Banking system error diagnosis method, device, medium and system

Abstract

This application provides a method, apparatus, medium, and system for diagnosing errors in a banking system. The method includes: constructing a structure tree model to store parameters of various monitoring points related to the operation of the banking system; receiving system anomaly information and querying the structure tree model based on the anomaly information to obtain input parameters of monitoring points related to the anomaly information, including CPU utilization, memory usage, disk I / O, and network latency; inputting the obtained input parameters into a pre-trained neural network model to process the input parameters; obtaining the model results output by the neural network model and generating corresponding alarm information based on the model results to indicate operational errors and / or program errors. This solves the problem that, when a system anomaly or fault occurs, it is often difficult to quickly determine the source of the problem and the service point due to the lack of an effective localization mechanism.

Description

Technical Field

[0001] This application relates to the field of banking system technology, and more specifically, to a banking system error diagnosis method, a banking system error diagnosis device, a computer-readable storage medium, and a banking system error diagnosis system. Background Technology

[0002] In the traditional operation and management of core financial systems, especially large-scale banking systems with centralized architectures, the operation and maintenance model is relatively fixed, mainly relying on manual monitoring and post-event response. In a distributed architecture, the core system is decomposed into numerous independent service nodes, each responsible for a specific functional module. This brings significant performance improvements, modular management, and resource optimization. However, it also introduces a series of challenges, especially for operation and maintenance management. The complex system structure and the large number of device nodes greatly increase the difficulty and cost of operational assurance. Specifically, this manifests as follows:

[0003] Increased operation and maintenance costs: The number of servers and application instances that need to be monitored in a distributed architecture has surged, placing higher demands on the technical capabilities and workload of operation and maintenance personnel.

[0004] Difficulty in locating problems: When a system malfunctions or fails, the lack of an effective location mechanism often makes it difficult to quickly identify the source of the problem and the service point, thus slowing down the resolution of the problem.

[0005] Inefficient communication: Information transfer between the operations and maintenance team and the development team is not smooth enough, especially in emergency situations, which may affect the rapid response and resolution of problems. Summary of the Invention

[0006] The main purpose of this application is to provide a method, device, computer-readable storage medium, and system for diagnosing errors in a banking system, so as to at least solve the problem that when a system is abnormal or malfunctioning, it is often difficult to quickly determine the source and service point of the problem due to the lack of an effective localization mechanism.

[0007] To achieve the above objectives, according to one aspect of this application, a method for diagnosing errors in a banking system is provided. The method includes: constructing a structure tree model to store parameters of various monitoring points related to the operation of the banking system; receiving system anomaly information and querying the structure tree model based on the system anomaly information to obtain input parameters of monitoring points related to the system anomaly information, the parameters of the monitoring points including CPU utilization, memory usage, disk I / O, and network latency; inputting the obtained input parameters into a pre-trained neural network model to process the input parameters; obtaining the model results output by the neural network model and generating corresponding alarm information based on the model results to indicate operational errors and / or program errors.

[0008] Optionally, the model results include operational error confidence and program error confidence. Based on the model results, corresponding alarm information is generated, including: generating a first alarm message to indicate an operational error when the operational error confidence is greater than the program error confidence; generating a second alarm message to indicate a program error when the operational error confidence is less than the program error confidence; and generating a third alarm message to indicate both operational and program errors when the operational error confidence is equal to the program error confidence.

[0009] Optionally, obtaining the input parameters of the monitoring points related to the system anomaly information includes: extracting target keywords from the system anomaly information; searching for monitoring points related to the target keywords from the structure tree model based on the target keywords, obtaining all relevant parameters of the monitoring points related to the target keywords, and using all the relevant parameters as the input parameters.

[0010] Optionally, after generating corresponding alarm information based on the model results, the method further includes: storing the mapping relationship between the target keyword and the unique identifier of the input parameter in a keyword database; and when a new abnormal keyword matches the keyword stored in the keyword database, retrieving the corresponding input parameter from the structure tree model based on the unique identifier of the input parameter.

[0011] Optionally, after generating corresponding alarm information based on the model results, the method further includes: if the alarm information indicates an operational error, displaying the corresponding operation guide in a visual manner; if the alarm information indicates a program error, triggering a code review process to query code defects and perform code repair operations.

[0012] Optionally, generating corresponding alarm information based on the model results includes: sending the model results to a target terminal, wherein the target terminal is a terminal used by the developers; receiving the target error result sent by the target terminal; and generating corresponding alarm information based on the target error result.

[0013] Optionally, generating corresponding alarm information based on the target error result includes: generating a first alarm message to indicate an operation error when the target error result indicates an operation error; generating a second alarm message to indicate a program error when the target error result indicates a program error; and generating a third alarm message to indicate both operation and program errors when the target error result indicates both operation and program errors.

[0014] According to another aspect of this application, a bank system error diagnosis device is provided, comprising: a construction unit for constructing a structure tree model, the structure tree model being used to store parameters of various monitoring points related to the operation of the bank system; a first processing unit for receiving system anomaly information and querying the structure tree model according to the system anomaly information to obtain input parameters of monitoring points related to the system anomaly information, the parameters of the monitoring points including CPU utilization, memory usage, disk I / O, and network latency; a second processing unit for inputting the obtained input parameters into a pre-trained neural network model, so that the neural network model processes the input parameters; and a third processing unit for obtaining the model results output by the neural network model and generating corresponding alarm information according to the model results to indicate operational errors and / or program errors.

[0015] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform any of the methods described.

[0016] According to another aspect of this application, a bank system error diagnosis system is provided, comprising: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including methods for performing any one of the methods described.

[0017] Applying the technical solution of this application, the structure tree model organizes the operational monitoring points of the banking system according to a hierarchical structure. Each monitoring point stores its associated parameters, such as CPU utilization, memory usage, disk I / O, and network latency. This approach provides a clear framework for visually assessing the health status of each part of the system and locating anomalies. When the system detects anomalies, it queries the parameters of related monitoring points through the structure tree model. This query process is based on the correlation between the anomaly and the monitoring points, quickly pinpointing potential sources of failure. The retrieved monitoring point parameters are then input into a pre-trained neural network model. Trained on extensive operational data, the neural network model can identify anomaly patterns under different parameter combinations, providing intelligent analysis for anomaly localization. Alarm information is generated based on the output of the neural network model. This information can be specific to errors in a particular service or operation, helping maintenance personnel quickly identify the nature of the problem (operational error or program error) and take targeted measures. Over time, the structure tree model and neural network model can be continuously optimized, such as by adding more monitoring points or adjusting the training data of the neural network, to improve the accuracy and efficiency of anomaly localization. This solves the problem that when a system malfunctions or fails, it is often difficult to quickly determine the source of the problem and the service point due to the lack of an effective localization mechanism. Attached Figure Description

[0018] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0019] Figure 1 A flowchart illustrating a bank system error diagnosis method according to an embodiment of this application is shown.

[0020] Figure 2 A structural block diagram of a bank system error diagnosis device provided according to an embodiment of this application is shown. Detailed Implementation

[0021] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0022] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0023] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application 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 for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover 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.

[0024] As described in the background section, the structure tree model organizes the operational monitoring points of the banking system according to a hierarchical structure. Each monitoring point stores its associated parameters, such as CPU utilization, memory usage, disk I / O, and network latency. This approach provides a clear framework for visually assessing the health status of each part of the system and locating anomalies. When the system detects anomalies, it queries the parameters of related monitoring points through the structure tree model. This query process is based on the correlation between the anomaly and the monitoring points, quickly pinpointing the potential source of the fault. The retrieved monitoring point parameters are then input into a pre-trained neural network model. Trained on extensive operational data, the neural network model can identify anomaly patterns under different parameter combinations, providing intelligent analysis for anomaly localization. Alarm information is generated based on the output of the neural network model. This information can be specific to errors in a particular service or operation, helping maintenance personnel quickly identify the nature of the problem (operational error or program error) and take targeted measures. Over time, the structure tree model and neural network model can be continuously optimized, such as by adding more monitoring points or adjusting the training data of the neural network, to improve the accuracy and efficiency of anomaly localization. This addresses the problem that, when system anomalies or faults occur, the lack of an effective localization mechanism often makes it difficult to quickly determine the source of the problem and the service point. To address the problem that, due to the lack of an effective localization mechanism, it is often difficult to quickly determine the source and service point of a system error when an anomaly or malfunction occurs, embodiments of this application provide a method, apparatus, computer-readable storage medium, and system for diagnosing errors in a banking system.

[0025] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0026] This embodiment provides a method for diagnosing errors in a banking system. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] Figure 1 This is a flowchart of a bank system error diagnosis method according to an embodiment of this application. Figure 1 As shown, the method includes the following steps:

[0028] Step S101: Construct a structure tree model. The structure tree model is used to store the parameters of each monitoring point related to the operation of the banking system.

[0029] Step S102: Receive system anomaly information and query the structure tree model based on the system anomaly information to obtain the input parameters of the monitoring points related to the system anomaly information. The parameters of the monitoring points include CPU utilization, memory usage, disk I / O and network latency.

[0030] Disk I / O (Input and Output) refers to disk input and output operations, which are the processes of data exchange between a computer system and disk storage devices. Disk I / O operations mainly involve reading and writing data. When a computer needs to read data from the disk, it sends an I / O request to the disk. After receiving the request, the disk converts it into a disk read operation. When a computer needs to write data to the disk, it also sends an I / O request. After receiving the request, the disk performs the corresponding write operation.

[0031] Step S103: Input the obtained input parameters into the pre-trained neural network model so that the neural network model processes the input parameters.

[0032] Step S104: Obtain the model results output by the above neural network model, and generate corresponding alarm information based on the above model results to indicate operation errors and / or program errors.

[0033] In the steps described above, the structure tree model organizes the operational monitoring points of the banking system according to a hierarchical structure. Each monitoring point stores its associated parameters, such as CPU utilization, memory usage, disk I / O, and network latency. This provides a clear framework for visually assessing the health status of each part of the system and locating anomalies. When the system detects anomalies, it queries the parameters of related monitoring points through the structure tree model. This query process is based on the correlation between the anomaly and the monitoring points, quickly pinpointing the possible source of the fault. The retrieved monitoring point parameters are then input into a pre-trained neural network model. Trained on a large amount of operational data, the neural network model can identify anomaly patterns under different parameter combinations, providing intelligent analysis for anomaly localization. Alarm information is generated based on the output of the neural network model. This information can be specific to errors in a particular service or operation, helping maintenance personnel quickly identify the nature of the problem (operational error or program error) and take targeted measures. Over time, the structure tree model and neural network model can be continuously optimized, such as by adding more monitoring points or adjusting the training data of the neural network, to improve the accuracy and efficiency of anomaly localization. This solves the problem that, when system anomalies or faults occur, the lack of an effective localization mechanism often makes it difficult to quickly determine the source of the problem and the service point.

[0034] In one specific embodiment of this application, the above model results include operational error confidence and program error confidence. Generating corresponding alarm information based on the above model results includes: generating a first alarm message to indicate an operational error when the operational error confidence is greater than the program error confidence; generating a second alarm message to indicate a program error when the operational error confidence is less than the program error confidence; and generating a third alarm message to indicate both operational and program errors when the operational error confidence is equal to the program error confidence.

[0035] By quantifying the confidence levels of operational and procedural errors, the source of problems can be more accurately determined, avoiding blindly switching between operational and procedural investigations, thus greatly improving the efficiency and accuracy of problem diagnosis. The first alarm message indicates an operational error, helping to immediately correct inappropriate actions and prevent further system impact; the second alarm message indicates a procedural error, initiating a software repair process to ensure code quality; the third alarm message indicates that the problem may stem from both operational and procedural factors, requiring a more detailed joint investigation to ensure a comprehensive solution. When the confidence levels of operational and procedural errors are equal, a third alarm message is generated, indicating a possible dual problem, avoiding misjudgment based on a single cause and ensuring the effectiveness and accuracy of the alarm information. By rapidly identifying and responding to errors, whether at the operational or procedural level, problems can be resolved promptly, reducing user waiting time and system downtime, thereby improving user experience and satisfaction. Clearly categorized alarm messages facilitate the rapid mobilization of appropriate resources (such as operators or developers) to intervene in troubleshooting, simplifying communication and collaboration between teams and reducing the time cost of troubleshooting.

[0036] In one specific embodiment of this application, obtaining the input parameters of the monitoring points related to the above-mentioned system anomaly information includes: extracting target keywords from the above-mentioned system anomaly information; searching for monitoring points related to the above-mentioned target keywords from the structure tree model based on the above-mentioned target keywords, obtaining all relevant parameters of the monitoring points related to the above-mentioned target keywords, and using all the above-mentioned relevant parameters as the above-mentioned input parameters.

[0037] By extracting keywords from anomaly information, the modules or services where anomalies may occur can be quickly identified, and specific monitoring points can be found through a structure tree model. This is more efficient than traditional full-system scanning or manual inspection, significantly reducing the time required for problem localization. Utilizing the correlation between keywords and the structure tree model reduces false alarms caused by improper monitoring point configuration, while also lowering the risk of missing actual anomalies due to insufficient monitoring, thus improving the accuracy of anomaly detection. When the system is large and complex, comprehensive monitoring consumes a lot of resources. Keyword-driven monitoring point localization allows for targeted retrieval of parameters from specific monitoring points, avoiding unnecessary resource waste and optimizing the overall resource allocation of the monitoring system. Once an anomaly is identified, all parameters from relevant monitoring points are immediately retrieved as input parameters, facilitating rapid analysis of the anomaly's cause and the development of recovery strategies. This is particularly important for distributed systems, as the high coupling between system components makes rapid response and recovery crucial for maintaining system stability and service continuity. Automated parameter extraction and monitoring point localization contribute to building intelligent operation and maintenance systems. The system can automatically retrieve monitoring point parameters based on anomaly information, perform preliminary analysis, and even trigger preset fault handling procedures, thereby reducing the workload of operation and maintenance personnel and improving operational efficiency. The structure tree model is essentially a knowledge graph. By continuously updating the relationship between anomaly information and monitoring points, this knowledge graph can be continuously enriched and optimized, making it an important tool for anomaly prediction and proactive prevention.

[0038] In one specific embodiment of this application, after generating corresponding alarm information based on the above model results, the method further includes: storing the mapping relationship between the above target keywords and the unique identifiers of the above input parameters in a keyword database; and when a new abnormal keyword matches the keyword stored in the above keyword database, obtaining the corresponding input parameter from the above structure tree model based on the unique identifiers of the above input parameters.

[0039] Specific implementation process:

[0040] Anomaly detection and keyword extraction: When the system detects an anomaly, it analyzes the anomaly log to extract key information describing the anomaly. This key information may include error codes, error messages, transaction types, module names, etc., collectively referred to as "target keywords".

[0041] Generation of unique identifiers for input parameters: For transaction requests or data change requests that trigger an anomaly, the system will automatically generate a unique identifier. This identifier contains information such as the timestamp of the request, the request ID, and the data change ID, which is sufficient to distinguish each request and ensure the traceability of each transaction or data change.

[0042] Mapping relationship establishment and storage: A mapping relationship is established between target keywords and unique identifiers of input parameters. This means that each exception is associated with a specific transaction request or data change request. These mapping relationships are then stored in a specially designed keyword database for subsequent queries and associations.

[0043] New Anomaly Matching and Rapid Location: When an anomaly occurs again, the system automatically checks whether the keywords contained in the anomaly information match any keywords stored in the keyword database. If a match is found, the system can directly find the unique identifier of the input parameter corresponding to the previous anomaly from the structure tree model based on the stored mapping relationship, thereby quickly locating the specific transaction or data change details.

[0044] Historical data utilization and learning: By continuously accumulating the mapping relationship between anomalies and input parameters, the keyword database gradually becomes a historical database for problem diagnosis. This can not only be used for rapid localization of immediate problems, but also serve as a dataset for training future anomaly detection and problem prediction models, improving the overall system's adaptability and intelligence.

[0045] With the support of a keyword database, operations and maintenance (O&M) personnel can quickly find transaction or data change details related to new anomalies, saving time spent manually searching through massive amounts of logs and greatly improving the speed and accuracy of problem localization. Anomaly investigations that previously required repeated checks can now be automated through intelligent matching in the keyword database, effectively reducing the workload of O&M personnel and avoiding repetitive manpower consumption. The keyword database records the associations between all anomalies and input parameters, essentially establishing a knowledge base for problem-solving. This helps newly joined O&M or development personnel quickly master methods for handling common problems, promoting experience accumulation and knowledge sharing within the team.

[0046] In one specific embodiment of this application, after generating corresponding alarm information based on the above model results, the method further includes: if the alarm information indicates an operational error, displaying the corresponding operation guide in a visual manner; if the alarm information indicates a program error, triggering a code review process to query code defects and perform code repair operations.

[0047] Alarm message parsing: When the model detects an anomaly and generates an alarm message, the alarm message is first parsed to determine its nature, whether it is an operational error or a program error. This determination is based on key fields of the alarm message, such as error code, error location, and error description.

[0048] Operation error handling:

[0049] Visualized Guide Display: If the alarm message indicates an operational error, the system will automatically match it to a pre-set operational guide database. This database contains solutions to various common operational errors, each accompanied by a clear visual guide, such as a flowchart, operation video, or text and image instructions. The visual guides are presented in an intuitive and easy-to-understand manner, helping operators quickly understand the cause of the error and the corrective steps.

[0050] Real-time guidance: The system may also provide online real-time guidance services, such as through instant messaging tools or customer service hotlines, with dedicated technical support personnel providing one-on-one guidance to ensure that operators can correctly follow the steps in the guide.

[0051] Program error handling:

[0052] Triggering the code review process: If an alert indicates a program error, the system will automatically initiate the code review process. This may include static code analysis, code quality checks, and dynamic testing and debugging performed by the development team.

[0053] Code Defect Query: The above process identifies code defects that cause errors. The system records these defects and generates a defect report, which includes information such as defect location, scope of impact, and priority.

[0054] Code Fix Operation: Based on the defect report, the development team performs code fix operations. After the fix is ​​completed, regression testing must be performed to ensure that the error has been resolved and that the fix operation has not introduced any new problems.

[0055] Feedback and Optimization: Regardless of whether it's an operational error or a program error, the system collects feedback information after the issue is resolved. This feedback is used to optimize the alarm model and guide database. For example, if the problem persists after the operator follows the guide, the feedback will be used to revise the guide or further refine the classification of alarm information.

[0056] Improving problem-solving efficiency: Real-time, intuitive guidance allows operators to quickly correct errors, avoiding prolonged system downtime. The guidance reduces reliance on advanced technical support, enabling ordinary operators to independently resolve common issues. Code review processes and defect detection mechanisms facilitate continuous code optimization, reducing future program errors and thus improving overall system stability and performance. By automatically triggering error handling processes, the system possesses a degree of self-healing capability, automatically or semi-automatically resolving problems and minimizing manual intervention.

[0057] In one specific embodiment of this application, generating corresponding alarm information based on the above model results includes: sending the above model results to a target terminal, wherein the target terminal is a terminal used by the developer; receiving the target error result sent by the target terminal; and generating corresponding alarm information based on the target error result.

[0058] Developers possess a deeper understanding of the system's internal logic and architecture. They can leverage their expertise to perform secondary verification of model-identified errors, ensuring the accuracy and relevance of alerts, avoiding false alarms or missed alarms, and improving troubleshooting efficiency. Directly notifying developers allows for immediate initiation of the problem-solving process, reducing delays in handling faults. Upon receiving alerts, developers can quickly intervene, analyze the cause of the problem, and develop remediation plans, accelerating problem resolution. This secondary verification by developers provides feedback for model training. If the model reports a false alarm, developers can annotate and provide the correct error information to adjust model parameters and optimize the algorithm, enabling it to more accurately identify errors in the future. This process promotes communication and collaboration between operations and development personnel. After receiving and verifying an alert, developers can engage in detailed discussions with operations personnel to jointly understand the nature of the problem, develop the best solution, and enhance teamwork.

[0059] In one specific embodiment of this application, generating corresponding alarm information based on the above-mentioned target error result includes: generating a first alarm message to indicate an operation error when the above-mentioned target error result indicates an operation error; generating a second alarm message to indicate a program error when the above-mentioned target error result indicates a program error; and generating a third alarm message to indicate both operation and program errors when the above-mentioned target error result indicates both operation and program errors.

[0060] By categorizing errors into two main types—operational errors and program errors—and potentially including both types simultaneously, this approach helps operations and development teams quickly identify problem types and implement targeted solutions, improving the efficiency and accuracy of problem-solving. Traditional alarm systems may struggle to distinguish between operational and program errors, potentially leading operations personnel down a wrong path or failing to identify program-level issues in a timely manner. This method, through clear categorization, reduces the possibility of misjudgment and also lowers the risk of missing critical program errors. First and second alarm messages are sent to the teams responsible for operations and programs, respectively. This promotes effective communication and collaboration between different departments or teams to jointly analyze and resolve problems. Especially in the case of a third alarm message, joint intervention from operations and development teams is necessary to ensure a comprehensive resolution of the issue.

[0061] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0062] This application also provides a bank system error diagnosis device. It should be noted that the bank system error diagnosis device of this application can be used to execute the bank system error diagnosis method provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0063] The following describes the bank system error diagnosis device provided in the embodiments of this application.

[0064] Figure 2 This is a schematic diagram of a bank system error diagnosis device according to an embodiment of this application. Figure 2 As shown, the device includes: a construction unit 21 for constructing a structure tree model, which stores parameters of various monitoring points related to the operation of the banking system; a first processing unit 22 for receiving system anomaly information and querying the structure tree model based on the system anomaly information to obtain input parameters of monitoring points related to the system anomaly information, including CPU utilization, memory usage, disk I / O, and network latency; a second processing unit 23 for inputting the obtained input parameters into a pre-trained neural network model so that the neural network model processes the input parameters; and a third processing unit 24 for obtaining the model results output by the neural network model and generating corresponding alarm information based on the model results to indicate operational errors and / or program errors.

[0065] In one specific embodiment of this application, the above model results include operational error confidence and program error confidence. The third processing unit includes: a first generation module for generating a first alarm message to indicate an operational error when the operational error confidence is greater than the program error confidence; a second generation module for generating a second alarm message to indicate a program error when the operational error confidence is less than the program error confidence; and a third generation module for generating a third alarm message to indicate both operational and program errors when the operational error confidence is equal to the program error confidence.

[0066] In one specific embodiment of this application, the first processing unit includes: an extraction module for extracting target keywords from the above-mentioned system anomaly information; and a search module for searching for monitoring points related to the target keywords from the structure tree model based on the target keywords, obtaining all relevant parameters of the monitoring points related to the target keywords, and using all the relevant parameters as the above-mentioned input parameters.

[0067] In one specific embodiment of this application, the bank system error diagnosis device includes: a fourth processing unit for storing the mapping relationship between the target keyword and the unique identifier of the input parameter in a keyword database after generating corresponding alarm information based on the above model results; and a fifth processing unit for obtaining the corresponding input parameter from the above structure tree model based on the unique identifier of the input parameter when a new abnormal keyword matches the keyword stored in the above keyword database.

[0068] In one specific embodiment of this application, the bank system error diagnosis device includes: a sixth processing unit, which, after generating corresponding alarm information based on the above model results, displays the corresponding operation guide in a visual manner when the alarm information indicates an operational error; and a seventh processing unit, which, when the alarm information indicates a program error, triggers a code review process to query code defects and perform code repair operations.

[0069] In one specific embodiment of this application, the third processing unit includes: a first processing module for sending the model result to a target terminal, wherein the target terminal is a terminal used by the developer; a second processing module for receiving the target error result sent by the target terminal; and a third processing module for generating corresponding alarm information based on the target error result.

[0070] In one specific embodiment of this application, the third processing module includes: a first generation submodule for generating a first alarm message to indicate an operation error when the target error result indicates an operation error; a second generation submodule for generating a second alarm message to indicate a program error when the target error result indicates a program error; and a third generation submodule for generating a third alarm message to indicate both operation and program errors when the target error result indicates both operation and program errors.

[0071] The aforementioned bank system error diagnosis device includes a processor and a memory. The aforementioned building units, first processing unit, second processing unit, and third processing unit are all stored as program units in the memory. The processor executes these program units stored in the memory to achieve the corresponding functions. All of the aforementioned modules reside in the same processor; alternatively, the aforementioned modules may be located in different processors in any combination.

[0072] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured. Adjusting kernel parameters can resolve system anomalies or faults. However, due to the lack of an effective troubleshooting mechanism, it is often difficult to quickly pinpoint the source and service point of the problem.

[0073] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0074] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the aforementioned bank system error diagnosis method.

[0075] This invention provides a processor for running a program, wherein the program executes the aforementioned bank system error diagnosis method during runtime.

[0076] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps: constructing a structure tree model to store parameters of various monitoring points related to the operation of a banking system; receiving system anomaly information and querying the structure tree model based on the system anomaly information to obtain input parameters of monitoring points related to the system anomaly information, including CPU utilization, memory usage, disk I / O, and network latency; inputting the obtained input parameters into a pre-trained neural network model to process the input parameters; obtaining the model results output by the neural network model and generating corresponding alarm information based on the model results to indicate operational errors and / or program errors. The device described herein can be a server, PC, PAD, mobile phone, etc.

[0077] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps: constructing a structure tree model, the structure tree model being used to store parameters of various monitoring points related to the operation of the banking system; receiving system anomaly information and querying the structure tree model based on the system anomaly information to obtain input parameters of the monitoring points related to the system anomaly information, the parameters of the monitoring points including CPU utilization, memory usage, disk I / O, and network latency; inputting the obtained input parameters into a pre-trained neural network model so that the neural network model processes the input parameters; obtaining the model results output by the neural network model and generating corresponding alarm information based on the model results to indicate operational errors, and / or, to indicate program errors.

[0078] This application also provides a bank system error diagnosis system, including: one or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and the one or more programs include methods for performing any of the above-described methods.

[0079] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0080] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0081] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0082] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0083] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0084] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0085] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0086] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0087] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0088] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0089] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A method for diagnosing errors in a banking system, characterized in that, include: Construct a tree structure model, which is used to store parameters of various monitoring points related to the operation of the banking system; Receive system anomaly information and query the structure tree model based on the system anomaly information to obtain the input parameters of the monitoring points related to the system anomaly information. The parameters of the monitoring points include CPU utilization, memory usage, disk I / O and network latency. The acquired input parameters are input into a pre-trained neural network model so that the neural network model processes the input parameters. Obtain the model results output by the neural network model, and generate corresponding alarm information based on the model results to indicate operation errors and / or program errors.

2. The method according to claim 1, characterized in that, The model results include operational error confidence and program error confidence. Corresponding alarm information is generated based on the model results, including: If the confidence level of the operational error is greater than the confidence level of the program error, a first alarm message is generated to indicate the operational error. If the confidence level of the operational error is less than the confidence level of the program error, a second alarm message is generated to indicate a program error. If the confidence level of the operation error is equal to the confidence level of the program error, a third alarm message is generated to indicate the operation error and the program error.

3. The method according to claim 1, characterized in that, The input parameters for the monitoring points related to the system anomaly information are obtained, including: Extract target keywords from the system anomaly information; Based on the target keyword, the monitoring points related to the target keyword are found from the structure tree model, and all relevant parameters of the monitoring points related to the target keyword are obtained, and all the relevant parameters are used as the input parameters.

4. The method according to claim 3, characterized in that, After generating the corresponding alarm information based on the model results, the method further includes: The mapping relationship between the target keywords and the unique identifiers of the input parameters is stored in the keyword database; If a new abnormal keyword matches a keyword stored in the keyword database, the corresponding input parameter is retrieved from the structure tree model based on the unique identifier of the input parameter.

5. The method according to claim 1, characterized in that, After generating the corresponding alarm information based on the model results, the method further includes: When the alarm message indicates an operational error, the corresponding operation guide is displayed in a visual manner; When the alarm message indicates a program error, a code review process is triggered to check for code defects and perform code repair operations.

6. The method according to claim 1, characterized in that, Based on the model results, corresponding alarm information is generated, including: The model results are sent to the target terminal, which is the terminal used by the developers. Receive the target error result sent by the target terminal; Based on the target error result, generate corresponding alarm information.

7. The method according to claim 6, characterized in that, Based on the target error result, generate corresponding alarm information, including: If the target error result indicates an operational error, a first alarm message is generated to indicate the operational error; If the target error result indicates a program error, a second alarm message is generated to indicate the program error. If the target error result indicates an operational error or a program error, a third alarm message is generated to indicate the operational error or program error.

8. A bank system error diagnosis device, characterized in that, include: A building unit is used to build a tree structure model, which stores parameters of various monitoring points related to the operation of the banking system. The first processing unit is used to receive system anomaly information and query the structure tree model according to the system anomaly information to obtain the input parameters of the monitoring points related to the system anomaly information. The parameters of the monitoring points include CPU utilization, memory usage, disk I / O and network latency. The second processing unit is used to input the acquired input parameters into a pre-trained neural network model so that the neural network model processes the input parameters. The third processing unit is used to obtain the model results output by the neural network model and generate corresponding alarm information based on the model results to indicate operation errors and / or program errors.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 7.

10. A bank system error diagnosis system, characterized in that, include: One or more processors, a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising methods for performing any one of claims 1 to 7.

Images