model.
Wherein the fault tree model is composed of predicted fault events and logical relationships between the predicted fault events. The predicted failure events include a top event, all intermediate events corresponding to the top event, and all bottom events corresponding to the top event. The top event is a result event concerned in the fault tree analysis, the middle event is an event between the top event and the bottom event, and the middle event is not only a cause of the top event but also a result caused by the bottom event. The bottom event is a cause event which only causes other events in the fault tree analysis and is positioned at the tail end of each branch of the fault tree. Logical relationships include and, or, not, etc.
In specific implementation, all possible fault events of the bank system can be recorded one by one based on the operation data of the bank system, namely the fault events are predicted by the bank system. Then, the logical relationship between the predicted fault events is determined, and a fault tree model of the banking system is constructed based on the predicted fault events and the logical relationship between the predicted fault events.
The operation data comprises data related to normal operation of the bank system, such as customer service, production scheduling, operation, system maintenance, network maintenance, application maintenance, safety management, equipment maintenance, data archive management, monitoring and emergency treatment, service quality management, comprehensive management and the like.
In a possible implementation manner, as shown in fig. 2, if the bank system is a queuing and number-calling machine background system, all possible fault events of the queuing and number-calling machine background system are recorded one by one based on the running data of the queuing and number-calling machine background system, such as network maintenance, device maintenance, application maintenance, running operation, and the like, for example, the fault events of the queuing and number-calling machine background system may include: the method comprises the following steps of queuing machine background system faults, batch faults, online faults, Entegor workflow faults, database faults, HTTP direct connection interface faults, page faults, service interface faults, data loss, disk array damage, program logic errors, HTTP connection failures, service interface registration failures and the like. The fault event is a predicted fault event of the background system of the queuing machine.
Then, determining a logical relationship between the predicted fault events, for example, the logical relationship between the predicted fault events of the background system of the queuing machine may be: data loss and disk array damage can cause database faults, database faults or Entegor workflow faults can cause batch faults, HTTP direct interface faults can be caused by program logic errors or HTTP connection failures or service interface registration failures, page faults can be caused by program logic errors or HTTP connection failures or service interface registration failures, service interface faults can be caused by program logic errors or HTTP connection failures or service interface registration failures, online faults can be caused by HTTP direct interface faults or page faults or service interface faults, and batch faults or online faults can cause queuing machine background system faults. And finally, constructing a fault tree model of the background system of the queuing machine as shown in fig. 2 based on the predicted fault events of the background system of the queuing machine and the logical relationship among the predicted fault events.
The system comprises a queuing and number calling machine background system, a server and a queuing and number calling machine background system, wherein the queuing and number calling machine background system fault is a top event of a fault tree model of the queuing and number calling machine background system, the batch fault, the online fault, the database fault, the HTTP direct connection interface fault, the page fault and the server interface fault are intermediate events of the fault tree model of the queuing and number calling machine background system, and the Entegor workflow fault, the data loss, the disk array damage, the program logic error, the HTTP connection failure and the server interface registration failure are bottom events of the fault tree model of the queuing and number calling machine background system.
102, determining the occurrence probability of each top event, the occurrence probability of each middle event and the occurrence probability of each bottom event, and determining a reference fault event from the predicted fault events based on the event occurrence probabilities;
the embodiment of the application can analyze each predicted fault event of the fault tree model of the system based on the occurrence probability.
In specific implementation, the occurrence probability of each predicted failure event, that is, the occurrence probability of each top event, the occurrence probability of each middle event, and the occurrence probability of each bottom event, may be determined by fully considering information such as the cause event of each predicted failure event, the operating state of the system to which the predicted failure event belongs. One or more reference fault events with higher occurrence probabilities are then screened from all the predicted fault events based on the occurrence probability of each predicted fault event. For example, the predicted fault events with the occurrence probability greater than a certain threshold may be determined as the reference fault events, or the predicted fault events corresponding to the first 5 occurrence probabilities after the occurrence probabilities are sorted in a descending order may be determined as the reference fault events, which is not limited in this application.
And 103, determining a fault prediction result of the bank system based on the reference fault event.
