System operation and maintenance method and device, computer equipment, storage medium and program product

Abstract

The invention relates to a system operation and maintenance method and device, computer equipment, a storage medium and a program product. Comprising the steps of obtaining target fault description information in target log information of a target system; inputting the target fault description information into a target fault analysis network to obtain a target fault link and a target fault type; inputting the target fault type and the target fault link into a target fault processing network to obtain a target fault position and a target fault modification mode; and processing the target fault position by adopting the target fault modification mode. According to the scheme, the target fault description information is input into the target fault analysis network, so that the target fault link and the target fault type can be quickly predicted; and the target fault link and the target fault type are input into the target fault processing network, so that the target fault position and the target fault modification mode can be quickly predicted, the fault positioning and fault processing efficiency is improved, and the system operation and maintenance efficiency is further improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a system operation and maintenance method, apparatus, computer equipment, storage medium and program product. Background Art

[0002] With the development of technology, the functions of software systems are becoming more and more complex, which also makes the operation and maintenance of software systems more and more difficult.

[0003] In traditional technology, the operation and maintenance personnel usually obtain the stored log and other document information, and analyze the log according to the existing operation and maintenance guidance data to determine the cause of the software system failure, which leads to the problem of low system operation and maintenance efficiency. Summary of the invention

[0004] Based on this, it is necessary to provide a system operation and maintenance method, device, computer equipment, storage medium and program product to improve the system operation and maintenance efficiency in response to the above technical problems.

[0005] In a first aspect, the present application provides a system operation and maintenance method, the method comprising:

[0006] Obtain target fault description information from target log information of the target system;

[0007] Inputting the target fault description information into a target fault analysis network to obtain a target fault link and a target fault type; wherein the target fault link includes a target function module in the target system associated with the target fault description information;

[0008] Inputting the target fault type and the target fault link into a target fault processing network to obtain a target fault location and a target fault modification method;

[0009] The target fault location is processed using the target fault modification method.

[0010] In one of the embodiments, the target fault analysis network is trained in the following manner:

[0011] Acquire first sample data; wherein the first sample data includes sample fault description information in the sample log information of the target system, and a sample fault link and a sample fault type corresponding to the sample fault description information;

[0012] The sample fault description information is used as training data, and the sample fault links and sample fault types corresponding to the sample fault description information are used as label data to train the initial fault analysis network to obtain a target fault analysis network.

[0013] In one of the embodiments, the sample fault description information includes at least an execution action and a fault code;

[0014] The obtaining of first sample data includes:

[0015] Obtaining sample fault description information and source code from sample log information of the target system;

[0016] Filtering out target code corresponding to the execution action in the sample fault description information from the source code of the target system;

[0017] determining a candidate faulty link based on the target code;

[0018] Filtering out sample fault links from the candidate fault links according to the fault codes in the sample fault description information;

[0019] Outputting the sample fault link to a marking party, so that the marking party marks the sample fault type based on the sample fault link;

[0020] Get the sample fault type returned by the marking party.

[0021] In one embodiment, determining a candidate faulty link based on the target code comprises:

[0022] In the case where there is a function module including the target code in the module library corresponding to the source code of the target system, taking the function module including the target code as a candidate function module associated with the target code;

[0023] In the case that there is no function module containing the target code in the module library corresponding to the source code of the target system, generating a candidate function module associated with the target code according to the target code in accordance with the module generation rule;

[0024] According to the execution order between the candidate functional modules, the candidate fault link corresponding to the target code is determined.

[0025] In one of the embodiments, the target fault processing network is trained in the following manner:

[0026] Acquire second sample data; wherein the second sample data includes a sample fault type, a sample fault link, a sample fault location, and a sample fault correction method;

[0027] The sample fault types and the sample fault links are used as training data, and the sample fault locations and the sample fault correction methods are used as label data to train an initial fault processing network to obtain a target fault processing network.

[0028] In one embodiment, obtaining the second sample data includes:

[0029] Using the sample faulty links and sample fault types in the first sample data as the sample faulty links and sample fault types in the second sample data;

[0030] Recording the modification operations performed by the marking party in the sample fault link; wherein the modification operations include code modification methods and / or device status change operations, as well as code modification locations, and the device status is the status of the device running the target system;

[0031] The code modification position in the modification operation that can eliminate the fault is taken as a sample fault position, and the code modification method corresponding to the sample fault position and / or the device state change operation is taken as a sample fault modification method.

