Failure processing method and device of financial system, electronic equipment and storage medium

Abstract

The invention discloses a fault processing method and device of a financial system, electronic equipment and a storage medium, and relates to the technical field of financial science and technology. The method comprises the following steps: in response to an operation instruction of a target financial system, obtaining monitoring data in a monitoring screen, and determining abnormal monitoring data; when it is determined that the target monitoring data is abnormal monitoring data, obtaining at least one piece of target image data matched with the target monitoring data; inputting the target image data into a pre-trained fault classification model of the financial system to obtain a target fault category corresponding to the target monitoring data; wherein the fault classification model of the financial system is used for determining a fault category; determining a target fault solution based on the target fault category; according to the scheme, the problems that a fault positioning method depending on manual analysis and experience judgment is low in efficiency and the accuracy is difficult to guarantee are solved, and the fault of the financial system can be rapidly and accurately determined and processed.

Description

Technical Field

[0001] The present invention relates to the field of financial technology, and in particular to a method, device, electronic device and storage medium for troubleshooting a financial system. Background Art

[0002] With the rapid development of information technology, the scale and complexity of financial software systems are increasing, making fault location and resolution in production environments an extremely challenging task. Traditional fault location methods often rely on manual analysis and empirical judgment, which is inefficient and difficult to guarantee accuracy.

[0003] How to quickly and accurately identify and handle failures in financial systems is a key research issue in the industry. Summary of the Invention

[0004] The present invention provides a method, device, electronic equipment and storage medium for handling faults of a financial system, so as to quickly and accurately determine faults of the financial system and handle the faults.

[0005] According to one aspect of the present invention, a method for handling a fault in a financial system is provided, the method comprising:

[0006] Responding to an operation instruction of the target financial system, acquiring various monitoring data in the monitoring screen and determining abnormal monitoring data;

[0007] When the target monitoring data is determined to be abnormal monitoring data, obtaining at least one target image data matching the target monitoring data;

[0008] Inputting each target image data into a pre-trained fault classification model for a financial system to obtain a target fault category corresponding to the target monitoring data; wherein the fault classification model for the financial system is used to determine the fault category;

[0009] A target fault solution is determined based on the target fault category to resolve the abnormality of the target financial system.

[0010] According to another aspect of the present invention, a fault handling device for a financial system is provided, the device comprising:

[0011] an abnormal monitoring data determination module, configured to obtain various monitoring data in the monitoring screen in response to an operation instruction of the target financial system, and determine abnormal monitoring data;

[0012] an image data acquisition module, configured to acquire at least one target image data matching the target monitoring data when the target monitoring data is determined to be abnormal monitoring data;

[0013] a fault category determination module, configured to input each target image data into a pre-trained fault classification model for a financial system to obtain a target fault category corresponding to the target monitoring data; wherein the fault classification model for the financial system is used to determine the fault category;

[0014] The fault solution determination module is configured to determine a target fault solution based on the target fault category to resolve the abnormality of the target financial system.

[0015] According to another aspect of the present invention, an electronic device is provided, comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the fault handling method for a financial system according to any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the fault handling method of the financial system according to any embodiment of the present invention when executed.

[0020] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the fault handling method of the financial system according to any embodiment of the present invention.

[0021] The technical solution of the embodiment of the present invention obtains each monitoring data in the monitoring screen and determines abnormal monitoring data by responding to the operation instructions of the target financial system; when it is determined that the target monitoring data is abnormal monitoring data, obtains at least one target image data matching the target monitoring data; can quickly monitor abnormal data and obtain image data associated with the abnormal data, which can facilitate subsequent more accurate classification and positioning of faults compared to directly obtaining text data; each target image data is input into a pre-trained fault classification model of the financial system to obtain a target fault category corresponding to the target monitoring data; wherein the fault classification model of the financial system is used to determine the fault category; based on the target fault category, a target fault solution is determined to resolve the abnormality of the target financial system, which solves the problem that the fault positioning method relying on manual analysis and experience judgment is low in efficiency and difficult to ensure accuracy, and can quickly and accurately determine and process the faults of the financial system.