In a specific implementation, the screened one or more reference fault events can be analyzed one by one, and a fault prediction result of the bank system is determined according to an analysis result. Specifically, each reference fault event may be analyzed based on information such as other fault events that may be caused by the reference fault event, the influence that may be caused on the banking system, and the severity of the influence on the system. And determining the reference fault event which possibly causes more other fault events as the fault event of the bank system according to the analysis result, namely the fault prediction result of the bank system. Or determining the reference fault event which may cause serious influence on the bank system as the fault event of the bank system according to the analysis result. Or determining other fault events possibly caused by each reference event as fault events of the bank system.
According to the system fault prediction method provided by the embodiment of the application, the FTA can be used for constructing the fault tree model of the bank system, the occurrence probability of each predicted fault event in the fault tree model is calculated, and the fault prediction result of the bank system is determined based on the predicted fault event with higher occurrence probability, namely the fault event of the bank system is determined. Therefore, the probability of each predicted fault event of the bank system can be calculated, all possible fault events in the bank system are considered comprehensively, and comprehensiveness and integrity of system fault prediction are guaranteed. And the method and the device can further analyze partial predicted fault events in all the predicted fault events based on the occurrence probability, thereby determining the fault prediction result of the bank system and improving the accuracy of system fault prediction.
The embodiments described above describe a scheme for determining the probability of occurrence of each predicted failure event. In another embodiment of the present application, the probability of occurrence of each predicted failure event may be determined based on the prior probability and the conditional probability of each predicted failure event. For example, the first question "determining the occurrence probability of each top event, the occurrence probability of each middle event, and the occurrence probability of each bottom event" specifically includes the steps shown in fig. 3:
in an embodiment of the present application, the occurrence probability of each predicted fault event may be determined based on a bayesian network model. Specifically, the prior probability and the conditional probability of each node in the bayesian network model may be determined first.
And each node in the Bayesian network model corresponds to each predicted fault event in the fault tree model. The prior probability of the node is the prior probability of the predicted fault event corresponding to the node, and the conditional probability of the node is the conditional probability of the predicted fault event corresponding to the node. Predicting the prior probability of the fault event to be the probability obtained according to past experience and analysis; the conditional probability of the predicted fault event is the probability of the predicted fault event occurring under the condition of some other predicted fault event, and the conditional probability is related to the logic relationship between the predicted fault events;
in a possible implementation manner, the fault tree model of the bank system may be converted into a bayesian network model. Specifically, the bottom event in the fault tree model is represented as a root node in the bayesian network model. If a certain bottom event in the fault tree model occurs for multiple times, only one root node needs to be corresponding to the Bayesian network model, and the occurrence probability of the bottom event in the fault tree model is the prior probability of the corresponding root node in the Bayesian network model. Representing each logic gate in the fault tree model (i.e., a middle event or a top event in the fault tree model) as a node in the bayesian network model; and expressing the relation between the predicted fault events in the fault tree model as the connection relation between nodes in the Bayesian network model, wherein the direction of the directed edge of the connection node corresponds to the input-output relation of a logic gate in the fault tree model. Then, a priori probability and conditional probability of each predicted fault event can be determined by professionals according to past experience and analysis, and the priori probability and the conditional probability of each node in the Bayesian model can be determined according to the determined priori probability and the determined conditional probability of each predicted fault event. If a certain node corresponds to N child nodes, the node has N conditional probabilities, and each conditional probability is the probability of the node under the condition of one of the child nodes.
Taking the background system of the queuing and calling machine as an example, the fault tree model of the background system of the queuing and calling machine is converted, and the bayesian model obtained after the conversion is shown in fig. 4. The method comprises the steps that a fault event corresponding to a node A is a queuing machine background system fault, a fault event corresponding to a node B is a batch fault, a fault event corresponding to a node C is an online fault, a fault event corresponding to a node D is an Entegor workflow fault, a fault event corresponding to a node E is a database fault, a fault event corresponding to a node F is an HTTP direct connection interface fault, a fault event corresponding to a node G is a page fault, a fault event corresponding to a node H is a service interface fault, a fault event corresponding to a node I is data loss, a fault event corresponding to a node J is disk array damage, a fault event corresponding to a node K is a program logic error, a fault event corresponding to a node L is an HTTP connection failure, and a fault event corresponding to a node M is a service interface registration failure.