[0032] In a second aspect, the present application further provides a system operation and maintenance device, the device comprising:

[0033] An acquisition module is used to acquire target fault description information in target log information of a target system;

[0034] A fault analysis module, used for inputting the target fault description information into a target fault analysis network to obtain a target fault link and a target fault type; wherein the target fault link includes a target function module in the target system associated with the target fault description information;

[0035] A fault processing module, used for inputting the target fault type and the target fault link into a target fault processing network to obtain a target fault location and a target fault modification method;

[0036] A processing module is used to process the target fault position by adopting the target fault modification method.

[0037] In a third aspect, the present application further provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0038] Obtain target fault description information from target log information of the target system;

[0039] Inputting the target fault description information into a target fault analysis network to obtain a target fault link and a target fault type; wherein the target fault link includes a target function module in the target system associated with the target fault description information;

[0040] Inputting the target fault type and the target fault link into a target fault processing network to obtain a target fault location and a target fault modification method;

[0041] The target fault location is processed using the target fault modification method.

[0042] In a fourth aspect, the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0043] Obtain target fault description information from target log information of the target system;

[0044] Inputting the target fault description information into a target fault analysis network to obtain a target fault link and a target fault type; wherein the target fault link includes a target function module in the target system associated with the target fault description information;

[0045] Inputting the target fault type and the target fault link into a target fault processing network to obtain a target fault location and a target fault modification method;

[0046] The target fault location is processed using the target fault modification method.

[0047] In a fifth aspect, the present application further provides a computer program product, the computer program product comprising a computer program, which implements the following steps when executed by a processor:

[0048] Obtain target fault description information from target log information of the target system;

[0049] Inputting the target fault description information into a target fault analysis network to obtain a target fault link and a target fault type; wherein the target fault link includes a target function module in the target system associated with the target fault description information;

[0050] Inputting the target fault type and the target fault link into a target fault processing network to obtain a target fault location and a target fault modification method;

[0051] The target fault location is processed using the target fault modification method.

[0052] The above-mentioned system operation and maintenance method, device, computer equipment, storage medium and program product obtain the target fault description information in the target log information of the target system; and input the target fault description information into the target fault analysis network to obtain the target fault link and the target fault type; and input the target fault type and the target fault link into the target fault processing network to obtain the target fault location and the target fault modification method; and then use the target fault modification method to process the target fault location. The above-mentioned scheme can quickly predict the target fault link and the target fault type by inputting the target fault description information into the target fault analysis network; and then inputting the target fault link and the target fault type into the target fault processing network to quickly predict the target fault location and the target fault modification method, thereby improving the efficiency of fault location and fault processing, and thus improving the efficiency of system operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 An application environment diagram of a system operation and maintenance method in an embodiment;

[0054] Figure 2 A flowchart of a system operation and maintenance method in one embodiment;

[0055] Figure 3 A schematic diagram of a process of obtaining a target fault analysis network in one embodiment;

[0056] Figure 4 A schematic diagram of a fault function module corresponding to sample fault description information in an embodiment;

[0057] Figure 5 A schematic diagram of a process for obtaining first sample data in an embodiment;

[0058] Figure 6 A schematic diagram of a process of determining a candidate faulty link based on a target code in one embodiment;

[0059] Fig. 7A A schematic diagram of a process of obtaining a target fault processing network in an embodiment;

[0060] Figure 7B A schematic diagram of training an initial fault processing network in one embodiment;

[0061] Fig. 8A A schematic diagram of a process for obtaining second sample data in one embodiment;

[0062] Figure 8B A signaling diagram for training an initial fault handling network in one embodiment;

[0063] Fig. 9 is a structural block diagram of a system operation and maintenance device in an embodiment;

[0064] Fig.10 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0066] The system operation and maintenance method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown in the figure, the operation and maintenance personnel can input the target fault description information in the target log information of the target system into the terminal through the interactive interface; then the terminal obtains the target fault description information and inputs the target fault description information into the target fault analysis network, and the target fault analysis network outputs the target fault link and target fault type based on the source code and log information of the target system learned historically; then the target fault link and target fault type are input into the target fault processing network to obtain the target fault location and target fault modification method, so that the terminal can process the target fault location based on the target fault modification method to eliminate the fault.