[0022] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present invention, nor is it intended to limit the scope of the present invention. Other features of the present invention will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 This is a flowchart of a method for troubleshooting a financial system according to a first embodiment of the present invention;

[0025] Figure 2 This is a flowchart of a method for troubleshooting a financial system according to a second embodiment of the present invention;

[0026] Figure 3 This is a flowchart of another method for troubleshooting a financial system according to a second embodiment of the present invention;

[0027] Figure 4 This is a training flow chart of a fault classification model for a financial system provided in accordance with the second embodiment of the present invention;

[0028] Figure 5 This is a schematic diagram of the structure of a fault handling device for a financial system provided according to a third embodiment of the present invention;

[0029] Figure 6 The figure is a schematic diagram of the structure of an electronic device for implementing the fault handling method of the financial system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] Example 1

[0033] Figure 1 This is a flowchart of a method for troubleshooting a financial system according to a first embodiment of the present invention. This embodiment is applicable to the case of classifying and handling faults in a financial system. The method can be executed by a fault handling device for a financial system. The fault handling device for a financial system can be implemented in the form of hardware and / or software. The fault handling device for a financial system can be configured in electronic devices such as computers, servers, or tablet computers. Figure 1 As shown, the method includes:

[0034] Step 110 : In response to the operating instruction of the target financial system, obtain various monitoring data in the monitoring screen and determine abnormal monitoring data.

[0035] The target financial system may be any system related to financial services, such as a payment processing system, a securities trading system, a customer relationship management system, a wealth management system, or a foreign exchange trading system, and is not limited in this embodiment.

[0036] It should be noted that, in this embodiment, the information of the target financial system is obtained only after authorization by the user, and the method of obtaining the information is reasonable and legal.

[0037] Optionally, in this embodiment, during the operation of the target financial system, various monitoring data displayed on the monitoring screen can be acquired in real time. Examples include performance indicators of the target financial system, such as memory usage, CPU utilization, or network status indicators; environmental parameters, such as temperature, power status, or fan speed; or log data. Furthermore, abnormal monitoring data can be determined from the acquired monitoring data. The abnormal monitoring data can be any monitoring data and is not limited in this embodiment.

[0038] Optionally, in this embodiment, obtaining each monitoring data in the monitoring screen and determining abnormal monitoring data may include: comparing each monitoring data with the standard monitoring data respectively; when it is determined that the comparison result between the target monitoring data and the standard monitoring data is greater than a preset threshold, determining that the target monitoring data is abnormal.

[0039] In an optional implementation of this embodiment, each monitoring data in the monitoring screen can be compared with the standard monitoring data. For example, the performance indicator data can be compared with the standard performance indicator data, and the environmental parameters can be compared with the standard environmental parameters.

[0040] Furthermore, it can be determined whether the comparison result is greater than a preset threshold, where the preset threshold can be any numerical value and is not limited in this embodiment; if it is determined that the comparison result between the target monitoring data and the standard monitoring data is greater than the preset threshold, then it can be determined that the target monitoring data is abnormal.

[0041] In this embodiment, the change curve of each monitoring data can also be displayed in real time on the monitoring screen, and the change curve of each monitoring data can be directly compared with the standard curve. When the deviation degree between the change curve of the target monitoring data and the standard curve is greater than the preset deviation threshold, the target monitoring data can be determined to be abnormal monitoring data.

[0042] Step 120: When it is determined that the target monitoring data is abnormal monitoring data, obtain at least one target image data matching the target monitoring data.

[0043] Optionally, in this embodiment, after determining that abnormal target monitoring data is obtained, each target image data that matches the target monitoring data can be further obtained. In this embodiment, there is no limit on the number of target image data. It can be understood that the more target image data obtained, the more conducive it is to the subsequent determination of the target fault category that matches the target monitoring data.

[0044] Step 130: Input each of the target image data into a pre-trained fault classification model of the financial system to obtain a target fault category corresponding to the target monitoring data.

[0045] The fault classification model of the financial system is used to determine the fault category.