In specific implementation, the posterior probability of each node can be calculated based on the prior probability and the conditional probability of each node in the bayesian network model, and then the posterior probability of the node is determined as the occurrence probability of the prediction fault model corresponding to the node. Specifically, when the posterior probability of each node in the bayesian network model is calculated, the prior probability of the node and each conditional probability of the N conditional probabilities may be calculated respectively to obtain N posterior probabilities, that is, N occurrence probabilities exist in the predictive failure model corresponding to each node.
The embodiment of the application introduces a scheme for determining the occurrence probability of a predicted fault event, and specifically, a fault tree model of a bank system may be converted into a bayesian network model, then the prior probability and the conditional probability of each predicted fault event in the determined fault tree model are determined as the prior probability and the conditional probability of each node in the bayesian network model, and the posterior probability of the node is determined based on the prior probability and the conditional probability, that is, the occurrence probability of the predicted fault event corresponding to the node. According to the method and the device, the Bayesian network model is used for correcting the prior probability of each predicted fault event, so that the calculated occurrence probability of the predicted fault event is more accurate, and the accuracy of system fault prediction is further improved.
The embodiments described above describe a scheme for determining the probability of occurrence of each predicted failure event based on the prior probability and the conditional probability of each predicted failure event. In another embodiment of the present application, the probability of occurrence of each predicted failure event may be calculated by a bayesian formula. For example, the "determining the occurrence probability of the predicted failure event according to the conditional probability of the predicted failure event and the prior probability of the predicted failure event" mentioned above specifically includes:
substituting the conditional probability and the prior probability into a formula containing the following calculation formula to calculate the occurrence probability of the predicted fault event;
wherein, a is used to represent the predicted failure event a, B is used to represent the predicted failure event B, P (a) is the prior probability of the predicted failure event a, P (B) is the prior probability of the predicted failure event B, P (B | a) is the conditional probability of the predicted failure event a, and P (a | B) is the occurrence probability of the predicted failure event a.
In specific implementation, the prior probability and the conditional probability of each predicted fault event can be substituted into the bayesian formula, and the occurrence probability of each predicted fault event is calculated.
The prior probability of each predicted fault event and each conditional probability of the N conditional probabilities can be respectively substituted into the bayesian formula, and the N occurrence probabilities of each predicted fault event are calculated.
Wherein, a is a predicted fault event which needs to be subjected to probability calculation, B is one of the predicted fault events which can cause the predicted fault event a to occur, P (a) is a prior probability of the predicted fault event a, P (B) is a prior probability of the predicted fault event B, and P (B | a) is a conditional probability of the predicted fault event a, that is, the probability of the predicted fault event B occurring under the condition of the predicted fault event a; p (a | B) is the probability of occurrence of the predicted failure event a, i.e., the probability of occurrence of the predicted failure event a under the conditions of the predicted failure event B.
According to the method and the device, the prior probability and the conditional probability of each predicted fault event can be substituted into a Bayesian formula, and the occurrence probability of each predicted fault event can be obtained through calculation. And the prior probability of each predicted fault event is corrected by using a Bayesian formula, so that the calculated occurrence probability of the predicted fault event is more accurate, and the accuracy of system fault prediction is further improved.
The embodiments described hereinbefore describe a scheme for determining a reference failure event from predicted failure events. In another embodiment of the present application, a reference fault event may be determined from the predicted fault events based on the probability of occurrence of each predicted fault event and a threshold. For example, the aforementioned "determining a reference fault event from predicted fault events based on event occurrence probability" specifically includes:
and determining the predicted fault events with the occurrence probability larger than a first preset threshold value in the predicted fault events as reference fault events.
The embodiment of the application can analyze the predicted fault events with higher occurrence probability in the predicted fault events.
In a specific implementation, a probability threshold may be set as a first preset threshold, then all the occurrence probabilities of all the predicted fault events obtained by the above calculation are determined one by one, and the predicted fault event corresponding to the occurrence probability greater than the first preset threshold is determined as a reference fault event.
According to the method and the device, the predicted fault events with the probability larger than the first preset threshold value can be screened out from all the predicted fault events according to the occurrence probability of each predicted fault event, and the screened predicted fault events are determined as the reference fault events. Therefore, the method and the device can screen out part of the predicted fault events from all the predicted fault events to analyze, and improve the efficiency of system fault prediction while ensuring the accuracy of the system fault prediction.