[0067] The method can be executed by a terminal, wherein the terminal can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices, and the Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart car devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc.

[0068] In one embodiment, Figure 2 As shown, a system operation and maintenance method is provided, which is applied to Figure 1 The terminal in is used as an example to illustrate, including the following steps:

[0069] S201, obtaining target fault description information in target log information of a target system.

[0070] Exemplarily, the target system is a system with preset functions. The target log information is the log generated by the target system during the operation and maintenance process; the target fault description information can be understood as the error information in the target log information, wherein the target fault description information may include the operation performed incorrectly, the returned error code and error return information, and the expected correct return. For example, the target fault description information is "calling the interface delete_nat to delete the NAT gateway with ID xx, failing to return the error message of instance error, and expecting to return the success message of delete nat success".

[0071] The target fault description information in the target log information of the target system may be obtained according to the identifier of the target system and the identifier of the log information.

[0072] S202: Input the target fault description information into the target fault analysis network to obtain the target fault link and the target fault type.

[0073] Exemplarily, the target fault analysis network is used to predict the target fault link and the target fault type based on the target fault description information; wherein the target fault link includes a target functional module in the target system associated with the target fault description information. Thus, the target fault description information is input into the target fault analysis network, and the target fault link and the target fault type can be obtained. The target fault analysis network can be a Generative Pre-trained Transformer (GPT) model.

[0074] S203: Input the target fault type and the target fault link into the target fault processing network to obtain the target fault location and the target fault modification method.

[0075] Furthermore, the target fault processing network is used to predict the target fault location and target fault modification method based on the target fault type and target fault link. Therefore, the target fault type and target fault link are input into the target fault processing network, and the target fault location and target fault modification method can be obtained. Among them, the target fault location can be the specific functional module where the abnormality occurs, and the abnormal code line in the module; the target fault modification method can be the modified code corresponding to the target fault location, or the operation performed on the device running the target system, such as restarting the device and other operations. Among them, the target fault processing network can also be a GPT model.

[0076] S204: Process the target fault location using a target fault modification method.

[0077] Furthermore, the target fault location may be processed in a target fault modification manner, for example, the code may be modified or a corresponding operation may be performed on the device in accordance with the target fault modification manner to eliminate the fault.

[0078] The above system operation and maintenance method obtains the target fault description information in the target log information of the target system; and inputs the target fault description information into the target fault analysis network to obtain the target fault link and the target fault type; and inputs the target fault type and the target fault link into the target fault processing network to obtain the target fault location and the target fault modification method; and then uses the target fault modification method to process the target fault location. The above scheme can quickly predict the target fault link and the target fault type by inputting the target fault description information into the target fault analysis network; and then inputting the target fault link and the target fault type into the target fault processing network to quickly predict the target fault location and the target fault modification method, thereby improving the efficiency of fault location and fault processing, and thus improving the efficiency of system operation and maintenance.

[0079] In some optional implementations, see Figure 3 , Figure 3 A schematic diagram of a process for obtaining a target fault analysis network is provided, which specifically includes the following steps:

[0080] S301, obtaining first sample data.

[0081] The first sample data includes sample fault description information in the sample log information of the target system, as well as sample fault links and sample fault types corresponding to the sample fault description information. For example, the sample fault description information is "calling the interface delete_nat to delete the NAT gateway with ID xx, and returning the error message of instance error when failing, and expecting to return the success message of delete nat success", and the sample fault link is as follows: Figure 4 As shown, Figure 4 The schematic diagram of the fault function module corresponding to the sample fault description information is shown. The sample fault type is an interface connection fault.

[0082] S302 , using sample fault description information as training data, and using sample fault links and sample fault types corresponding to the sample fault description information as label data, to train an initial fault analysis network to obtain a target fault analysis network.

[0083] Furthermore, the sample fault description information may be used as training data, and the sample fault links and sample fault types corresponding to the sample fault description information may be used as label data to train the initial fault analysis network and obtain the target fault analysis network.