[0046] Optionally, in this embodiment, after obtaining each target image data that matches the target monitoring data, each target image data can be further input into a pre-trained fault classification model of the financial system, and each target image data can be analyzed and processed by the fault classification model of the financial system to determine the fault category corresponding to the target monitoring data.

[0047] Illustratively, in this embodiment, the fault category corresponding to the target monitoring data may be excessive memory usage, long response time, functional failure, or insufficient throughput, etc., which is not limited in this embodiment.

[0048] Step 140: Determine a target fault solution based on the target fault category to resolve the abnormality of the target financial system.

[0049] Optionally, in this embodiment, after determining the target fault category corresponding to the target monitoring data, a target fault solution matching the target monitoring data can be further determined based on the target fault category. Furthermore, the target fault solution can be executed to solve the abnormal problem of the target financial system.

[0050] Optionally, in this embodiment, determining a target fault solution based on the target fault category may include: determining a target fault solution that matches the target fault category in a preset knowledge base, and executing the target fault solution; wherein the preset knowledge base stores a correspondence between different categories of faults and each fault solution.

[0051] In this embodiment, different types of faults and the fault solutions corresponding to each fault may be predetermined and stored in a target database, which is the preset knowledge base involved in this embodiment.

[0052] In an optional implementation of this embodiment, after determining the target fault category corresponding to the target monitoring data, a target fault solution matching the target fault category can be further determined in the preset knowledge base determined above, and the target fault solution can be executed.

[0053] The technical solution of this embodiment obtains various monitoring data in the monitoring screen and determines abnormal monitoring data in response to the operating instructions of the target financial system; when it is determined that the target monitoring data is abnormal monitoring data, obtains at least one target image data matching the target monitoring data; the abnormal data can be quickly monitored and image data associated with the abnormal data can be obtained, which can facilitate more accurate classification and positioning of faults in the subsequent process compared to directly obtaining text data; each target image data is input into a pre-trained fault classification model of the financial system to obtain a target fault category corresponding to the target monitoring data; wherein the fault classification model of the financial system is used to determine the fault category; based on the target fault category, a target fault solution is determined to resolve the abnormality of the target financial system, which solves the problem that the fault positioning method relying on manual analysis and experience judgment is low in efficiency and difficult to ensure accuracy, and can quickly and accurately determine and handle the faults of the financial system.

[0054] Example 2

[0055] Figure 2 This is a flowchart of a method for troubleshooting a financial system according to the second embodiment of the present invention. This embodiment is a further refinement of the above technical solution. The technical solution in this embodiment can be combined with various optional solutions in one or more of the above embodiments. Figure 2 As shown, the method includes:

[0056] Step 210: In response to the operating instruction of the target financial system, obtain the monitoring data in the monitoring screen and determine abnormal monitoring data.

[0057] Step 220: When it is determined that the target monitoring data is abnormal monitoring data, obtain at least one target image data matching the target monitoring data.

[0058] Optionally, in this embodiment, obtaining at least one target image data matching the target monitoring data may include: capturing each target image data matching the target monitoring data through a screenshot tool; or, recording a display area matching the target monitoring data based on a video recording tool, and randomly extracting frames from the recorded video data to obtain each target image data.

[0059] In an optional implementation of this embodiment, when it is determined that the target monitoring data is abnormal monitoring data, each target image data that matches the target monitoring data can be captured by taking a screenshot. For example, the image data of the display area of the target monitoring data can be captured multiple times in succession to obtain each target image data.

[0060] In another optional implementation of this embodiment, when it is determined that the target monitoring data is abnormal monitoring data, the display area matching the target monitoring data can be recorded through a video recording tool. For example, a video data with a duration of 30 seconds can be recorded; further, the video data can be randomly framed, for example, one frame of video frame data is extracted every frame interval, and further, each extracted video frame data is determined as each target image data.

[0061] Step 230: Input each of the target image data into a pre-trained fault classification model of the financial system to obtain a target fault category corresponding to the target monitoring data.

[0062] Optionally, in this embodiment, the fault classification model of the financial system can be determined by the following steps: generating a fault data set matching the target financial system; inputting the fault data set into the target convolutional neural network for iterative training, and obtaining the fault classification model of the financial system when the condition for iteration stopping is met.