The embodiments described above describe a scheme for determining the outcome of a fault prediction for a banking system. In another embodiment of the present application, the failure event of the banking system, i.e. the failure prediction result of the banking system, may be determined according to the related event of the reference failure event. For example, the "determining a fault prediction result of a banking system based on a reference fault event" referred to above specifically includes the steps as shown in fig. 5:
in the embodiment of the present application, when analyzing the reference fault event, the FMEA may be used to analyze the reference fault event.
In a specific implementation, a reference fault event to be analyzed can be used as a potential failure mode, and all possible consequences caused by the reference fault event are analyzed. Specifically, all other possible fault events caused by the reference fault event may be analyzed, and taken as relevant events of the reference fault event.
In a specific implementation, the determined related event of the reference fault event may be further analyzed, so as to determine a fault event of the banking system. Specifically, the number of related events of the reference fault event may be analyzed, and the reference fault event whose number of related events is greater than a preset threshold may be determined as the fault event of the banking system. Whether a core event exists in the related events of the reference fault event or not can be analyzed, if the core event exists in the related events of the reference fault event, the reference fault event is determined as the fault event of the bank system, or the reference fault event and the core event in the related events of the reference fault event are determined as the fault event of the bank system. In order to ensure the safety of the banking system and the accuracy of the fault prediction, all related fault events of the reference fault event may also be determined as fault events of the banking system.
According to the embodiment of the application, the FMEA can be used for analyzing the reference fault event, determining the related event of the reference fault event, and further analyzing the related event, so that the fault event of the bank system is determined. Therefore, the embodiment of the application can combine the FTA and the FMEA, so that each reference fault event is comprehensively analyzed, and the logical relationship between the fault events can be completely explained. And related events of the reference fault event are further analyzed, the fault event of the bank system is determined according to the result of the double analysis of the reference fault event, and the accuracy of system fault prediction is improved.
The embodiments described hereinbefore describe a scheme for determining a fault event of a banking system based on a related event with reference to the fault event. In another embodiment of the present application, the fault event of the banking system may be determined according to the degree of correlation of each related event of the reference fault events. For example, the "determining a fault event of a banking system according to a related event" referred to above specifically includes the steps as shown in fig. 6:
in the embodiment of the application, the fault event of the system can be determined according to the correlation degree of the related event of the reference fault event.
In a specific implementation, when the correlation degree of each related event is determined, whether the related event is a core event or not may be determined, and if the related event is a core event, it may be indicated that the correlation degree of the related event and the core security event of the banking system is relatively large. If the related event is a non-core event, it can indicate that the related event is less related to the core security event of the banking system. The closer the event and the core safety event are in the fault book model, the greater the correlation degree of the event and the core safety event in all the related events which are core events in essence; conversely, the farther the event is in the fault book model from the core security event, the less relevant it is.
The core security event of the bank system is a top event of the bank system, the core event is a fault event affecting the core function of the bank system, and the non-core event is a fault event affecting the non-core function of the bank system. Aiming at a background system of the queuing and calling machine, the fault of the background system of the queuing and calling machine is a core safety event. Fault events affecting the number taking and calling functions of the system are core events, such as a background system fault of a queuing and calling machine, an online fault, a fault of an HTTP direct connection interface, a page fault, a fault of a service interface, a program logic error, an HTTP connection failure and a service interface registration failure. The fault events influencing the functions of file downloading, setting and the like of the queuing machine are non-core events, such as batch faults, Entegor workflow faults, database faults, data loss and disk array damage.
The correlation degree of batch faults, Entegor workflow faults, database faults, data loss, disk array damage and queuing machine background system faults is small. The correlation degree of online faults, HTTP direct connection interface faults, page faults, service interface faults, program logic errors, HTTP connection failures, service interface registration failures and queuing call machine background system faults is larger. And the correlation degree of the online fault is larger than that of the HTTP direct connection interface fault, the page fault and the service interface fault, and the correlation degree of the HTTP direct connection interface fault, the page fault and the service interface fault is larger than that of the program logic error, the HTTP connection failure and the service interface registration failure.
In a specific implementation, the relevance degree of each relevant event may be assigned according to the magnitude relationship between the relevance degrees of all the relevant events. Then, a preset threshold of the degree of correlation is set, which is a second preset threshold. And then judging and processing the correlation degree of each related event, and determining the related events with the correlation degree larger than a second preset threshold value as fault events of the bank system.