[0084] For example, the sample fault description information can be input into the initial fault analysis network for training, and the predicted predicted fault link and predicted fault type can be output; then the loss between the predicted fault link and the sample fault link is calculated, as well as the loss between the predicted fault type and the sample fault type. Based on the loss between the predicted fault link and the sample fault link and the loss between the predicted fault type and the sample fault type, the model parameters of the initial fault analysis network are adjusted so that the loss between the predicted fault link and the sample fault link and the loss between the predicted fault type and the sample fault type are less than a preset value, or stabilized at a preset value, and the training of the initial fault analysis network is stopped to obtain the target fault analysis network.

[0085] In an embodiment of the present application, sample fault description information is used as training data, and sample fault links and sample fault types corresponding to the sample fault description information are used as label data to train an initial fault analysis network to obtain a target fault analysis network. The target fault analysis network can then be used to quickly predict a target fault link and a target fault type based on the target fault description information, thereby improving the efficiency of fault analysis.

[0086] Furthermore, the sample fault description information in the above embodiment includes at least an execution action and a fault code. For example, the execution action may be "calling interface delete_nat to delete the NAT gateway with ID xx"; the fault code may be "instanceerror". The first sample data may be obtained based on the execution action and the fault code in the sample fault description information.

[0087] Based on this, see Figure 5 , Figure 5 A schematic diagram of a process for obtaining first sample data is provided, which specifically includes the following steps:

[0088] S501, obtaining sample fault description information and source code in sample log information of a target system.

[0089] For example, the operation and maintenance personnel can input the sample fault description information in the sample log information of the target system through the interactive interface of the terminal, and the terminal obtains the sample fault description information and can obtain the source code of the target system according to the identifier of the target system.

[0090] S502: Filter out target codes corresponding to the execution actions in the sample fault description information from the source code of the target system.

[0091] Furthermore, the target code corresponding to the execution action in the sample fault description information can be screened out in the source code of the target system. For example, if the execution action in the sample fault description information is "calling interface delete_nat to delete the NAT gateway with ID xx", the target code containing interface delete_nat can be screened out in the source code of the target system.

[0092] S503: Determine a candidate faulty link based on the target code.

[0093] Furthermore, the functional modules containing the target code may be determined first, and candidate fault links may be generated according to the execution order between the functional modules containing the target code.

[0094] S504: Filter out sample fault links from candidate fault links according to the fault codes in the sample fault description information.

[0095] Furthermore, the running recurrence path of the target code can be simulated, and each line of source code and its path involved in the execution of the erroneous operation can be recorded. When the fault code or error message appears, or the target code ends, the recurrence process is stopped. The specific erroneous code location is marked as a fault, and the functional module containing the fault code is marked as a fault, and a sample fault link is generated based on the execution order of the functional module containing the fault code.

[0096] S505: Output the sample fault links to a marking party, so that the marking party marks the sample fault types based on the sample fault links.

[0097] Furthermore, the sample fault link can be output to the marking party, which is convenient for the marking party to confirm whether the generated sample fault link is correct on the one hand; on the other hand, when the sample fault link is generated correctly, it is convenient for the marking party to mark the sample fault type based on the sample fault link. For example, the marking party can click on each functional module in the sample fault link in turn to view the code under each functional module, determine the cause of the error based on the fault code and execution logic, and mark the error with specific label information, for example, the label information can include the error type and log error keywords, etc. Among them, the marking party can be an operation and maintenance personnel.

[0098] S506: Obtain the sample fault type returned by the marking party.

[0099] Exemplarily, the marking party may mark the sample fault type on the terminal interactive interface, which can be understood as returning the sample fault type to the terminal, so that the terminal obtains the sample fault type returned by the marking party. In this way, the first sample data is obtained.

[0100] In an embodiment of the present application, candidate fault links are obtained based on sample fault description information and the source code of the target system, and then based on the interaction with the marking party, the sample fault type is obtained to obtain the first sample data, thereby facilitating the training of the initial fault analysis network.

[0101] Furthermore, S503 in the above embodiment can be implemented in the following manner.

[0102] For example, see Figure 6 , Figure 6 A flowchart of determining a candidate fault link based on a target code is provided, which specifically includes the following steps:

[0103] S601: When there is a function module containing a target code in a module library corresponding to a source code of a target system, the function module containing the target code is used as a candidate function module associated with the target code.

[0104] Exemplarily, the module library corresponding to the source code of the target system includes functional modules that have divided the code. If there are functional modules containing the target code in the module library corresponding to the source code of the target system, the functional modules containing the target code can be directly used as candidate functional modules associated with the target code, and candidate fault links can be generated based on the execution order between the candidate functional modules.

[0105] S602: When there is no function module containing the target code in the module library corresponding to the source code of the target system, a candidate function module associated with the target code is generated according to the target code in accordance with the module generation rule.

[0106] Exemplarily, the module library corresponding to the source code of the target system may not include the functional modules of the target code. In this case, candidate functional modules associated with the target code may be generated according to the target code in accordance with the module generation rules.

[0107] The module generation rule can be set according to actual needs. For example, the module generation rule can be to logically divide each code segment in the target code into a functional module, and can divide less than 10 functional modules into the same link layer.

[0108] S603: Determine the candidate fault link corresponding to the target code according to the execution order between the candidate functional modules.

[0109] Furthermore, the candidate fault links corresponding to the target code can be determined according to the execution order between the candidate functional modules, wherein the candidate fault links include at least one link layer, and each link layer includes at least one functional module.

[0110] In an embodiment of the present application, when there is a function module containing the target code in the module library corresponding to the source code of the target system, a candidate fault link can be directly generated based on the function module containing the target code; when there is no function module containing the target code in the module library corresponding to the source code of the target system, the candidate function module associated with the target code can be first generated according to the module generation rule according to the target code, and then the candidate fault link corresponding to the target code can be determined according to the execution order between the candidate function modules; in this way, the sample fault link in the first sample data can be obtained, which is convenient for training the initial fault analysis network to obtain the target fault analysis network.

[0111] In some optional implementations, see Fig. 7A , Fig. 7A A flowchart of obtaining a target fault handling network is provided, which specifically includes the following steps:

[0112] S701, obtaining second sample data.

[0113] The second sample data includes a sample fault type, a sample fault link, a sample fault location, and a sample fault correction method;

[0114] For example, a sample fault link can be found at Figure 4 As shown, Figure 4 The marked fault modules and code behavior sample fault locations in the sample fault modification method may include the modified code corresponding to the sample fault location, or operations performed on the device running the target system, such as restarting the device.

[0115] S702 , using sample fault types and sample fault links as training data, and sample fault locations and sample fault correction methods as label data, to train an initial fault processing network to obtain a target fault processing network.

[0116] Furthermore, the initial fault processing network can be trained with sample fault types and sample fault links as training data, and sample fault locations and sample fault correction methods as label data to obtain a target fault processing network.

[0117] For example, see Figure 7B , Figure 7B A schematic diagram for training an initial fault handling network is provided.

[0118] The sample fault type T and the sample fault link L can be input into the initial fault processing network for training, and the predicted predicted fault position D1 and the predicted fault modification method W1 can be output; then the error value between the predicted fault position D1 and the sample fault position D2 is calculated, and the error value between the predicted fault modification method W1 and the sample fault modification method W2 is calculated; based on the error value between the predicted fault position D1 and the sample fault position D2 and the error value between the predicted fault modification method W1 and the sample fault modification method W2, the model parameters of the initial fault processing network are adjusted so that the error value between the predicted fault position D1 and the sample fault position D2 and the error value between the predicted fault modification method W1 and the sample fault modification method W2 are less than the preset value, or stabilized at the preset value, and the initial fault processing network is stopped from being trained to obtain the target fault processing network.

[0119] In an embodiment of the present application, the initial fault processing network is trained using sample fault types and sample fault links as training data, and sample fault locations and sample fault modification methods as label data to obtain a target fault processing network. The target initial fault processing network can then be used to quickly predict the target fault location and target fault modification method based on the target fault type and target fault link, thereby improving the efficiency of fault processing.

[0120] Further, see Fig. 8A , Fig. 8A A schematic diagram of a process for obtaining second sample data is provided, which specifically includes the following steps:

[0121] S801: Use sample faulty links and sample fault types in first sample data as sample faulty links and sample fault types in second sample data.

[0122] Exemplarily, the sample fault links and sample fault models in the first sample data can be used as the sample fault links and sample fault types in the second sample data. The method of determining the sample fault links and sample fault models in the first sample data is as described in the above embodiment and will not be described in detail here.

[0123] S802, recording the modification operation performed by the marking party in the sample fault link.

[0124] Exemplarily, the sample fault link can be displayed to the marking party so that the marking party can perform modification operations in the sample fault link, wherein the modification operations include code modification methods and / or device status change operations, as well as code modification locations, and the device status is the status of the device running the target system.

[0125] Exemplarily, during the process in which the marking party performs a modification operation in the sample faulty link, the modification operation performed by the marking party in the sample faulty link is recorded.

[0126] S803, taking the code modification position in the modification operation that can eliminate the fault as a sample fault position, and taking the code modification method corresponding to the sample fault position and / or the device state change operation as a sample fault modification method.

[0127] Furthermore, after the marking party performs a modification operation in the sample fault link, the terminal can automatically execute the modified code again or perform a device status change operation based on the modification operation performed by the marking party in the sample fault link to verify whether the fault is eliminated. Then, the code modification position in the modification operation that can eliminate the fault is used as the sample fault position, and the code modification method corresponding to the sample fault position and / or the device status change operation are used as the sample fault modification method.

[0128] For example, see Figure 8B , Figure 8B A signaling diagram for training an initial fault processing network is provided. The marking party can input sample fault description information into the interactive interface of the terminal, and the terminal finds the target code containing the interface and the candidate fault link according to the interface involved in the operation performed in the sample fault description information; and obtains sample log information of the target system, annotates the fault function module in the candidate fault link based on the fault code and other information in the sample log information, and generates a sample fault link based on the fault function module.

[0129] The sample fault link is then returned to the marking party so that the marking party can check the solution strategy. For example, the marking party attempts a solution strategy, and the terminal can simulate the fault elimination situation after executing the solution strategy. If the fault is eliminated, the prompt information of the fault elimination is fed back to the marking party, and the solution strategy is used as the sample fault modification method; the marking party marks the fault type based on the solution strategy adopted to eliminate the fault to obtain the sample fault type and sample fault location.

[0130] Furthermore, the initial fault processing network is trained with sample fault types and sample fault links as training data, and sample fault locations and sample fault correction methods as label data to obtain a target fault processing network.

[0131] In an embodiment of the present application, a sample fault link and a sample fault type in the first sample data are used as the sample fault link and the sample fault type in the second sample data; and by recording the modification operation performed by the marking party in the sample fault link, the code modification position in the modification operation that can eliminate the fault is used as the sample fault position, and the code modification method corresponding to the sample fault position, and / or the device status change operation is used as the sample fault modification method, so that the second sample data is obtained, so as to facilitate training of the initial fault processing network based on the second sample data to obtain the target fault processing network.

[0132] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0133] Based on the same inventive concept, the embodiment of the present application also provides a system operation and maintenance device for implementing the system operation and maintenance method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more system operation and maintenance device embodiments provided below can refer to the limitations on the system operation and maintenance method above, and will not be repeated here.

[0134] In one embodiment, Fig. 9 As shown, a system operation and maintenance device is provided, including:

[0135] An acquisition module 10 is used to acquire target fault description information in target log information of a target system;

[0136] The fault analysis module 20 is used to input the target fault description information into the target fault analysis network to obtain the target fault link and the target fault type; wherein the target fault link includes the target function module associated with the target fault description information in the target system;

[0137] The fault processing module 30 is used to input the target fault type and the target fault link into the target fault processing network to obtain the target fault location and the target fault modification method;

[0138] The processing module 40 is used to process the target fault position by adopting a target fault modification method.

[0139] The above-mentioned system operation and maintenance device obtains the target fault description information in the target log information of the target system; and inputs the target fault description information into the target fault analysis network to obtain the target fault link and the target fault type; and inputs the target fault type and the target fault link into the target fault processing network to obtain the target fault location and the target fault modification method; and then uses the target fault modification method to process the target fault location. The above-mentioned scheme can quickly predict the target fault link and the target fault type by inputting the target fault description information into the target fault analysis network; and then inputting the target fault link and the target fault type into the target fault processing network to quickly predict the target fault location and the target fault modification method, thereby improving the efficiency of fault location and fault processing, and thus improving the efficiency of system operation and maintenance.

[0140] In one of the embodiments, the device further comprises a first training module;

[0141] The acquisition module 10 is further used to acquire first sample data; wherein the first sample data includes sample fault description information in the sample log information of the target system, and a sample fault link and a sample fault type corresponding to the sample fault description information;

[0142] The first training module is used to train the initial fault analysis network using sample fault description information as training data and sample fault links and sample fault types corresponding to the sample fault description information as label data to obtain a target fault analysis network.

[0143] In one embodiment, the sample fault description information includes at least an execution action and a fault code; the acquisition module 10 specifically includes:

[0144] A first acquisition unit, used to acquire sample fault description information and source code from sample log information of a target system;

[0145] A first screening unit is used to screen out target codes corresponding to the execution actions in the sample fault description information from the source code of the target system;

[0146] A first determining unit, configured to determine a candidate faulty link based on a target code;

[0147] A second screening unit, configured to screen out a sample fault link from the candidate fault links according to the fault code in the sample fault description information;

[0148] An output unit, configured to output the sample fault link to a marking party, so that the marking party marks the sample fault type based on the sample fault link;

[0149] The second acquisition unit is used to acquire the sample fault type returned by the marking party.

[0150] In one embodiment, the first determining unit is specifically configured to:

[0151] When there is a function module containing the target code in the module library corresponding to the source code of the target system, the function module containing the target code is used as a candidate function module associated with the target code; when there is no function module containing the target code in the module library corresponding to the source code of the target system, a candidate function module associated with the target code is generated according to the target code in accordance with the module generation rule; and a candidate fault link corresponding to the target code is determined according to the execution order between the candidate function modules.

[0152] In one of the embodiments, the device further comprises a second training module;

[0153] The acquisition module 10 is further used to acquire second sample data; wherein the second sample data includes a sample fault type, a sample fault link, a sample fault location and a sample fault modification method;

[0154] The second training module is used to train the initial fault processing network using the sample fault type and the sample fault link as training data and the sample fault location and the sample fault modification method as label data to obtain the target fault processing network.

[0155] In one embodiment, the acquisition module 10 further includes:

[0156] A second determining unit, configured to use the sample faulty link and the sample fault type in the first sample data as the sample faulty link and the sample fault type in the second sample data;

[0157] A recording unit, used to record the modification operation performed by the marking party in the sample fault link; wherein the modification operation includes a code modification position and a code modification method, and / or an operation of changing the state of a device, where the device is a device running the target system;

[0158] The third determining unit is used to use the code modification position in the modification operation that can eliminate the fault as a sample fault position, and use the code modification method corresponding to the sample fault position and / or the device state change operation as a sample fault modification method.

[0159] Each module in the above system operation and maintenance device can be implemented in whole or in part by software, hardware, or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0160] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig.10 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a system operation and maintenance method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0161] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0162] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0163] Obtain target fault description information from target log information of the target system;

[0164] Input the target fault description information into the target fault analysis network to obtain a target fault link and a target fault type; wherein the target fault link includes a target function module in the target system associated with the target fault description information;

[0165] Input the target fault type and the target fault link into the target fault processing network to obtain the target fault location and the target fault modification method;

[0166] The target fault location is processed using a target fault modification method.

[0167] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0168] Acquire first sample data; wherein the first sample data includes sample fault description information in sample log information of the target system, and sample fault links and sample fault types corresponding to the sample fault description information; use the sample fault description information as training data, and use the sample fault links and sample fault types corresponding to the sample fault description information as label data to train an initial fault analysis network to obtain a target fault analysis network.

[0169] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0170] Obtain sample fault description information and source code from sample log information of the target system; filter out target code corresponding to the execution action in the sample fault description information from the source code of the target system; determine candidate fault links based on the target code; filter out sample fault links from candidate fault links according to the fault code in the sample fault description information; output the sample fault links to the marking party so that the marking party marks the sample fault type based on the sample fault links; and obtain the sample fault type returned by the marking party.

[0171] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0172] When there is a function module containing the target code in the module library corresponding to the source code of the target system, the function module containing the target code is used as a candidate function module associated with the target code; when there is no function module containing the target code in the module library corresponding to the source code of the target system, a candidate function module associated with the target code is generated according to the target code in accordance with the module generation rule; and a candidate fault link corresponding to the target code is determined according to the execution order between the candidate function modules.

[0173] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0174] Obtain second sample data; wherein the second sample data includes a sample fault type, a sample fault link, a sample fault location, and a sample fault modification method; use the sample fault type and the sample fault link as training data, and use the sample fault location and the sample fault modification method as label data to train the initial fault processing network to obtain a target fault processing network.

[0175] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0176] The sample fault link and the sample fault type in the first sample data are used as the sample fault link and the sample fault type in the second sample data; the modification operation performed by the marking party in the sample fault link is recorded; wherein the modification operation includes the code modification method and / or the device status change operation, and the code modification position, and the device status is the state of the device running the target system; the code modification position in the modification operation that can eliminate the fault is used as the sample fault position, and the code modification method corresponding to the sample fault position, and / or the device status change operation are used as the sample fault modification method.

[0177] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the system operation and maintenance method described in any of the above embodiments are implemented.

[0178] In one embodiment, a computer program product is provided, including a computer program, which, when executed by a processor, implements the steps of the system operation and maintenance method described in any of the above embodiments.

[0179] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0180] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0181] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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.

[0182] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A system operation and maintenance method, characterized in that: The method comprises: Obtain target fault description information from target log information of the target system; Inputting the target fault description information into a target fault analysis network to obtain a target fault link and a target fault type; wherein the target fault link includes a target function module in the target system associated with the target fault description information; Inputting the target fault type and the target fault link into a target fault processing network to obtain a target fault location and a target fault modification method; The target fault location is processed using the target fault modification method.

2. The method according to claim 1, characterized in that: The target fault analysis network is trained in the following way; Acquire first sample data; wherein the first sample data includes sample fault description information in the sample log information of the target system, and a sample fault link and a sample fault type corresponding to the sample fault description information; The sample fault description information is used as training data, and the sample fault links and sample fault types corresponding to the sample fault description information are used as label data to train the initial fault analysis network to obtain a target fault analysis network.

3. The method according to claim 2, characterized in that The sample fault description information at least includes an execution action and a fault code; The obtaining of first sample data includes: Obtaining sample fault description information and source code from sample log information of the target system; Filtering out target codes corresponding to the execution actions in the sample fault description information from the source code of the target system; determining a candidate faulty link based on the target code; Filtering out sample fault links from the candidate fault links according to the fault codes in the sample fault description information; Outputting the sample fault link to a marking party, so that the marking party marks the sample fault type based on the sample fault link; Get the sample fault type returned by the marking party.

4. The method according to claim 3, characterized in that The determining of a candidate faulty link based on the target code comprises: In the case where there is a function module including the target code in the module library corresponding to the source code of the target system, taking the function module including the target code as a candidate function module associated with the target code; In the case that there is no function module containing the target code in the module library corresponding to the source code of the target system, generating a candidate function module associated with the target code according to a module generation rule; According to the execution order between the candidate functional modules, the candidate fault link corresponding to the target code is determined.

5. The method according to claim 3, characterized in that: The target fault processing network is trained in the following way; Acquire second sample data; wherein the second sample data includes a sample fault type, a sample fault link, a sample fault location, and a sample fault correction method; The sample fault types and the sample fault links are used as training data, and the sample fault locations and the sample fault correction methods are used as label data to train an initial fault processing network to obtain a target fault processing network.

6. The method according to claim 5, characterized in that The obtaining of the second sample data comprises: Using the sample faulty link and the sample faulty type in the first sample data as the sample faulty link and the sample faulty type in the second sample data; Recording the modification operations performed by the marking party in the sample fault link; wherein the modification operations include code modification methods and / or device status change operations, as well as code modification locations, and the device status is the status of the device running the target system; The code modification position in the modification operation that can eliminate the fault is taken as a sample fault position, and the code modification method and / or the device state change operation corresponding to the sample fault position is taken as a sample fault modification method.

7. A system operation and maintenance device, characterized in that: The device comprises: An acquisition module is used to acquire target fault description information in target log information of a target system; A fault analysis module, used for inputting the target fault description information into a target fault analysis network to obtain a target fault link and a target fault type; wherein the target fault link includes a target function module in a target system associated with the target fault description information; A fault processing module, used for inputting the target fault type and the target fault link into a target fault processing network to obtain a target fault location and a target fault modification method; A processing module is used to process the target fault position by adopting the target fault modification method.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images