[0063] In an optional implementation of this embodiment, generating a fault data set that matches the target financial system may include: determining at least two preset fault scenarios; injecting the preset fault scenarios during the operation of the target financial system, and obtaining target operation data of the target financial system that matches the preset fault scenarios; the target operation data includes at least one of the following: business performance, performance indicators, and resource consumption; obtaining first image data of each target operation data before the preset fault scenario is injected; obtaining second image data of each target operation data after the preset fault scenario is injected; forming the first image data, the second image data, and the target operation data into a training data pair; and determining multiple training data pairs as the fault data set.

[0064] Optionally, in this embodiment, the preset failure scenario may be network latency or high disk IO, etc., which are not limited in this embodiment. Furthermore, the preset failure scenario may be injected into the target financial system during its operation. After the injection is complete, target operating data of the target financial system matching the preset failure scenario is obtained; wherein the target operating data includes at least one of the following: business performance, performance indicators, and resource consumption.

[0065] In this embodiment, a number of fault scenarios can be randomly generated based on chaos engineering, which can ensure that the number of faults involved is large and comprehensive.

[0066] It can be understood that in this embodiment, business performance reflects the continuity and stability of business running on the system. Performance indicators include TPS (Transactions Per Second), response time, transaction success rate, transaction failure rate, transaction timeout rate, etc., which are used to reflect the level of system service capabilities. Resource consumption indicators include CPU utilization, memory utilization, disk IO, network or connection pool occupancy, etc., which reflect the level of resource consumption of system operation.

[0067] Furthermore, first image data of each target operating data before the preset fault scenario is injected can be obtained, and second image data of each target operating data after the preset fault scenario is injected can be obtained; exemplarily, the first image can be TPS data before the fault injection, and the second image can be TPS data after the fault injection.

[0068] Furthermore, the first image data, the second image data and the target operation data (such as the TPS data in the above example) can be combined into a training data pair; further, multiple training data pairs can be combined to obtain the fault data set in this embodiment, that is, the training data of the fault classification model of the financial system.

[0069] Furthermore, the fault data set can be input into the target convolutional neural network (for example, any convolutional neural network or large model with classification function) for iterative training. When the iteration stopping condition is met, the fault classification model of the financial system is output.

[0070] The iteration stopping condition may be an accuracy condition or an iteration number condition, which is not limited in this embodiment.

[0071] Optionally, in this embodiment, inputting the fault data set into the target convolutional neural network for iterative training may include: inputting each of the training data pairs into the target convolutional neural network respectively, and processing the training data pairs based on the convolution layer, pooling layer, and fully connected layer of the target convolutional neural network.

[0072] Step 240: Determine a target fault solution that matches the target fault category in a preset knowledge base, and execute the target fault solution.

[0073] The solution of this embodiment can generate a fault dataset that matches the target financial system; input the fault dataset into the target convolutional neural network for iterative training, and obtain a fault classification model for the financial system when the iteration stop condition is met. This can quickly determine a machine learning model for classifying faults in the financial system, providing a basis for quickly and accurately determining the fault category of the financial system.

[0074] In order to better understand the fault handling method of the financial system involved in this embodiment, Figure 3 This is a flowchart of another method for troubleshooting a financial system according to the second embodiment of the present invention. Figure 3 , which may include:

[0075] In this embodiment, when conducting chaos engineering experiments, a series of failure scenarios can be designed, such as network latency and high disk I / O. In each failure scenario, system operational data is recorded, including business performance, performance indicators, and resource consumption. Business performance reflects the continuity and stability of business operations on the system. Performance indicators include TPS, response time, transaction success rate, transaction failure rate, and transaction timeout rate, which reflect the system's service capabilities. Resource consumption indicators include CPU utilization, memory utilization, disk I / O, network, connection pool occupancy, and JVM utilization, which reflect the level of resource consumption during system operation.

[0076] During the chaos engineering experiment, various data from the fault injection process are collected in real time. For example, 480,000 target images can be obtained. Furthermore, the obtained target images can be preprocessed by data cleaning, normalization, grayscale conversion, etc. Finally, a training dataset with 40,000 images for each fault scenario, 2,000 images for each type of system operating parameter, and a grayscale image size of 128×64 is obtained.

[0077] Furthermore, the training data set obtained above can be input into a convolutional neural network for iterative training, thereby obtaining a final trained fault classification model for the financial system; Figure 4 This is a training flow chart of a fault classification model for a financial system according to the second embodiment of the present invention, wherein:

[0078] Input layer: used to receive image data. In this embodiment, the size of the input image is normalized to 128×64. Each image is used as a channel, and there are 20 channels in total. Therefore, the size of the input layer is 128×64×20.

[0079] Convolutional layer, used to extract features from the image through convolution operations.

[0080] The pooling layer is used to downsample the feature map obtained by the convolutional layer to reduce the dimension of the feature map.

[0081] The fully connected layer maps the feature vectors to the probabilities of each class. For example, in this embodiment, the fully connected layer can have 128 neurons, each of which is fully connected to all neurons in the previous layer. This layer can integrate the local features from the convolutional and pooling layers and flatten them into a one-dimensional vector, which serves as the input to the next fully connected layer.

[0082] The output layer is used to output the final classification result. Exemplarily, in this embodiment, the output layer has 12 neurons, and the number of neurons is the number of fault types.

[0083] It can be understood that the error function is the loss function. In this embodiment, the loss function can be a cross entropy loss function or a hinge loss function, which is not limited in this embodiment.

[0084] At the same time, it should also be noted that, in this embodiment, the training process of the fault classification model of the financial system can be divided into a forward propagation stage and a backward propagation stage, wherein, in the forward propagation stage, convolution feature extraction, pooling, and error calculation can be performed. First, the sample data set is divided into a training set and a test set, and then the training parameters of the convolutional neural network are set, including the number of convolutional layers, pooling layers, and fully connected layers, the size and step size of the convolution kernel, the pooling area range and pooling standard, and the number of neurons in the fully connected layer. Furthermore, the training sample data can be input into the convolutional neural network, and feature extraction and calculation are performed through the convolutional layer and the pooling layer, and fault classification is performed through the fully connected layer to obtain the actual output value of the network under the current parameters.

[0085] During the backpropagation phase, error feedback and weight updates are performed. The cross-entropy loss function is used to calculate the difference between the ideal predicted value and the actual output value at each layer, i.e., the loss value. This loss value is then propagated to each layer, and the parameters are fine-tuned layer by layer in reverse until the desired effect is achieved within the expected number of iterations. During this process, the gradients of all loss functions are calculated and used to update the weights to minimize the loss function.

[0086] The solution in this embodiment combines the fault simulation capabilities of chaos engineering with the feature extraction capabilities of convolutional neural networks to achieve efficient, accurate, and intelligent localization of production faults. Chaos engineering techniques simulate the uncertainties inherent in production environments, collecting rich and authentic fault data. The feature extraction and classification capabilities of convolutional neural networks accurately identify fault types.

[0087] Example 3

[0088] Figure 5 FIG. 1 is a schematic diagram of a fault handling device for a financial system according to a third embodiment of the present invention. Figure 5 As shown, the apparatus includes: an abnormal monitoring data determination module 510 , an image data acquisition module 520 , a fault category determination module 530 , and a fault solution determination module 540 .

[0089] The abnormal monitoring data determination module 510 is used to obtain various monitoring data in the monitoring screen in response to the operation instruction of the target financial system and determine abnormal monitoring data;

[0090] The image data acquisition module 520 is configured to acquire at least one target image data matching the target monitoring data when the target monitoring data is determined to be abnormal monitoring data;

[0091] a fault category determination module 530 for inputting each target image data into a pre-trained fault classification model for a financial system to obtain a target fault category corresponding to the target monitoring data; wherein the fault classification model for the financial system is used to determine the fault category;

[0092] The fault solution determination module 540 is configured to determine a target fault solution based on the target fault category to resolve the abnormality of the target financial system.

[0093] The solution of this embodiment is to obtain various monitoring data in the monitoring screen and determine abnormal monitoring data in response to the operating instructions of the target financial system through the abnormal monitoring data determination module; obtain at least one target image data matching the target monitoring data when the target monitoring data is determined to be abnormal monitoring data through the image data acquisition module; input each target image data into a pre-trained fault classification model of the financial system through the fault category determination module to obtain a target fault category corresponding to the target monitoring data; wherein the fault classification model of the financial system is used to determine the fault category; and determine a target fault solution based on the target fault category to resolve the abnormality of the target financial system through the fault solution determination module. This solves the problem that the fault location method that relies on manual analysis and empirical judgment is inefficient and difficult to ensure accuracy, and can quickly and accurately determine and handle financial system faults.

[0094] In an optional implementation of this embodiment, the fault handling apparatus of the financial system further includes a fault classification model training module of the financial system, configured to:

[0095] generating a fault data set matching the target financial system;

[0096] The fault data set is input into a target convolutional neural network for iterative training, and a fault classification model of the financial system is obtained when a condition for iteration stopping is met.

[0097] In an optional implementation of this embodiment, the fault classification model training module of the financial system is further configured to:

[0098] Identify at least two pre-defined failure scenarios;

[0099] During the operation of the target financial system, injecting the preset fault scenario and obtaining target operating data of the target financial system that matches the preset fault scenario; the target operating data includes at least one of the following: business performance, performance indicators, and resource consumption;

[0100] Acquire first image data of each target operation data before a preset fault scenario is injected;

[0101] Acquire second image data of each target operation data after a preset fault scenario is injected;

[0102] Combining the first image data, the second image data, and the target operation data into a training data pair;

[0103] A plurality of training data pairs are determined as the fault data sets.

[0104] In an optional implementation of this embodiment, the fault classification model training module of the financial system is further specifically configured to:

[0105] Each of the training data pairs is input into the target convolutional neural network respectively, and the training data pairs are processed based on the convolution layer, pooling layer, and fully connected layer of the target convolutional neural network.

[0106] In an optional implementation of this embodiment, the abnormal monitoring data determining module 510 is specifically configured to:

[0107] respectively comparing each of the monitoring data with the standard monitoring data;

[0108] When it is determined that the comparison result between the target monitoring data and the standard monitoring data is greater than a preset threshold, it is determined that the target monitoring data is abnormal.

[0109] In an optional implementation of this embodiment, the image data acquisition module 520 is specifically configured to:

[0110] intercepting the target image data matching the target monitoring data by using a screenshot tool;

[0111] or,

[0112] Based on a video recording tool, a video of a display area matching the target monitoring data is recorded, and frames of the recorded video data are randomly extracted to obtain each target image data.

[0113] In an optional implementation of this embodiment, the fault solution determination module 540 is specifically configured to

[0114] Determining a target fault solution matching the target fault category in a preset knowledge base, and executing the target fault solution;

[0115] The preset knowledge base stores corresponding relationships between different types of faults and solutions to the faults.

[0116] The fault handling device for a financial system provided by an embodiment of the present invention can execute the fault handling method for a financial system provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0117] In the technical solutions of the embodiments of the present invention, the collection, storage, use, processing, transmission, provision and disclosure of financial system information (such as monitoring data, etc.) are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0118] Example 4

[0119] Figure 6 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0120] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0121] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0122] The processor 11 can be various general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a fault handling method for a financial system, which includes: responding to an operating instruction of a target financial system, obtaining various monitoring data in a monitoring screen, and determining abnormal monitoring data; when it is determined that the target monitoring data is abnormal monitoring data, obtaining at least one target image data that matches the target monitoring data; inputting each target image data into a pre-trained fault classification model for the financial system to obtain a target fault category corresponding to the target monitoring data; wherein the fault classification model for the financial system is used to determine the fault category; and determining a target fault solution based on the target fault category to resolve the abnormality of the target financial system.

[0123] In some embodiments, the fault handling method for a financial system can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the fault handling method for a financial system described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to execute the fault handling method for a financial system via any other suitable means (e.g., via firmware).

[0124] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0125] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0126] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0127] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0128] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0129] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0130] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in the present invention can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved. This is not limited herein.

[0131] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

[0132] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the database detection method provided in any embodiment of the present application.

[0133] The computer program product may be implemented by writing computer program code for performing the operations of the present invention in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0134] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned. They should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0135] Note that the above are only preferred embodiments of the present invention and the technical principles employed. Those skilled in the art will appreciate that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments, and substitutions are possible for those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments and may include many other equivalent embodiments without departing from the scope of the present invention. The scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for handling a financial system fault, characterized in that: include: Responding to an operation instruction of the target financial system, acquiring various monitoring data in the monitoring screen and determining abnormal monitoring data; When the target monitoring data is determined to be abnormal monitoring data, obtaining at least one target image data matching the target monitoring data; Inputting each target image data into a pre-trained fault classification model for a financial system to obtain a target fault category corresponding to the target monitoring data; wherein the fault classification model for the financial system is used to determine the fault category; A target fault solution is determined based on the target fault category to resolve the abnormality of the target financial system.

2. The method for troubleshooting a financial system according to claim 1, characterized in that: The fault classification model of the financial system is determined by the following steps: generating a fault data set matching the target financial system; The fault data set is input into a target convolutional neural network for iterative training, and a fault classification model of the financial system is obtained when a condition for iteration stopping is met.

3. The method for troubleshooting a financial system according to claim 2, characterized in that: The generating of a fault data set matching the target financial system includes: Identify at least two pre-defined failure scenarios; During the operation of the target financial system, injecting the preset fault scenario and obtaining target operating data of the target financial system that matches the preset fault scenario; the target operating data includes at least one of the following: business performance, performance indicators, and resource consumption; Acquire first image data of each target operation data before a preset fault scenario is injected; Acquire second image data of each target operation data after a preset fault scenario is injected; Combining the first image data, the second image data, and the target operation data into a training data pair; A plurality of training data pairs are determined as the fault data sets.

4. The method for troubleshooting a financial system according to claim 3, characterized in that: Inputting the fault data set into a target convolutional neural network for iterative training includes: Each of the training data pairs is input into the target convolutional neural network respectively, and the training data pairs are processed based on the convolution layer, pooling layer, and fully connected layer of the target convolutional neural network.

5. The method for troubleshooting a financial system according to claim 1, characterized in that: The step of obtaining each monitoring data in the monitoring screen and determining abnormal monitoring data includes: respectively comparing each of the monitoring data with the standard monitoring data; When it is determined that the comparison result between the target monitoring data and the standard monitoring data is greater than a preset threshold, it is determined that the target monitoring data is abnormal.

6. The method for troubleshooting a financial system according to claim 1, characterized in that: The acquiring of at least one target image data matching the target monitoring data comprises: intercepting the target image data matching the target monitoring data by using a screenshot tool; or, Based on a video recording tool, a video of a display area matching the target monitoring data is recorded, and frames of the recorded video data are randomly extracted to obtain each target image data.

7. The method for troubleshooting a financial system according to claim 1, characterized in that: The determining a target fault solution based on the target fault category includes: Determining a target fault solution matching the target fault category in a preset knowledge base, and executing the target fault solution; The preset knowledge base stores corresponding relationships between different types of faults and solutions to the faults.

8. A fault handling device for a financial system, characterized in that: include: an abnormal monitoring data determination module, configured to obtain various monitoring data in the monitoring screen in response to an operation instruction of the target financial system, and determine abnormal monitoring data; an image data acquisition module, configured to acquire at least one target image data matching the target monitoring data when the target monitoring data is determined to be abnormal monitoring data; a fault category determination module, configured to input each target image data into a pre-trained fault classification model for a financial system to obtain a target fault category corresponding to the target monitoring data; wherein the fault classification model for the financial system is used to determine the fault category; The fault solution determination module is configured to determine a target fault solution based on the target fault category to resolve the abnormality of the target financial system.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor so that the at least one processor can execute the fault handling method for a financial system according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the fault handling method for a financial system according to any one of claims 1 to 7 when executed.

Images