The related events of all the reference fault events can also be arranged in a descending order according to the degree of correlation. Then, a position threshold is set as a second preset threshold, for example, a 5 th related event. And determining the related events before the second preset threshold as fault events of the bank system. For example, if all related fault events of the reference fault events are program logic errors, HTTP direct connection interface faults, HTTP connection faults, page faults, online faults, faults of a background system of the queuing machine, data loss, database faults, and batch faults. And performing descending arrangement on the related events according to the correlation degree, and sequentially performing background system failure, online failure, HTTP direct connection interface failure, page failure, program logic error, HTTP connection failure, batch failure, database failure and data loss on the queuing machine. The queuing machine background system failure, the online failure, the HTTP direct interface failure, and the page failure that are ranked before the 5 th related event can be determined as the failure event of the queuing machine background system.
The embodiment of the application introduces a method for determining the fault event of a bank system according to the correlation degree of the related event and the core security event. Specifically, according to a certain rule, the magnitude relationship between the degrees of correlation of all the related events may be determined, and one or more related events with a greater degree of correlation may be determined as a fault event of the banking system. Therefore, after each reference fault event is analyzed, the related events of the reference fault events can be further analyzed, the fault events of the bank system are determined according to the results of the double analysis of the reference fault events, and the accuracy of system fault prediction is improved.
It should be understood that, although the steps in the flowcharts related to the embodiments as described above are sequentially displayed as indicated by arrows, the steps are not necessarily performed sequentially as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least a part of the steps in the flowcharts related to the embodiments described above may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the execution order of the steps or stages is not necessarily sequential, but may be rotated or alternated with other steps or at least a part of the steps or stages in other steps.
Based on the same inventive concept, the embodiment of the application also provides a system fault prediction device for realizing the system fault prediction method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the method, so specific limitations in one or more embodiments of the system fault prediction device provided below can be referred to the limitations of the system fault prediction method in the foregoing, and details are not described herein again.
In one embodiment, as shown in fig. 7, there is provided a system failure prediction apparatus including: the device comprises a prediction module, a reference fault event determination module and a fault prediction result determination module, wherein:
the prediction module 701 is used for performing preliminary fault prediction on the bank system based on a fault tree analysis algorithm and operation data of the bank system to obtain a predicted fault event of the bank system; predicting fault events comprising a top event, all intermediate events corresponding to the top event and all bottom events corresponding to the top event;
a reference fault event determining module 702, configured to determine an occurrence probability of each top event, an occurrence probability of each middle event, and an occurrence probability of each bottom event, and determine a reference fault event from the predicted fault events based on the event occurrence probabilities;
and a failure prediction result determining module 703, configured to determine a failure prediction result of the banking system based on the reference failure event.
In one embodiment, the reference fault event determination module 702 is specifically configured to determine a logical relationship between predicted fault events of the banking system, and determine a conditional probability of each predicted fault event based on the logical relationship; and determining the occurrence probability of the predicted fault event according to the conditional probability of the predicted fault event and the prior probability of the predicted fault event.
In one embodiment, determining the probability of occurrence of the predicted fault event based on the conditional probability of the predicted fault event and the prior probability of the predicted fault event comprises: substituting the conditional probability and the prior probability into a formula containing the following calculation formula to calculate the occurrence probability of the predicted fault event;
wherein A is used for representing a predicted failure event A, B is used for representing a predicted failure event B, P (A) is the prior probability of the predicted failure event A, and P (B) is the prior probability of the predicted failure event B; p (B | a) is the conditional probability of predicting failure event a; p (a | B) is the probability of occurrence of the predicted failure event a.
In an embodiment, the reference fault event determining module 702 is specifically configured to determine, as the reference fault event, a predicted fault event with an occurrence probability greater than a first preset threshold in the predicted fault events.
In an embodiment, the failure prediction result determining module 703 is specifically configured to determine a related event of a reference failure event based on the failure mode and the influence analysis algorithm, where the related event is an event caused by the reference failure event; and determining the fault event of the bank system according to the related event.
In one embodiment, determining a fault event for a banking system based on the related events includes: determining a degree of correlation for each correlated event; the degree of correlation is used for representing the degree of correlation between the related events and core security events of the bank system; and determining the fault event of the banking system according to the related events of which the degree of correlation is greater than a second preset threshold value.
The modules in the system failure prediction device can be wholly or partially implemented by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 8. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used to store some data related to the system failure prediction method of the embodiment of the present application, for example, the data of the prior probability, the conditional probability, the occurrence probability, and the like of each predicted failure event described above. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a system failure prediction method.
Those skilled in the art will appreciate that the architecture shown in fig. 8 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory and a processor, the memory having a computer program stored therein, the processor implementing the following steps when executing the computer program:
performing primary fault prediction on the bank system based on a fault tree analysis algorithm and operation data of the bank system to obtain a predicted fault event of the bank system; predicting fault events comprising a top event, all intermediate events corresponding to the top event and all bottom events corresponding to the top event;
determining the occurrence probability of each top event, the occurrence probability of each middle event and the occurrence probability of each bottom event, and determining a reference fault event from the predicted fault events based on the event occurrence probabilities;
a fault prediction result for the banking system is determined based on the reference fault event.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
determining the probability of occurrence of each top event, the probability of occurrence of each middle event, and the probability of occurrence of each bottom event, comprising: determining a logical relationship between predicted fault events of the banking system, and determining a conditional probability of each predicted fault event based on the logical relationship; and determining the occurrence probability of the predicted fault event according to the conditional probability of the predicted fault event and the prior probability of the predicted fault event.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
determining the occurrence probability of the predicted fault event according to the conditional probability of the predicted fault event and the prior probability of the predicted fault event, wherein the determining comprises the following steps: substituting the conditional probability and the prior probability into a formula containing the following calculation formula to calculate the occurrence probability of the predicted fault event;
wherein A is used for representing a predicted failure event A, B is used for representing a predicted failure event B, P (A) is the prior probability of the predicted failure event A, and P (B) is the prior probability of the predicted failure event B; p (B | a) is the conditional probability of predicting failure event a; p (a | B) is the probability of occurrence of the predicted failure event a.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
determining a reference fault event from the predicted fault events based on the event occurrence probability, comprising: and determining the predicted fault events with the occurrence probability larger than a first preset threshold value in the predicted fault events as reference fault events.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
determining a fault prediction result for the banking system based on the reference fault event, including: determining related events of the reference fault events based on the fault modes and the influence analysis algorithm, wherein the related events are events caused by the reference fault events; and determining the fault event of the bank system according to the related event.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
determining a fault event of a banking system according to the related events, comprising: determining a degree of correlation for each correlated event; the degree of correlation is used for representing the degree of correlation between the related events and core security events of the bank system; and determining the fault event of the banking system according to the related events of which the degree of correlation is greater than a second preset threshold value.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of:
performing primary fault prediction on the bank system based on a fault tree analysis algorithm and operation data of the bank system to obtain a predicted fault event of the bank system; predicting fault events comprising a top event, all intermediate events corresponding to the top event and all bottom events corresponding to the top event;
determining the occurrence probability of each top event, the occurrence probability of each middle event and the occurrence probability of each bottom event, and determining a reference fault event from the predicted fault events based on the event occurrence probabilities;
a fault prediction result for the banking system is determined based on the reference fault event.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining the probability of occurrence of each top event, the probability of occurrence of each middle event, and the probability of occurrence of each bottom event, comprising: determining a logical relationship between predicted fault events of the banking system, and determining a conditional probability of each predicted fault event based on the logical relationship; and determining the occurrence probability of the predicted fault event according to the conditional probability of the predicted fault event and the prior probability of the predicted fault event.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining the occurrence probability of the predicted fault event according to the conditional probability of the predicted fault event and the prior probability of the predicted fault event, wherein the determining comprises the following steps: substituting the conditional probability and the prior probability into a formula containing the following calculation formula to calculate the occurrence probability of the predicted fault event;
wherein A is used for representing a predicted failure event A, B is used for representing a predicted failure event B, P (A) is the prior probability of the predicted failure event A, and P (B) is the prior probability of the predicted failure event B; p (B | a) is the conditional probability of predicting failure event a; p (a | B) is the probability of occurrence of the predicted failure event a.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a reference fault event from the predicted fault events based on the event occurrence probability, comprising: and determining the predicted fault events with the occurrence probability larger than a first preset threshold value in the predicted fault events as reference fault events.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a fault prediction result for the banking system based on the reference fault event, including: determining related events of the reference fault events based on the fault modes and the influence analysis algorithm, wherein the related events are events caused by the reference fault events; and determining the fault event of the bank system according to the related event.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a fault event of a banking system according to the related events, comprising: determining a degree of correlation for each correlated event; the degree of correlation is used for representing the degree of correlation between the related events and core security events of the bank system; and determining the fault event of the banking system according to the related events of which the degree of correlation is greater than a second preset threshold value.
In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, performs the steps of:
performing primary fault prediction on the bank system based on a fault tree analysis algorithm and operation data of the bank system to obtain a predicted fault event of the bank system; predicting fault events comprising a top event, all intermediate events corresponding to the top event and all bottom events corresponding to the top event;
determining the occurrence probability of each top event, the occurrence probability of each middle event and the occurrence probability of each bottom event, and determining a reference fault event from the predicted fault events based on the event occurrence probabilities;
a fault prediction result for the banking system is determined based on the reference fault event.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining the probability of occurrence of each top event, the probability of occurrence of each middle event, and the probability of occurrence of each bottom event, comprising: determining a logical relationship between predicted fault events of the banking system, and determining a conditional probability of each predicted fault event based on the logical relationship; and determining the occurrence probability of the predicted fault event according to the conditional probability of the predicted fault event and the prior probability of the predicted fault event.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining the occurrence probability of the predicted fault event according to the conditional probability of the predicted fault event and the prior probability of the predicted fault event, wherein the determining comprises the following steps: substituting the conditional probability and the prior probability into a formula containing the following calculation formula to calculate the occurrence probability of the predicted fault event;
wherein A is used for representing a predicted failure event A, B is used for representing a predicted failure event B, P (A) is the prior probability of the predicted failure event A, and P (B) is the prior probability of the predicted failure event B; p (B | a) is the conditional probability of predicting failure event a; p (a | B) is the probability of occurrence of the predicted failure event a.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a reference fault event from the predicted fault events based on the event occurrence probability, comprising: and determining the predicted fault events with the occurrence probability larger than a first preset threshold value in the predicted fault events as reference fault events.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a fault prediction result for the banking system based on the reference fault event, including: determining related events of the reference fault events based on the fault modes and the influence analysis algorithm, wherein the related events are events caused by the reference fault events; and determining the fault event of the bank system according to the related event.
In one embodiment, the computer program when executed by the processor further performs the steps of:
determining a fault event of a banking system according to the related events, comprising: determining a degree of correlation for each correlated event; the degree of correlation is used for representing the degree of correlation between the related events and core security events of the bank system; and determining the fault event of the banking system according to the related events of which the degree of correlation is greater than a second preset threshold value.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read-Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high-density embedded nonvolatile Memory, resistive Random Access Memory (ReRAM), Magnetic Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases referred to in various embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. A method for system failure prediction, the method comprising:
performing primary fault prediction on the bank system based on a fault tree analysis algorithm and operation data of the bank system to obtain a predicted fault event of the bank system; the predicted fault event comprises a top event, all intermediate events corresponding to the top event and all bottom events corresponding to the top event;
determining the occurrence probability of each top event, the occurrence probability of each middle event and the occurrence probability of each bottom event, and determining a reference fault event from the predicted fault events based on the event occurrence probabilities;
determining a fault prediction result for the banking system based on the reference fault event.
2. The method of claim 1, wherein determining the probability of occurrence of each of the top events, the probability of occurrence of each of the intermediate events, and the probability of occurrence of each of the bottom events comprises:
determining a logical relationship between predicted failure events of the banking system, determining a conditional probability of each of the predicted failure events based on the logical relationship;
and determining the occurrence probability of the predicted fault event according to the conditional probability of the predicted fault event and the prior probability of the predicted fault event.
3. The method of claim 2, wherein determining the probability of occurrence of the predicted fault event based on the conditional probability of the predicted fault event and the prior probability of the predicted fault event comprises:
substituting the conditional probability and the prior probability into a formula containing the following calculation formula to calculate the occurrence probability of the predicted fault event;
wherein A is used for representing a predicted failure event A, B is used for representing a predicted failure event B, P (A) is the prior probability of the predicted failure event A, and P (B) is the prior probability of the predicted failure event B; p (B | a) is the conditional probability of predicting failure event a; p (a | B) is the probability of occurrence of the predicted failure event a.
4. The method of claim 1, wherein determining a reference fault event from the predicted fault events based on the event occurrence probability comprises:
and determining the predicted fault events with the occurrence probability larger than a first preset threshold value in the predicted fault events as the reference fault events.
5. The method of claim 1, wherein determining a fault prediction outcome for the banking system based on the reference fault event comprises:
determining a related event of the reference fault event based on a fault mode and an influence analysis algorithm, wherein the related event is an event caused by the reference fault event;
and determining the fault event of the bank system according to the related event.
6. The method of claim 5, wherein said determining a fault event for the banking system based on the related event comprises:
determining a degree of correlation for each of the correlated events; the correlation degree is used for representing the correlation degree of the correlation event and the core security event of the banking system;
and determining the fault event of the bank system according to the related events of which the related degrees are greater than a second preset threshold value.
7. A system failure prediction apparatus, the apparatus comprising:
the prediction module is used for carrying out preliminary fault prediction on the bank system based on a fault tree analysis algorithm and operation data of the bank system to obtain a predicted fault event of the bank system; the predicted fault event comprises a top event, all intermediate events corresponding to the top event and all bottom events corresponding to the top event;
a reference fault event determination module, configured to determine an occurrence probability of each top event, an occurrence probability of each middle event, and an occurrence probability of each bottom event, and determine a reference fault event from the predicted fault events based on event occurrence probabilities;
and the fault prediction result module is used for determining a fault prediction result of the bank system based on the reference fault event.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111532573.5A CN114186031A (en) | 2021-12-15 | 2021-12-15 | System fault prediction method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111532573.5A CN114186031A (en) | 2021-12-15 | 2021-12-15 | System fault prediction method, device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114186031A true CN114186031A (en) | 2022-03-15 |
Family
ID=80605116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111532573.5A Pending CN114186031A (en) | 2021-12-15 | 2021-12-15 | System fault prediction method, device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114186031A (en) |
-
2021
- 2021-12-15 CN CN202111532573.5A patent/CN114186031A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11269718B1 (en) | Root cause detection and corrective action diagnosis system | |
| US11487996B2 (en) | Real-time predictive maintenance of hardware components using a stacked deep learning architecture on time-variant parameters combined with a dense neural network supplied with exogeneous static outputs | |
| CN110888788A (en) | Anomaly detection method and device, computer equipment and storage medium | |
| US20210097431A1 (en) | Debugging and profiling of machine learning model training | |
| US20200053108A1 (en) | Utilizing machine intelligence to identify anomalies | |
| US20210097433A1 (en) | Automated problem detection for machine learning models | |
| CN113822421A (en) | Neural network based anomaly positioning method, system, equipment and storage medium | |
| Benmessahel et al. | Predictability of fuzzy discrete event systems | |
| US11468365B2 (en) | GPU code injection to summarize machine learning training data | |
| CN114881349A (en) | Big data analysis-based early warning method and storage medium | |
| Dhanalaxmi et al. | A review on software fault detection and prevention mechanism in software development activities | |
| Pinto et al. | Hadoop distributed computing clusters for fault prediction | |
| CN117033039A (en) | Fault detection method, device, computer equipment and storage medium | |
| CN111626498A (en) | Equipment operation state prediction method, device, equipment and storage medium | |
| Wang et al. | How long will it take to mitigate this incident for online service systems? | |
| CN112379913B (en) | Software optimization method, device, equipment and storage medium based on risk identification | |
| Wang et al. | Understanding and predicting incident mitigation time | |
| WO2021067385A1 (en) | Debugging and profiling of machine learning model training | |
| Samarakoon et al. | System abnormality detection in stock market complex trading systems using machine learning techniques | |
| CN114186031A (en) | System fault prediction method, device, computer equipment and storage medium | |
| Kirschenmann et al. | Decision dependent stochastic processes | |
| US20230035666A1 (en) | Anomaly detection in storage systems | |
| CN114743703A (en) | Reliability analysis method, device, equipment and storage medium for nuclear power station unit | |
| Georgoulopoulos et al. | A survey on hardware failure prediction of servers using machine learning and deep learning | |
| Zheng et al. | On the sensitivity of stationary solutions of Markov regenerative processes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |