CN115686895A - Database abnormality diagnosis method, apparatus, device, medium, and program product - Google Patents
Database abnormality diagnosis method, apparatus, device, medium, and program product Download PDFInfo
- Publication number
- CN115686895A CN115686895A CN202210844183.XA CN202210844183A CN115686895A CN 115686895 A CN115686895 A CN 115686895A CN 202210844183 A CN202210844183 A CN 202210844183A CN 115686895 A CN115686895 A CN 115686895A
- Authority
- CN
- China
- Prior art keywords
- database
- target
- neural network
- network model
- repair
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Debugging And Monitoring (AREA)
Abstract
The disclosure provides a database abnormity diagnosis method, and relates to the technical field of artificial intelligence. The database abnormality diagnosis method comprises the following steps: acquiring an error log of a target database and a real-time operation index of the target database; determining the abnormal description and the abnormal grade of the target database by utilizing a neural network model according to the error log and the operation index; determining a target repair strategy according to the abnormal description, the abnormal level and the state of the neural network model, wherein the neural network model comprises a plurality of states, and the neural network model is switched among the plurality of states according to the credibility of the neural network model; and repairing the abnormity of the target database according to the target repairing strategy. The present disclosure also provides a database abnormality diagnosis apparatus, device, medium, and program product.
Description
Technical Field
The present disclosure relates to the field of artificial intelligence technologies, and in particular, to a database anomaly diagnosis method, apparatus, electronic device, storage medium, and program product.
Background
With the development of a banking business system, the data volume is suddenly increased, and in order to ensure that online business can stably run, a plurality of sets of test environments need to be deployed to meet various test requirements, so that the number of databases in the test environments is exponentially expanded.
Generally, when the operation of the database is abnormal, operation and maintenance personnel of the senior database can inquire the operation state of the database by reading operation and maintenance logs of the database and the like, and then solve the abnormality of the database by means of operation and maintenance experience.
However, as the number of databases increases, the frequency of database anomalies increases greatly compared to the past, and solving the database anomalies by the above method is difficult to meet the actual requirements.
Disclosure of Invention
In view of the above, the present disclosure provides a database abnormality diagnosis method, apparatus, electronic device, storage medium, and program product.
According to a first aspect of the present disclosure, there is provided a database abnormality diagnosis method, including:
acquiring an error report log of a target database and a real-time operation index of the target database;
determining the abnormal description and the abnormal grade of the target database by utilizing a neural network model according to the error log and the operation index;
determining a target repair strategy according to the abnormality description, the abnormality level and the state of the neural network model, wherein the neural network model comprises a plurality of states, and the neural network model switches among the plurality of states according to the credibility of the neural network model;
and repairing the abnormity of the target database according to the target repairing strategy.
According to an embodiment of the present disclosure, the determining, by using the neural network model, the abnormality of the target database and the abnormality level of the abnormality according to the error log and the operation index includes:
performing first formatting processing on the error report log to obtain first feature vector data;
performing second formatting processing on the operation index to obtain second feature vector data;
performing the following steps using the long-short term memory neural network model:
according to the first feature vector data and the second feature vector data, determining the abnormality of the target database and the reason for generating the abnormality so as to obtain the abnormality description;
and determining the abnormality grade according to the abnormality and the reason for generating the abnormality.
According to an embodiment of the present disclosure, the plurality of states of the neural network model includes a first state and a second state;
when the neural network model is in the first state, determining a target repair strategy according to the anomaly description, the anomaly level and the state of the neural network model, including:
sending the abnormal description, the abnormal grade, the error log and the operation index to an auditor;
determining the target repair strategy according to the feedback of the auditor; and (c) a second step of,
correcting the neural network model according to the feedback of the auditor;
when the neural network model is in the second state, determining a target repair strategy according to the anomaly description, the anomaly level and the state of the neural network model, including:
and acquiring a repair strategy matched with the exception description and the exception grade to obtain the target repair strategy.
According to an embodiment of the present disclosure, repairing the abnormality of the target database according to the target repair policy includes:
generating a repair instruction matched with the target repair strategy according to the target repair strategy, and storing the repair instruction into a repair queue;
sending at least part of repair instructions in the repair queue to a server matched with the repair instruction according to a preset period, wherein the repair instruction is configured to enable the server matched with the repair instruction to repair the target database;
when a plurality of repair instructions are stored in the repair queue, the repair instructions are sorted according to the exception grade matched with each repair instruction.
According to an embodiment of the present disclosure, after repairing the abnormality of the target database, the database abnormality diagnosis method further includes:
querying a first target user matched with the target database;
generating early warning information according to the error log, the operation index, the abnormal description, the abnormal grade and the target repairing strategy;
sending the early warning information to the first target user, wherein the early warning information is configured to: and displaying according to a display mode matched with the abnormal grade.
According to an embodiment of the present disclosure, after repairing the abnormality of the target database, the database abnormality diagnosis method further includes:
sending the early warning information to a second target user;
and correcting the neural network model according to the feedback of the second target user, and updating the reliability of the neural network model.
According to an embodiment of the present disclosure, the operation index includes: semi-synchronous parameter information, database basic configuration information, database hardware information, database software information, transaction call amount and response time.
A second aspect of the present disclosure provides a database abnormality diagnosis apparatus, including:
the acquisition module is used for acquiring an error report log of a target database and a real-time operation index of the target database;
the first processing module is used for determining the abnormal description and the abnormal grade of the target database by utilizing a neural network model according to the error log and the operation index;
the second processing module is used for determining a target repair strategy according to the abnormality description and the abnormality grade, wherein the neural network model comprises a plurality of states, and the neural network model is switched among the plurality of states according to the credibility of the neural network model;
and the repairing module is used for repairing the abnormity of the target database according to the target repairing strategy.
A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the database anomaly diagnostic method described above.
The fourth aspect of the present disclosure also provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the above-described database anomaly diagnosis method.
The fifth aspect of the present disclosure also provides a computer program product comprising a computer program that, when executed by a processor, implements the database abnormality diagnosis method described above.
One or more of the above-described embodiments may provide the following advantages or benefits:
by adopting the database abnormity diagnosis method of the embodiment of the disclosure, automatic diagnosis and repair can be carried out on the target database, and in the process, higher degree of automation is realized, the dependence on manpower is reduced, and the abnormity repair efficiency is improved. More importantly, in the embodiment of the disclosure, the error log and the operation index are combined, and the neural network model is used for performing anomaly diagnosis (that is, determining the description and the level of the anomaly), so that which kind of anomaly occurs in the target database can be determined, and the cause of the anomaly and the emergency degree of the anomaly can be analyzed, so that the diagnosis result has finer granularity. On the basis, the target repairing strategy can be determined according to the abnormal description, the abnormal level and the state of the neural network model, the target repairing strategy can be generated according to an accurate and careful diagnosis result all the time, and the repairing priority can be configured according to the emergency degree, so that automatic repairing based on the target repairing strategy is accurate and reliable, and the target database is guaranteed to run stably.
Drawings
The foregoing and other objects, features and advantages of the disclosure will be apparent from the following description of embodiments of the disclosure, which proceeds with reference to the accompanying drawings, in which:
fig. 1 schematically illustrates an application scenario diagram of a database anomaly diagnosis method, apparatus, electronic device, storage medium and program product according to an embodiment of the present disclosure;
FIG. 2 schematically shows one of the flow charts of a database anomaly diagnosis method according to an embodiment of the present disclosure;
FIG. 3 schematically illustrates a flow chart for determining an anomaly description and an anomaly level according to an embodiment of the present disclosure;
FIG. 4 schematically illustrates one of the flow charts for determining a target repair strategy according to an embodiment of the present disclosure;
FIG. 5 schematically illustrates a second flow chart of determining a target repair strategy according to an embodiment of the present disclosure;
FIG. 6 schematically illustrates a flow diagram for repairing a target database according to an embodiment of the present disclosure;
FIG. 7a schematically illustrates a second flow chart of a database anomaly diagnosis method according to an embodiment of the present disclosure;
FIG. 7b schematically illustrates a third flowchart of a database anomaly diagnosis method according to an embodiment of the present disclosure;
fig. 8 is a block diagram schematically showing the configuration of a database abnormality diagnosis apparatus according to an embodiment of the present disclosure;
FIG. 9 schematically illustrates a block diagram of an electronic device adapted to implement a database anomaly diagnosis method according to an embodiment of the present disclosure.
Detailed Description
Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.
All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.
Where a convention analogous to "A, B and at least one of C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include, but not be limited to, systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).
It should be noted that the database abnormality diagnosis method, apparatus, electronic device, storage medium and program product provided by the embodiments of the present disclosure relate to the technical field of artificial intelligence. The database abnormality diagnosis method, apparatus, electronic device, storage medium, and program product provided by the embodiments of the present disclosure may be applied to the financial field or any field other than the financial field, for example, the database abnormality diagnosis method, apparatus, electronic device, storage medium, and program product provided by the embodiments of the present disclosure may be applied to a test service in the financial field. The present disclosure does not limit the application fields of the database abnormality diagnosis method, apparatus, electronic device, storage medium, and program product.
In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure, application and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations, necessary confidentiality measures are taken, and the customs of the public order is not violated.
The embodiment of the disclosure provides a database abnormality diagnosis method, which includes: acquiring an error log and a real-time operation index of a target database; determining the abnormal description and the abnormal grade of the target database by using a neural network model according to the error log and the operation index; determining a target repair strategy according to the abnormal description, the abnormal level and the state of the neural network model, wherein the neural network model comprises a plurality of states, and the neural network model is switched among the plurality of states according to the credibility of the neural network model; sending a repair instruction to the target database according to the target repair strategy, wherein the repair instruction is configured to: and enabling the target database to repair the abnormity according to the repair instruction.
By adopting the database abnormity diagnosis method of the embodiment of the disclosure, automatic diagnosis and repair can be carried out on the target database, and in the process, higher degree of automation is realized, the dependence on manpower is reduced, and the abnormity repair efficiency is improved. More importantly, in the embodiment of the disclosure, the error log and the operation index are combined, and the neural network model is used for performing anomaly diagnosis (that is, determining the description and the level of the anomaly), so that which kind of anomaly occurs in the target database can be determined, and the cause of the anomaly and the emergency degree of the anomaly can be analyzed, so that the diagnosis result has finer granularity. On the basis, the target repairing strategy can be determined according to the abnormal description, the abnormal level and the state of the neural network model, the target repairing strategy can be generated according to an accurate and careful diagnosis result all the time, and the repairing priority can be configured according to the emergency degree, so that automatic repairing based on the target repairing strategy is accurate and reliable, and the target database is guaranteed to run stably.
Fig. 1 schematically shows an application scenario diagram of a database anomaly diagnosis method, apparatus, electronic device, storage medium and program product according to an embodiment of the present disclosure, and as shown in fig. 1, an application scenario 100 according to this embodiment may include terminal devices 101, 102, 103, a network 104 and a server 105. The network 104 serves as a medium for providing communication links between the terminal devices 101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
A user may use terminal devices 101, 102, 103 to interact with a server 105 over a network 104 to receive or send messages or the like. The terminal devices 101, 102, 103 may have installed thereon various communication client applications, such as shopping applications, web browser applications, search applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.
The server 105 may be a server providing various services, such as a background management server (for example only) providing support for websites browsed by users using the terminal devices 101, 102, 103. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to the user request) to the terminal device.
It should be noted that the database abnormality diagnosis method provided by the embodiment of the present disclosure may be generally executed by the server 105. Accordingly, the database abnormality diagnosis apparatus provided by the embodiment of the present disclosure may be generally disposed in the server 105. The database abnormality diagnosis method provided by the embodiment of the present disclosure may also be executed by a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105. Accordingly, the database abnormality diagnosis apparatus provided in the embodiment of the present disclosure may also be disposed in a server or a server cluster that is different from the server 105 and is capable of communicating with the terminal devices 101, 102, 103 and/or the server 105.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
The database abnormality diagnosis method of the disclosed embodiment will be described in detail below with reference to fig. 2 to 7b based on the scenario described in fig. 1.
Fig. 2 schematically shows one of flowcharts of a database abnormality diagnosis method according to an embodiment of the present disclosure, and as shown in fig. 2, the database abnormality diagnosis method of this embodiment includes steps S210 to S240.
It should be noted that, although the steps in the drawings are shown in sequence as indicated by arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not performed in the exact order shown and may be performed in other orders unless explicitly stated herein. Moreover, at least some of the steps in the figures may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, in different orders, and may be performed in turn or in alternation with other steps or at least some of the sub-steps or stages of other steps.
In step S210, an error log and a real-time operation index of the target database are obtained.
In the embodiment of the present disclosure, the method for diagnosing database abnormality may be applied to automatically diagnose abnormality of a database in a test environment, and the target database may include a database for providing functions such as data support in the test environment, for example, the target database may include a mysql database.
In the embodiment of the present disclosure, the error log of the target database may be obtained according to a preset frequency, and the error log in the target database may also be monitored in real time. When the error logs of the target database are obtained according to the preset frequency, the preset frequency may be determined according to actual needs, for example, the preset frequency may be set to be one hour, half hour, fifteen minutes, or even one minute. When the error logs in the target database are monitored in real time, once the target error logs are found, step S210 may be executed.
In the embodiment of the disclosure, the operation index of the target database can be continuously monitored and collected, so as to obtain a real-time operation index.
Optionally, when the error log of the target database is obtained according to the preset frequency, the operation index may also be obtained according to the same preset frequency, so that the matching between the error log and the operation index is realized by using the preset frequency as a dimension, and further, in step S220, a group of matched error log and operation index is used as an input parameter of the neural network model.
Optionally, when the error logs of the target database are obtained according to the preset frequency, the length of the preset frequency may be controlled, so that the error logs obtained each time only include one exception as much as possible, for example, the sampling frequency may be increased by increasing the preset frequency, so that the error logs obtained each time only include one exception as much as possible.
In step S220, according to the error log and the operation index, the anomaly description and the anomaly level of the target database are determined by using the neural network model.
In the embodiment of the present disclosure, the error log includes an exception occurred in the target database, for example, an out-of-memory limit, and the like. By utilizing the neural network model and combining the error log and the operation indexes, the operation indexes which have problems when the memory is over-limited can be analyzed, and then the reasons for generating the memory over-limit are analyzed according to the problem indexes, so that abnormal description is obtained.
For example, key features may be extracted from error logs and performance metrics and then input into the neural network model. The neural network model may classify these key features as a whole according to pre-trained rules.
For example, when the key feature a is extracted from the error log and the key feature B is extracted from the operation index, the key feature a and the key feature B can be classified into C as a whole through the neural network model, and the anomaly description C' set corresponding to the classification result is obtained. The key feature a may include information of "abnormality D occurred in the target database", and the key feature B includes a problem indicator E when "abnormality D occurred in the target database". When extracting the key feature A from the error log and extracting the key feature F from the operation index, the key feature A and the key feature F can be classified to G as a whole through the neural network model, and then the abnormal description G ' set corresponding to the classification result is obtained, wherein the key feature A can comprise information of ' abnormal D occurring in the target database ', and the key feature F comprises the problem index H when the ' abnormal D occurring in the target database '.
Alternatively, the abnormality level may be used to indicate the degree of urgency of an abnormality, and since the abnormality description includes information such as the cause of the abnormality, the abnormality level may be set in correspondence with the abnormality description, for example, when the abnormality description is the abnormality description C ', it may be determined that the abnormality level is a first level corresponding to the "abnormality description C'". When the abnormality description is the abnormality description G ', it may be determined that the abnormality level is a second level corresponding to the "abnormality description G'".
In step S230, a target repair strategy is determined according to the anomaly description, the anomaly level, and the state of the neural network model. Wherein the neural network model comprises a plurality of states, the neural network model switching between the plurality of states according to its confidence level.
In the embodiment of the present disclosure, the plurality of states of the neural network model may include a first state and a second state, for example, at an initial stage of the application of the neural network model, the reliability of the neural network model is to be verified, and therefore, the neural network model may be in the first state, and at this time, a target repair policy matching the neural network model may be determined according to the abnormal description, for example, for the abnormal description G ', the repair policy may include an adjustment problem indicator H, and for the abnormal description C', the repair policy may include an adjustment problem indicator E. And then, sending the result (abnormal description and abnormal grade) output by the neural network model to an auditor for rechecking, determining a target repair strategy according to the feedback result of the auditor (for example, the abnormal description and the abnormal grade determined by the auditor according to the error log and the operation index), correspondingly adjusting the neural network model, and updating the reliability of the neural network model. When the reliability meets the requirement, the neural network model can be in a second state, and at the moment, the target repair strategy can be determined directly according to the result output by the neural network model. In this way, in step S230, the target repair strategy can be determined according to the accurate description of the anomaly and the anomaly level, so that the effectiveness of the target repair strategy can be improved.
Alternatively, the repair policy may be prioritized according to the anomaly level, for example, when the anomaly level is high, this repair policy may be made to have a high priority, so that repair is prioritized. Accordingly, when the anomaly level is low, this repair strategy may be made to have a lower priority, and thus repairs may be made relatively late.
In step S240, the abnormality of the target database is repaired according to the target repair policy.
In this embodiment of the present disclosure, a repair instruction may be issued to the target database according to the target repair policy, and the repair instruction may be configured to: and the target database automatically repairs the abnormity according to the repair instruction, for example, the problem index H or the problem index E is automatically adjusted according to the repair instruction so as to repair.
By adopting the database abnormity diagnosis method of the embodiment of the disclosure, automatic diagnosis and repair can be carried out on the target database, and in the process, higher degree of automation is realized, the dependence on manpower is reduced, and the abnormity repair efficiency is improved. More importantly, in the embodiment of the disclosure, the error log and the operation index are combined, and the neural network model is used for performing anomaly diagnosis (that is, determining the description and the level of the anomaly), so that which kind of anomaly occurs in the target database can be determined, and the cause of the anomaly and the emergency degree of the anomaly can be analyzed, so that the diagnosis result has finer granularity. On the basis, the target repairing strategy can be determined according to the abnormal description, the abnormal level and the state of the neural network model, the target repairing strategy can be generated according to an accurate and careful diagnosis result all the time, and the repairing priority can be configured according to the emergency degree, so that automatic repairing based on the target repairing strategy is accurate and reliable, and the target database is guaranteed to run stably.
The database abnormality diagnosis method provided by the embodiment of the present disclosure is further described below with reference to fig. 2 to 7 b.
In some embodiments, the operational indicators include: semi-synchronous parameter information, database basic configuration information, database hardware information, database software information, transaction call amount and response time.
In the embodiment of the disclosure, the error log of the target database can be acquired through tools such as FTP, and the operation index of the target database can be acquired through tools such as XSHELL.
In some embodiments, the neural network model may include a convolutional neural network, a long-short term memory neural network, a deep belief network, a generative countermeasure network, a recurrent neural network, and so on, in the embodiments of the present disclosure, the neural network model includes a long-short term memory neural network model, fig. 3 schematically illustrates a flowchart for determining an anomaly description and an anomaly level according to the embodiments of the present disclosure, and as shown in fig. 3, step S220 includes steps S221 to S223.
In step S221, a first formatting process is performed on the error log to obtain first feature vector data.
In step S222, a second formatting process is performed on the operation index to obtain second feature vector data.
In the embodiment of the present disclosure, since the error log and the operation index are non-formatted data, in order to facilitate the use of the neural network model, the error log and the operation index need to be formatted, that is, the error log is first formatted, and the operation index is second formatted. In the embodiment of the disclosure, the error log and the operation index may be preprocessed and formatted by a natural language processing algorithm. The pre-processing may include, for example: case conversion, number processing, removal of useless symbols such as redundant spaces, word segmentation of text, removal of stop words, and the like. In the embodiment of the present disclosure, the natural language processing algorithm may be determined according to actual needs, for example, the natural language processing algorithm may include a word2vec algorithm.
Optionally, the formats of the first feature vector data and the second feature vector data may be determined according to actual needs, for example, after the second formatting process is performed on the operation index, the format of the first feature vector data and the second feature vector data may be obtained as an index name: numerical "second feature vector data. The first feature vector data is similar to the first feature vector data, and therefore, the description thereof is omitted.
In step S223, step S2231 and step S2232 are performed using the long-short term memory neural network model.
In step S2231, an anomaly of the target database and a cause of the anomaly are determined according to the first eigenvector data and the second eigenvector data, so as to obtain an anomaly description.
In the embodiment of the disclosure, the prediction set knowledge base may be constructed by combining expert experience, for example, samples (e.g., feature vector data of error log samples and operation index samples) may be labeled by a dimension of an anomaly and a cause causing the anomaly, so as to construct the prediction set knowledge base. And after the prediction set knowledge base is constructed, training the neural network model by using the prediction set knowledge base.
For example, for the abnormal description of "the database is down caused by the memory overrun", the expert may label the third eigenvector data J representing "the database is down" and the fourth eigenvector data K representing "the memory overrun", so that after the neural network model is trained, when the neural network model is referred to as the third eigenvector data J and the fourth eigenvector data K, it can be determined that the abnormality of "the database is down" exists in the target database, and meanwhile, the reason of "the memory overrun" may be determined, and then the abnormal description is obtained by combining the two, that is, "the database is down caused by the memory overrun".
In step S2232, an anomaly level is determined based on the anomaly and the cause of the anomaly.
In the embodiment of the present disclosure, the division of the exception levels may be determined according to actual needs, for example, the exception levels may be divided into two levels according to risk degrees, which are a first level L1 and a second level L2.
Alternatively, the exception level may be set corresponding to the exception description, for example, the exception level corresponding to the exception description containing information such as "database deadlock", "data error", and "sql run timeout" may be set to the first level L1. And setting the exception grade corresponding to the exception description containing the information of insufficient memory, configuration error and the like as a second grade L2.
Optionally, the exception level may be further subdivided according to the cause in the exception description. For example, when the abnormality level setting is again performed in the above manner, the abnormality level corresponding to the abnormality X should be the first level L1, but when it is caused by a system power failure, a hardware error, or the like, the abnormality level corresponding thereto may be set to the third level L3.
In embodiments of the present disclosure, a hyper-parameter tuning method may be used to train the neural network model. Alternatively, the hyper-parameter adjustment method may include a grid search and a random search. For example, when the cost of training time is low, a grid search mode may be used, and when the cost of training time is high, a random search mode may be used.
Alternatively, when the mean error of the neural network model is within 30%, it is determined that the training is completed. And determining the corresponding abnormal description according to the first feature vector data and the second feature vector data by the trained neural network model.
In some embodiments, the plurality of states of the neural network model includes a first state and a second state. When the trustworthiness of the neural network model is to be verified, the neural network model may be placed in a first state. For example, the neural network model may be in the first state when the neural network model has just been put into use, and/or when the accuracy of the neural network model does not reach a preset accuracy. When the reliability of the neural network model is more reliable, the neural network model can be in the second state. For example, the neural network model may be in the second state when the neural network model has been in use for a certain time and/or when the accuracy of the neural network model reaches a preset accuracy.
Fig. 4 schematically illustrates one of the flowcharts for determining the target repair strategy according to the embodiment of the present disclosure, and as shown in fig. 4, when the neural network model is in the first state, step S230 includes steps S231 to S233.
In step S231, the anomaly description, the anomaly level, the error log, and the operation index are sent to the auditor.
In step S232, a target repair policy is determined according to the feedback of the auditor.
In step S233, the neural network model is corrected according to the feedback of the auditor.
In the embodiment of the present disclosure, the auditing party may recheck the anomaly description and the anomaly level determined by the neural network model according to the error log and the operation index. When the review passes, the first information may be fed back, and when the review does not pass, the second information may be fed back. When the auditor considers that the abnormal description and the abnormal level determined by the neural network model are consistent with the error log and the operation index, the double check can be determined to pass, otherwise, the double check is determined to fail.
Optionally, in response to the first information, the target repair policy may be determined according to the anomaly description and the anomaly level determined by the neural network model, and the reliability of the neural network model is updated in a forward direction, that is, the reliability of the updated neural network model is favorable for being in the second state.
Optionally, the second information includes an exception description and an exception level determined by the auditor according to the error log and the operation index. In the embodiment of the disclosure, the target repair policy may be determined according to the anomaly description and the anomaly level provided by the auditor in response to the second information. And correcting the neural network model according to the abnormal description and the abnormal grade in the second information.
Fig. 5 schematically illustrates a second flowchart of determining a target repair strategy according to an embodiment of the present disclosure, and as shown in fig. 5, when the neural network model is in the second state, step S230 includes step S234.
In step S234, a repair policy matching the anomaly description and the anomaly level is obtained to obtain a target repair policy.
In the embodiment of the present disclosure, a repair policy that matches the abnormal description and the abnormal level configuration may be configured according to expert experience, for example, the abnormal description "downtime of the database caused by memory overrun" may be described, and the repair policy may include "capacity expansion of the memory of the target database" or "limitation of access to the target database", and the like.
Fig. 6 schematically illustrates a flowchart of repairing a target database according to an embodiment of the present disclosure, and as shown in fig. 6, in some specific embodiments, step S240 includes steps S241 to S242.
In step S241, a repair instruction matching the target repair policy is generated according to the target repair policy and stored in the repair queue.
In the embodiment of the disclosure, the repair instruction is stored in the repair queue first, and then the abnormality of the target database is repaired in batch according to a preset period.
For example, the target database may be repaired while the target database is idle.
In step S242, at least a part of the repair instructions in the repair queue is sent to the server matched with the repair instruction according to a preset period, and the repair instruction is configured to enable the server matched with the repair instruction to repair the target database. When a plurality of repair instructions are stored in the repair queue, the repair instructions are sorted according to the abnormal level matched with each repair instruction.
In the embodiment of the present disclosure, priority labeling may be performed on the repair instruction according to the exception level, so that the repair instruction may be issued according to the priority labeling and the order of priority from high to low, so as to repair the exception of the target database.
Optionally, the exception level may be positively correlated with the risk degree of the exception, and the higher the exception level is, the higher the priority of the corresponding repair instruction is, so as to preferentially handle the exception with the higher risk degree.
Optionally, for multiple repair instructions, when the exception levels are the same, sorting may be performed according to the sequence in which the multiple repair instructions are stored in the repair queue.
In the embodiment of the disclosure, when the error log and the operation index are obtained, the IP address of the server where the target database is located may also be obtained, and the IP address is associated with the repair instruction. In step S242, the server corresponding to the IP address associated with the repair instruction may be used as the server matched with the repair instruction, and the repair instruction is sent to the server. The server can adjust corresponding system configuration and the like according to the repair instruction so as to perform self-repair on the target database.
Alternatively, in the embodiment of the present disclosure, step S230 and step S240 may be implemented based on another neural network model, and the neural network model may include a convolutional neural network, a long-short term memory neural network, a deep belief network, a generative confrontation network, a recurrent neural network, and the like, which may be specifically determined according to actual needs, and is not limited herein.
Fig. 7a schematically illustrates a second flowchart of the database abnormality diagnosis method according to the embodiment of the present disclosure, and as shown in fig. 7a, in some specific embodiments, after step S240, the database abnormality diagnosis method further includes step S310 to step S320.
In step S310, a first target user matching the target database is queried.
In step S320, early warning information is generated according to the error log, the operation index, the anomaly description, the anomaly level, and the target repairing policy.
In step S330, sending the warning information to the first target user, where the warning information is configured to: and displaying according to a display mode matched with the abnormal grade.
And evaluating the model after the model is built, judging whether the output command can solve the database problem, and conveying the model meeting the requirement to a pre-estimation model storage device for storage.
In the disclosed embodiment, the first target user may include a relevant staff member performing maintenance work on the target database. Optionally, the warning information may further include an IP address of the server, and the like. Therefore, related workers of the target database can be inquired according to the IP address of the server in combination with the standing book information and the like, and the early warning information is automatically pushed to the related workers to perform early warning.
Optionally, different exception levels may be labeled with different colors, icons, or text to achieve a hierarchical effect. For example, the higher the anomaly level, the more prominent colors, icons, or text may be used for labeling.
Fig. 7b schematically illustrates a third flowchart of the database abnormality diagnosis method according to the embodiment of the present disclosure, and as shown in fig. 7b, in some specific embodiments, after step S240, the database abnormality diagnosis method further includes step S410 and step S420.
In step S410, the warning information is sent to the second target user.
In step S420, the neural network model is modified according to the feedback of the second target user, and the reliability of the neural network model is updated.
In this embodiment of the present disclosure, the second target user may include a database operation and maintenance expert, and after sending the early warning information to the second target user, if the operation and maintenance expert can repair the abnormality of the target database according to the determined repair instruction, the operation and maintenance expert feeds back the third information.
In some particular embodiments, a confidence level of the neural network model may be adjusted in response to the third information to facilitate switching the neural network model to the second state. And if the operation and maintenance expert repair instruction cannot solve the abnormity of the target database, feeding back fourth information.
In some embodiments, the neural network model and the predetermined repair policy library may be modified in response to the fourth information, so as to implement tuning and upgrading.
By adopting the database abnormity diagnosis method of the embodiment of the disclosure, the processing speed and accuracy of database abnormity can be improved through automatic diagnosis and repair, thereby realizing self-adjustment and self-treatment in a certain range, enabling operation and maintenance to be more convenient and operation and maintenance to be more stable and reliable in a test environment database system. Moreover, the database anomaly diagnosis provided by the embodiment of the disclosure can also realize continuous iteration according to feedback, and when the current model cannot solve the database anomaly, the database anomaly diagnosis can be continuously optimized and upgraded in operation through manual intervention.
Based on the database abnormity diagnosis method, the disclosure also provides a database abnormity diagnosis device. The apparatus will be described in detail below with reference to fig. 8.
Fig. 8 schematically shows a block diagram of a database abnormality diagnosis apparatus according to an embodiment of the present disclosure, and as shown in fig. 8, a database abnormality diagnosis apparatus 800 of this embodiment includes an acquisition module 810, a first processing module 820, a second processing module 830, and a repair module 840.
The obtaining module 810 is configured to obtain an error log and an operation index of the target database in real time. In an embodiment, the obtaining module 810 may be configured to perform the step S210 described above, which is not described herein again.
The first processing module 820 is used for determining the abnormal description and the abnormal level of the target database by using the neural network model according to the error log and the operation index. In an embodiment, the first processing module 820 may be configured to perform the step S220 described above, and is not described herein again.
The second processing module 830 is configured to determine the target repair policy according to the anomaly description, the anomaly level, and a state of a neural network model, where the neural network model includes a plurality of states, and the neural network model switches between the plurality of states according to a reliability of the neural network model. In an embodiment, the second processing module 830 may be configured to perform the step S230 described above, and is not described herein again.
The repair module 840 is configured to repair the abnormality of the target database according to the target repair policy. In an embodiment, the repairing module 840 may be configured to perform the step S240 described above, which is not described herein again.
According to the embodiment of the present disclosure, any plurality of the obtaining module 810, the first processing module 820, the second processing module 830, and the repairing module 840 may be combined and implemented in one module, or any one of them may be split into a plurality of modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the disclosure, at least one of the obtaining module 810, the first processing module 820, the second processing module 830, and the repairing module 840 may be implemented at least partially as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented in hardware or firmware by any other reasonable manner of integrating or packaging a circuit, or implemented in any one of three implementations of software, hardware, and firmware, or in a suitable combination of any of them. Alternatively, at least one of the obtaining module 810, the first processing module 820, the second processing module 830 and the repairing module 840 may be at least partially implemented as a computer program module, which when executed may perform a corresponding function.
By adopting the database abnormity diagnosis device provided by the embodiment of the disclosure, automatic diagnosis and repair can be performed on the target database, in the process, higher degree of automation is realized, the dependence on manpower is reduced, and the abnormity repair efficiency is improved. More importantly, in the embodiment of the disclosure, the error log and the operation index are combined, and the neural network model is used for performing anomaly diagnosis (that is, determining the description and the level of the anomaly), so that which kind of anomaly occurs in the target database can be determined, and the cause of the anomaly and the emergency degree of the anomaly can be analyzed, so that the diagnosis result has finer granularity. On the basis, the target repairing strategy can be determined according to the abnormal description, the abnormal level and the state of the neural network model, the target repairing strategy can be generated according to an accurate and careful diagnosis result all the time, and the repairing priority can be configured according to the emergency degree, so that automatic repairing based on the target repairing strategy is accurate and reliable, and the target database is guaranteed to run stably.
In some embodiments, the neural network model comprises a long-short term memory neural network model, and the second processing module 830 is specifically configured to perform the following steps:
the error log is subjected to first formatting processing to obtain first feature vector data.
And performing second formatting processing on the operation index to obtain second feature vector data.
Performing the following steps by using the long-short term memory neural network model:
and determining the abnormality of the target database and the reason for generating the abnormality according to the first feature vector data and the second feature vector data to obtain the abnormality description.
And determining the abnormality grade according to the abnormality and the reason for generating the abnormality.
In some embodiments, the plurality of states of the neural network model includes a first state and a second state.
When the neural network model is in a first state, determining a target repair strategy according to the abnormity, the abnormity level and the state of the neural network model, wherein the method comprises the following steps:
and sending the abnormal description, the abnormal grade, the error log and the operation index to an auditor.
And determining a target repair strategy according to the feedback of the auditor. And (c) a second step of,
and correcting the neural network model according to the feedback of the auditor.
When the neural network model is in the second state, determining a target repair strategy according to the abnormity, the abnormity level and the state of the neural network model, wherein the target repair strategy comprises the following steps:
and acquiring a repair strategy matched with the exception description and the exception grade to obtain a target repair strategy.
In some embodiments, repairing the anomaly of the target database according to the target repair policy includes:
and generating a repair instruction matched with the target repair strategy according to the target repair strategy, and storing the repair instruction into a repair queue.
And sending at least part of the repair instructions in the repair queue to a server matched with the repair instructions according to a preset period, wherein the repair instructions are configured to enable the server matched with the repair instructions to repair the target database.
When a plurality of repair instructions are stored in the repair queue, the repair instructions are sorted according to the abnormal level matched with each repair instruction.
In some specific embodiments, the database exception diagnosis apparatus further includes a third processing module, and the third processing module is configured to, after repairing the exception of the target database, perform the following steps:
a first target user matching the target database is queried.
And generating early warning information according to the error log, the operation index, the abnormal description, the abnormal grade and the target repair strategy.
Sending early warning information to a first target user, wherein the early warning information is configured as: and displaying according to a display mode matched with the abnormal grade.
In some specific embodiments, the database abnormality diagnosis apparatus further includes a fourth processing module, where the fourth processing module is configured to, after repairing the abnormality of the target database, perform the following steps:
and sending the early warning information to a second target user.
And correcting the neural network model according to the feedback of the second target user, and updating the state of the neural network model.
In some embodiments, the operational indicators include: semi-synchronous parameter information, database basic configuration information, database hardware information, database software information, transaction call amount and response time.
By adopting the database abnormity diagnosis device of the embodiment of the disclosure, through automatic diagnosis and repair, the abnormal processing speed and accuracy of the database can be improved, thereby realizing self-adjustment and self-treatment in a certain range, enabling the operation and maintenance to be more convenient and faster, and the test environment database system to be more stable and reliable. Moreover, the database anomaly diagnosis provided by the embodiment of the disclosure can also realize continuous iteration according to feedback, and when the current model cannot solve the database anomaly, the database anomaly diagnosis can be continuously optimized and upgraded in operation through manual intervention.
FIG. 9 schematically illustrates a block diagram of an electronic device suitable for implementing a database anomaly diagnosis method according to an embodiment of the present disclosure.
As shown in fig. 9, an electronic apparatus 900 according to an embodiment of the present disclosure includes a processor 901 which can perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM) 902 or a program loaded from a storage portion 908 into a Random Access Memory (RAM) 903. Processor 901 may comprise, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 901 may also include on-board memory for caching purposes. The processor 901 may comprise a single processing unit or a plurality of processing units for performing the different actions of the method flows according to embodiments of the present disclosure.
In the RAM 903, various programs and data necessary for the operation of the electronic apparatus 900 are stored. The processor 901, the ROM 902, and the RAM 903 are connected to each other through a bus 904. The processor 901 performs various operations of the method flows according to the embodiments of the present disclosure by executing programs in the ROM 902 and/or the RAM 903. Note that the programs may also be stored in one or more memories other than the ROM 902 and the RAM 903. The processor 901 may also perform various operations of the method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.
The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the database abnormality diagnosis method according to the embodiment of the present disclosure.
According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include the ROM 902 and/or the RAM 903 described above and/or one or more memories other than the ROM 902 and the RAM 903.
Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the method illustrated in the flow chart. When the computer program product runs in a computer system, the program code is used for causing the computer system to realize the database abnormality diagnosis method provided by the embodiment of the present disclosure.
The computer program performs the above-described functions defined in the system/apparatus of the embodiments of the present disclosure when executed by the processor 901. The systems, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.
In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of a signal on a network medium, and downloaded and installed through the communication section 909 and/or installed from the removable medium 911. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 909, and/or installed from the removable medium 911. The computer program, when executed by the processor 901, performs the above-described functions defined in the system of the embodiment of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.
In accordance with embodiments of the present disclosure, program code for executing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, these computer programs may be implemented using high level procedural and/or object oriented programming languages, and/or assembly/machine languages. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, the "C" language, or the like. The program code may execute entirely on the user computing device, partly on the user device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It will be appreciated by a person skilled in the art that various combinations or/and combinations of features recited in the various embodiments of the disclosure and/or in the claims may be made, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.
The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.
Claims (11)
1. A method for diagnosing database abnormalities, comprising:
acquiring an error report log of a target database and a real-time operation index of the target database;
determining the abnormal description and the abnormal grade of the target database by utilizing a neural network model according to the error log and the operation index;
determining a target repair strategy according to the anomaly description, the anomaly level and the state of the neural network model, wherein the neural network model comprises a plurality of states, and the neural network model switches among the plurality of states according to the credibility of the neural network model;
and repairing the abnormity of the target database according to the target repairing strategy.
2. The database abnormality diagnosis method according to claim 1, wherein the neural network model includes a long-short term memory neural network model, and the determining the abnormality of the target database and the abnormality level of the abnormality using the neural network model based on the error log and the operation index includes:
performing first formatting processing on the error report log to obtain first feature vector data;
performing second formatting processing on the operation index to obtain second feature vector data;
performing the following steps using the long-short term memory neural network model:
according to the first feature vector data and the second feature vector data, determining the abnormality of the target database and the reason for generating the abnormality so as to obtain the abnormality description;
and determining the abnormality grade according to the abnormality and the reason for generating the abnormality.
3. The database abnormality diagnostic method according to claim 1, characterized in that the plurality of states of the neural network model include a first state and a second state;
when the neural network model is in the first state, determining a target repair strategy according to the abnormality description, the abnormality level and the state of the neural network model, wherein the determining comprises the following steps:
sending the abnormal description, the abnormal grade, the error log and the operation index to an auditor;
determining the target repair strategy according to the feedback of the auditor; and (c) a second step of,
correcting the neural network model according to the feedback of the auditor;
when the neural network model is in the second state, determining a target repair strategy according to the anomaly description, the anomaly level and the state of the neural network model, including:
and acquiring a repair strategy matched with the exception description and the exception grade to obtain the target repair strategy.
4. The database anomaly diagnosis method according to claim 1, wherein repairing the anomaly of the target database according to the target repair policy comprises:
generating a repair instruction matched with the target repair strategy according to the target repair strategy, and storing the repair instruction into a repair queue;
sending at least part of repair instructions in the repair queue to a server matched with the repair instructions according to a preset period, wherein the repair instructions are configured to enable the server matched with the repair instructions to repair the target database;
when a plurality of repair instructions are stored in the repair queue, the repair instructions are sorted according to the exception grade matched with each repair instruction.
5. The database abnormality diagnosis method according to claim 1, characterized in that after the abnormality of the target database is repaired, the database abnormality diagnosis method further comprises:
querying a first target user matched with the target database;
generating early warning information according to the error log, the operation index, the abnormal description, the abnormal grade and the target repair strategy;
sending the early warning information to the first target user, wherein the early warning information is configured to: and displaying according to a display mode matched with the abnormal grade.
6. The database abnormality diagnosis method according to claim 5, characterized in that after the abnormality of the target database is repaired, the database abnormality diagnosis method further comprises:
sending the early warning information to a second target user;
and correcting the neural network model according to the feedback of the second target user, and updating the reliability of the neural network model.
7. The database abnormality diagnostic method according to claim 1, characterized in that the operation index includes: semi-synchronous parameter information, database basic configuration information, database hardware information, database software information, transaction call amount and response time.
8. A database abnormality diagnostic apparatus characterized by comprising:
the acquisition module is used for acquiring an error report log of a target database and a real-time operation index of the target database;
the first processing module is used for determining the abnormal description and the abnormal grade of the target database by utilizing a neural network model according to the error log and the operation index;
the second processing module is used for determining a target repair strategy according to the abnormality description and the abnormality grade, wherein the neural network model comprises a plurality of states, and the neural network model is switched among the plurality of states according to the credibility of the neural network model;
and the repairing module is used for repairing the abnormity of the target database according to the target repairing strategy.
9. An electronic device, comprising:
one or more processors;
a storage device for storing one or more programs,
wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the database anomaly diagnosis method according to any one of claims 1 to 7.
10. A computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the database abnormality diagnosis method according to any one of claims 1 to 7.
11. A computer program product comprising a computer program which, when executed by a processor, implements the database anomaly diagnosis method according to any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210844183.XA CN115686895A (en) | 2022-07-18 | 2022-07-18 | Database abnormality diagnosis method, apparatus, device, medium, and program product |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210844183.XA CN115686895A (en) | 2022-07-18 | 2022-07-18 | Database abnormality diagnosis method, apparatus, device, medium, and program product |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115686895A true CN115686895A (en) | 2023-02-03 |
Family
ID=85060815
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210844183.XA Pending CN115686895A (en) | 2022-07-18 | 2022-07-18 | Database abnormality diagnosis method, apparatus, device, medium, and program product |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115686895A (en) |
-
2022
- 2022-07-18 CN CN202210844183.XA patent/CN115686895A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11562304B2 (en) | Preventative diagnosis prediction and solution determination of future event using internet of things and artificial intelligence | |
US11823109B2 (en) | System and method for evaluating images to support multiple risk applications | |
US11037080B2 (en) | Operational process anomaly detection | |
US11853337B2 (en) | System to determine a credibility weighting for electronic records | |
AU2019278989B2 (en) | System and method for analyzing and modeling content | |
US11675750B2 (en) | User generated tag collection system and method | |
CN113570269A (en) | Operation and maintenance project management method, device, equipment, medium and program product | |
US11645540B2 (en) | Deep graph de-noise by differentiable ranking | |
CN111178687A (en) | Financial risk classification method and device and electronic equipment | |
CN111191677A (en) | User characteristic data generation method and device and electronic equipment | |
US20220318681A1 (en) | System and method for scalable, interactive, collaborative topic identification and tracking | |
CN116225848A (en) | Log monitoring method, device, equipment and medium | |
CN114706856A (en) | Fault processing method and device, electronic equipment and computer readable storage medium | |
CN114238641A (en) | Method, device, equipment, storage medium and program product for mining operation and maintenance knowledge | |
CN114461499A (en) | Abnormal information detection model construction method and gray scale environment abnormal detection method | |
CN115686895A (en) | Database abnormality diagnosis method, apparatus, device, medium, and program product | |
CN113961441A (en) | Alarm event processing method, auditing method, device, equipment, medium and product | |
CN113900905A (en) | Log monitoring method and device, electronic equipment and storage medium | |
CN114140004A (en) | Data processing method and device, electronic equipment and storage medium | |
CN114358024A (en) | Log analysis method, apparatus, device, medium, and program product | |
US20230064674A1 (en) | Iterative training of computer model for machine learning | |
CN115689263A (en) | Information generation method, device, equipment and storage medium | |
CN118211832A (en) | Financial tax data risk monitoring method, system, electronic equipment and storage medium | |
CN116563032A (en) | Internet asset risk prediction method, device, equipment, medium and program product | |
CN117973627A (en) | Data prediction method, device, apparatus, storage medium, and program product |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |