A method, apparatus, electronic device, and storage medium for handling operational and maintenance anomalies.

Abstract

This application relates to the field of operation and maintenance processing technology, and provides a method, device, electronic device, and storage medium for handling operation and maintenance anomalies. The method includes: for any anomaly information in an operation and maintenance message, determining the key information corresponding to the anomaly information; based on the anomaly information and the key information, determining the target fit degree between the anomaly information and a preset anomaly type; selecting a target anomaly type from the preset anomaly types based on the target fit degree, and correcting the anomaly information through a correction method corresponding to the target anomaly type. This embodiment not only realizes the investigation of anomaly information, but also determines the anomaly type of the anomaly information and corrects the anomaly information, thus performing anomaly handling comprehensively, accurately, and efficiently.

Description

Technical Field

[0001] This application relates to the field of operation and maintenance processing technology, and in particular to a method, apparatus, electronic device and storage medium for handling operation and maintenance anomalies. Background Technology

[0002] With the development of technology, more and more products are being developed to meet new needs. In order to ensure the stable operation of these products, maintenance and management are necessary.

[0003] In related technologies, it is necessary to manually check for anomalies in operation and maintenance messages and perform anomaly repair.

[0004] However, as the number of products developed increases, the pressure of operation and maintenance becomes greater, and the above methods are difficult to handle anomalies accurately and efficiently. Summary of the Invention

[0005] This application provides a method, apparatus, electronic device, and storage medium for handling operational and maintenance anomalies, enabling precise and efficient anomaly handling.

[0006] In a first aspect, embodiments of this application provide a method for handling operational and maintenance anomalies, the method comprising:

[0007] For any abnormal information in the operation and maintenance message, determine the key information corresponding to the abnormal information;

[0008] Based on the abnormal information and the key information, determine the target fit between the abnormal information and the preset abnormal type;

[0009] Based on the target fit, a target anomaly type is selected from the preset anomaly types, and the anomaly information is corrected using the correction method corresponding to the target anomaly type.

[0010] The above solution not only investigates abnormal information in operation and maintenance messages, but also accurately determines the target fit between abnormal information and preset abnormal types based on abnormal information and key information; then it determines the target abnormal type of abnormal information, and accurately corrects the abnormal information by means of the correction method corresponding to the target abnormal type. This embodiment realizes the investigation, determination and correction of abnormal information, and performs abnormal handling in a comprehensive, accurate and efficient manner.

[0011] In some optional implementations, determining the key information corresponding to the abnormal information includes:

[0012] Determine the adjacent information of the abnormal information in the operation and maintenance message;

[0013] The key information representing anomalous content is determined through Neuro-Linguistic Programming (NLP); wherein, the anomalous content includes the anomalous information and the adjacent information.

[0014] The above scheme, since the adjacent information of the abnormal information can also reflect the relevant content of the abnormal information, uses NLP to extract features from the abnormal information and the abnormal content composed of adjacent information to obtain key information that represents the abnormal content. This key information can accurately and concisely reflect the main abnormal situation of the abnormal information.

[0015] In some optional implementations, based on the anomaly information and the key information, determining the target fit between the anomaly information and a preset anomaly type includes:

[0016] Feature extraction is performed on the abnormal information and the key information at each level to obtain the target features of the abnormal information at each level;

[0017] For any level, determine the fit between the target feature of the level and the preset feature of the preset anomaly type at the level;

[0018] For any preset anomaly type, the second fitting degree of the preset anomaly type is adjusted based on the first fitting degree of the preset anomaly type to obtain the target fitting degree between the anomaly information and the preset anomaly type; wherein, the first fitting degree is the fitting degree between the target feature at the nth level and the preset feature of the preset anomaly type at the nth level, and the second fitting degree is the fitting degree between the target feature at the Nth level and the preset feature of the preset anomaly type at the Nth level, n≤N-1, and N is the total number of levels.

[0019] The above scheme can obtain richer and more comprehensive features (target features of abnormal information) by extracting features from abnormal information and key information at each level; then determine the fitting degree between the preset features and the corresponding target features of each level of the preset abnormal type; and adjust the fitting degree of the Nth level based on the fitting degree of the 1st to (N-1)th levels of the preset abnormal type to obtain the target fitting degree between the abnormal information and the preset abnormal type.

[0020] In some optional implementations, a second fit of the preset anomaly type is adjusted based on a first fit of the preset anomaly type to obtain a target fit between the anomaly information and the preset anomaly type, including:

[0021] Determine the weight coefficients corresponding to the first degree of fit of the preset anomaly type;

[0022] The second fit of the preset anomaly type is adjusted based on the weighting coefficient to obtain the target fit between the anomaly information and the preset anomaly type.

[0023] In some optional implementations, selecting a target anomaly type from the preset anomaly types based on the target fit includes:

[0024] Sort all preset anomaly types in descending order of target fit.

[0025] If the verification result of the first correction result based on the first verification method is a successful verification, then the first preset anomaly type in the sorting result is determined as the target anomaly type; wherein, the first verification method is the verification method corresponding to the first preset anomaly type, and the first correction result is obtained by correcting the anomaly information through the correction method corresponding to the first preset anomaly type;

[0026] Otherwise, the m-th preset anomaly type in the sorting results is determined as the target anomaly type; wherein, the verification result of verifying the i-th correction result based on the i-th verification method is verification failure, the i-th verification method is the verification method corresponding to the i-th preset anomaly type, and the i-th correction result is obtained by correcting the anomaly information through the correction method corresponding to the i-th preset anomaly type; and the verification result of verifying the m-th correction result based on the m-th verification method is verification success, the m-th verification method is the verification method corresponding to the m-th preset anomaly type, and the m-th correction result is obtained by correcting the anomaly information through the correction method corresponding to the m-th preset anomaly type; i < m.

[0027] The above scheme sorts all preset anomaly types from highest to lowest target fit, selects the target anomaly type that can be verified to correct the above anomaly information, and the target anomaly type that ranks highest in the sort. The correction method corresponding to the target anomaly type can correctly correct the above anomaly information, and the target fit between the anomaly information and the target anomaly type is high.

[0028] Some optional implementations also include:

[0029] The operation and maintenance message, the anomaly information, the target anomaly type, and the correction method are notified through a preset notification method.

[0030] The above solution reduces the occurrence of system errors by notifying users of maintenance messages, anomaly information, target anomaly types, and correction methods, allowing for manual reconfirmation of maintenance anomaly handling.

[0031] Secondly, embodiments of this application also provide an operation and maintenance anomaly handling device, the device comprising:

[0032] The key information determination module is used to determine the key information corresponding to any abnormal information in the operation and maintenance message;

[0033] The goodness-of-fit determination module is used to determine the target goodness-of-fit between the abnormal information and the preset abnormality type based on the abnormal information and the key information.

[0034] The correction module is used to select a target anomaly type from the preset anomaly types based on the target fit degree, and correct the anomaly information through the correction method corresponding to the target anomaly type.

[0035] In some optional implementations, the key information determination module is specifically used for:

[0036] Determine the adjacent information of the abnormal information in the operation and maintenance message;

[0037] The key information representing anomalous content is determined through NLP; wherein, the anomalous content includes the anomalous information and the adjacent information.

[0038] In some optional implementations, the goodness-of-fit determination module is specifically used for:

[0039] Feature extraction is performed on the abnormal information and the key information at each level to obtain the target features of the abnormal information at each level;

[0040] For any level, determine the fit between the target feature of the level and the preset feature of the preset anomaly type at the level;

[0041] For any preset anomaly type, the second fitting degree of the preset anomaly type is adjusted based on the first fitting degree of the preset anomaly type to obtain the target fitting degree between the anomaly information and the preset anomaly type; wherein, the first fitting degree is the fitting degree between the target feature at the nth level and the preset feature of the preset anomaly type at the nth level, and the second fitting degree is the fitting degree between the target feature at the Nth level and the preset feature of the preset anomaly type at the Nth level, n≤N-1, and N is the total number of levels.

[0042] In some optional implementations, the goodness-of-fit determination module is specifically used for:

[0043] Determine the weight coefficients corresponding to the first degree of fit of the preset anomaly type;

[0044] The second fit of the preset anomaly type is adjusted based on the weighting coefficient to obtain the target fit between the anomaly information and the preset anomaly type.

[0045] In some optional implementations, the correction module is specifically used for:

[0046] Sort all preset anomaly types in descending order of target fit.

[0047] If the verification result of the first correction result based on the first verification method is a successful verification, then the first preset anomaly type in the sorting result is determined as the target anomaly type; wherein, the first verification method is the verification method corresponding to the first preset anomaly type, and the first correction result is obtained by correcting the anomaly information through the correction method corresponding to the first preset anomaly type;

[0048] Otherwise, the m-th preset anomaly type in the sorting results is determined as the target anomaly type; wherein, the verification result of verifying the i-th correction result based on the i-th verification method is verification failure, the i-th verification method is the verification method corresponding to the i-th preset anomaly type, and the i-th correction result is obtained by correcting the anomaly information through the correction method corresponding to the i-th preset anomaly type; and the verification result of verifying the m-th correction result based on the m-th verification method is verification success, the m-th verification method is the verification method corresponding to the m-th preset anomaly type, and the m-th correction result is obtained by correcting the anomaly information through the correction method corresponding to the m-th preset anomaly type; i < m.

[0049] In some alternative implementations, a notification module is also included for:

[0050] The operation and maintenance message, the anomaly information, the target anomaly type, and the correction method are notified through a preset notification method.

[0051] Thirdly, embodiments of this application provide an electronic device, including at least one processor and at least one memory, wherein the memory stores a computer program, and when the program is executed by the processor, the processor performs any of the operation and maintenance anomaly handling methods described in the first aspect above.

[0052] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program executable by a computer, which, when run on the computer, causes the computer to perform any of the operation and maintenance anomaly handling methods described in the first aspect above.

[0053] Fifthly, embodiments of this application provide a computer program product comprising computer-executable instructions, the computer-executable instructions being used to cause a computer to execute the operation and maintenance anomaly handling method as described in any of the first aspects.

[0054] Furthermore, the technical effects of any of the implementation methods in aspects two through five can be found in the technical effects of different implementation methods in aspect one, and will not be repeated here. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 A flowchart illustrating the first method for handling operational and maintenance anomalies provided in this application embodiment;

[0057] Figure 2 A flowchart illustrating the second method for handling operational and maintenance anomalies provided in this application embodiment;

[0058] Figure 3 A schematic diagram of the key information extraction model provided in the embodiments of this application;

[0059] Figure 4 A flowchart illustrating the third method for handling operational and maintenance anomalies provided in this application embodiment;

[0060] Figure 5 This is a schematic diagram of the hierarchical feature extraction model provided in the embodiments of this application;

[0061] Figure 6 A flowchart illustrating the fourth method for handling operational and maintenance anomalies provided in this application embodiment;

[0062] Figure 7 A flowchart illustrating the fifth method for handling operational and maintenance anomalies provided in this application embodiment;

[0063] Figure 8 This is a schematic diagram of the structure of the operation and maintenance anomaly handling device provided in the embodiments of this application;

[0064] Figure 9 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0065] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0066] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the term "connection" should be interpreted broadly. For example, it can refer to a direct connection, an indirect connection through an intermediate medium, or a connection within two devices. Those skilled in the art can understand the specific meaning of the above term in this application based on the specific circumstances.

[0067] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0068] To ensure stable product operation, product maintenance and management are necessary.

[0069] In related technologies, it is necessary to manually check for anomalies in operation and maintenance messages and perform anomaly repair.

[0070] However, with the increasing number of products under development, the operational and maintenance pressure is significant, and the above methods are insufficient for accurate and efficient anomaly handling. Especially for frequently occurring anomalies, repeated manual troubleshooting is required, consuming a considerable amount of time.

[0071] In some implementations, artificial intelligence is used to identify anomalies in operation and maintenance messages and issue alerts.

[0072] However, it is still necessary to manually determine the repair method for the anomaly and then perform the repair. This is especially true for complex anomalies, where a significant amount of time needs to be spent manually determining the appropriate repair method.

[0073] In view of this, embodiments of this application propose a method, apparatus, electronic device, and storage medium for handling operation and maintenance anomalies. The method includes: for any anomaly information in an operation and maintenance message, determining key information corresponding to the anomaly information; based on the anomaly information and the key information, determining a target fit degree between the anomaly information and a preset anomaly type; based on the target fit degree, selecting a target anomaly type from the preset anomaly types, and correcting the anomaly information through a correction method corresponding to the target anomaly type.

[0074] The above solution not only investigates abnormal information in operation and maintenance messages, but also accurately determines the target fit between abnormal information and preset abnormal types based on abnormal information and key information; then it determines the target abnormal type of abnormal information, and accurately corrects the abnormal information by means of the correction method corresponding to the target abnormal type. This embodiment realizes the investigation, determination and correction of abnormal information, and performs abnormal handling in a comprehensive, accurate and efficient manner.

[0075] The technical solution of this application and how it solves the above-mentioned technical problems will be described in detail below with reference to the accompanying drawings and specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0076] This application provides a first method for handling operational and maintenance anomalies, such as... Figure 1 As shown, it includes the following steps:

[0077] Step S101: For any abnormal information in the operation and maintenance message, determine the key information corresponding to the abnormal information.

[0078] For example, due to the special nature of the corpus of abnormal information, all abnormal information in the operation and maintenance messages can be identified by parsing and troubleshooting the messages; and for each abnormal message, its corresponding key information can be determined.

[0079] Step S102: Based on the abnormal information and the key information, determine the target fit between the abnormal information and the preset abnormal type.

[0080] For example, the aforementioned key information can accurately reflect the abnormal situation of the corresponding abnormal information. Therefore, based on the abnormal information and the key information, the target fit degree between the abnormal information and each preset abnormal type can be accurately determined, that is, the similarity probability between the abnormal information and each preset abnormal type. By determining the target fit degree between the abnormal information and the preset abnormal type, the target abnormal type of the abnormal information can be accurately determined.

[0081] Based on this, after determining the key information of the above-mentioned abnormal information, the target fit between the abnormal information and the preset abnormal type is determined based on these two parts of information.

[0082] Step S103: Select a target anomaly type from the preset anomaly types based on the target fit degree, and correct the anomaly information using the correction method corresponding to the target anomaly type.

[0083] In this embodiment, based on the target fit degree between the abnormal information and the preset abnormal type, the target abnormal type of the abnormal information can be accurately determined; then, based on the correction method corresponding to the target abnormal type, the abnormal information can be intelligently repaired to obtain the correct information.

[0084] The above solution not only investigates abnormal information in operation and maintenance messages, but also accurately determines the target fit between abnormal information and preset abnormal types based on abnormal information and key information; then it determines the target abnormal type of abnormal information, and accurately corrects the abnormal information by means of the correction method corresponding to the target abnormal type. This embodiment realizes the investigation, determination and correction of abnormal information, and performs abnormal handling in a comprehensive, accurate and efficient manner.

[0085] This application provides a second method for handling operational and maintenance anomalies, such as... Figure 2 As shown, it includes the following steps:

[0086] Step S201: For any abnormal information in the operation and maintenance message, determine the adjacent information of the abnormal information in the operation and maintenance message.

[0087] For example, the adjacent information of the anomaly information includes the context of the anomaly information.

[0088] This embodiment does not limit the specific implementation method for determining the abnormal information and adjacent information in the operation and maintenance message. For example, a convolutional neural network (CNN) model can be trained based on the sample operation and maintenance message and the abnormal information and adjacent information in the sample operation and maintenance message to obtain an anomaly investigation model; the operation and maintenance message can be input into the anomaly investigation model to obtain the abnormal information and adjacent information output by the anomaly investigation model.

[0089] Step S202: Determine key information representing anomalous content through NLP; wherein, the anomalous content includes the anomalous information and the adjacent information.

[0090] For example, the abnormal content composed of abnormal information and the adjacent information is input into the NLP model. The NLP model performs feature extraction on the abnormal content (such as abnormal methods, paths, etc.) to obtain key information representing the abnormal content (including abnormal function information, input parameters, etc.).

[0091] See Figure 3 The diagram shown is a schematic of a key information extraction model, which includes the above-mentioned anomaly detection model and the above-mentioned NLP model.

[0092] The operation and maintenance messages are input into the anomaly investigation model, which outputs anomaly information and adjacent information. The output of the anomaly investigation model is used as input to the NLP model to obtain the key information output by the NLP model.

[0093] The above Figure 3 This is merely an illustrative example, and the specific model used to determine key information is not limited in this embodiment.

[0094] Step S203: Based on the abnormal information and the key information, determine the target fit between the abnormal information and the preset abnormal type.

[0095] Step S204: Select a target anomaly type from the preset anomaly types based on the target fit degree, and correct the anomaly information using the correction method corresponding to the target anomaly type.

[0096] The specific implementation of steps S203 to S204 can be referred to the above embodiments, and will not be repeated here.

[0097] The above scheme, since the adjacent information of the abnormal information can also reflect the relevant content of the abnormal information, uses NLP to extract features from the abnormal information and the abnormal content composed of adjacent information to obtain key information that represents the abnormal content. This key information can accurately and concisely reflect the main abnormal situation of the abnormal information.

[0098] This application provides a third method for handling operational and maintenance anomalies, such as... Figure 4 As shown, it includes the following steps:

[0099] Step S401: For any abnormal information in the operation and maintenance message, determine the key information corresponding to the abnormal information.

[0100] The specific implementation of step S401 can be found in the above embodiments, and will not be repeated here.

[0101] Step S402: Extract features from the abnormal information and the key information at each level to obtain the target features of the abnormal information at each level.

[0102] In this embodiment, N levels are set up. By extracting features from abnormal information and key information at each level, richer and more comprehensive features can be obtained, which makes it easier to determine the target anomaly type more accurately in the future.

[0103] This embodiment does not limit the specific implementation method of feature extraction at each level, as can be found in the following reference. Figure 5 As shown, a hierarchical feature extraction model containing N anomaly classifiers is obtained by training a CNN model containing N softmax classifiers.

[0104] The abnormal information and key information are extracted by anomaly classifier 1 to obtain the target features of the abnormal information at the first level; the abnormal information and key information are extracted by anomaly classifier 2 to obtain the target features of the abnormal information at the second level; the abnormal information and key information are extracted by anomaly classifier 3 to obtain the target features of the abnormal information at the third level; ... the abnormal information and key information are extracted by anomaly classifier N to obtain the target features of the abnormal information at the Nth level.

[0105] Step S403: For any level, determine the fit between the target feature of the level and the preset feature of the preset anomaly type in the level.

[0106] During implementation, preset features for each level of the preset exception type are also set.

[0107] This embodiment does not provide a specific implementation of the method for determining the preset features. For example, the preset features can be determined by determining the target features mentioned above, which will not be elaborated here.

[0108] In this embodiment, determining the fit between the target feature and the preset feature means determining the similarity probability between the two features, such as by determining the distance between feature vectors.

[0109] Step S404: For any preset anomaly type, adjust the second fitting degree of the preset anomaly type based on the first fitting degree of the preset anomaly type to obtain the target fitting degree between the anomaly information and the preset anomaly type.

[0110] Wherein, the first degree of fit is the degree of fit between the target feature at level n and the preset feature of the preset anomaly type at level n, and the second degree of fit is the degree of fit between the target feature at level N and the preset feature of the preset anomaly type at level N, where n ≤ N-1, and N is the total number of levels.

[0111] The above steps have determined the fit between the preset features and the corresponding target features at each level of each preset anomaly type.

[0112] For any preset anomaly type, the fitting degree corresponding to the Nth level is adjusted based on the fitting degree corresponding to the 1st to (N-1)th levels of the preset anomaly type to obtain the target fitting degree between the anomaly information and the preset anomaly type.

[0113] Step S405: Select a target anomaly type from the preset anomaly types based on the target fit degree, and correct the anomaly information using the correction method corresponding to the target anomaly type.

[0114] The specific implementation of step S405 can be found in the above embodiments, and will not be repeated here.

[0115] The above scheme can obtain richer and more comprehensive features (target features of abnormal information) by extracting features from abnormal information and key information at each level; then determine the fitting degree between the preset features and the corresponding target features of each level of the preset abnormal type; and adjust the fitting degree of the Nth level based on the fitting degree of the 1st to (N-1)th levels of the preset abnormal type to obtain the target fitting degree between the abnormal information and the preset abnormal type.

[0116] In some optional implementations, step S404 above can be implemented in, but is not limited to, the following ways:

[0117] Determine the weight coefficients corresponding to the first degree of fit of the preset anomaly type;

[0118] The second fit of the preset anomaly type is adjusted based on the weighting coefficient to obtain the target fit between the anomaly information and the preset anomaly type.

[0119] For example, for any level, there is a pre-defined correspondence between the first degree of fit and the weight coefficient of each pre-defined anomaly type. Based on the correspondence of each pre-defined anomaly type at a certain level, the weight coefficient corresponding to the first degree of fit of the pre-defined anomaly type at that level is determined.

[0120] The product of all weight coefficients of the preset anomaly type and the second degree of fit is determined as the target degree of fit between the anomaly information and the preset anomaly type.

[0121] The above-described method for determining the target fit is merely an illustrative example and is not intended to limit this application.

[0122] This application provides a fourth method for handling operational and maintenance anomalies, such as... Figure 6 As shown, it includes the following steps:

[0123] Step S601: For any abnormal information in the operation and maintenance message, determine the key information corresponding to the abnormal information.

[0124] Step S602: Based on the abnormal information and the key information, determine the target fit between the abnormal information and the preset abnormal type.

[0125] The specific implementation of steps S601 to S602 can be referred to the above embodiments, and will not be repeated here.

[0126] Step S603: Sort all preset anomaly types in descending order of target fit.

[0127] Step S604: If the verification result of the first correction result based on the first verification method is a successful verification, then the first preset anomaly type in the sorting result is determined as the target anomaly type; wherein, the first verification method is the verification method corresponding to the first preset anomaly type, and the first correction result is obtained by correcting the anomaly information through the correction method corresponding to the first preset anomaly type;

[0128] Otherwise, the m-th preset anomaly type in the sorting results is determined as the target anomaly type; wherein, the verification result of verifying the i-th correction result based on the i-th verification method is verification failure, the i-th verification method is the verification method corresponding to the i-th preset anomaly type, and the i-th correction result is obtained by correcting the anomaly information through the correction method corresponding to the i-th preset anomaly type; and the verification result of verifying the m-th correction result based on the m-th verification method is verification success, the m-th verification method is the verification method corresponding to the m-th preset anomaly type, and the m-th correction result is obtained by correcting the anomaly information through the correction method corresponding to the m-th preset anomaly type; i < m.

[0129] For example, the preset anomaly types are sorted from largest to smallest according to the target fit, and the sorting result is preset anomaly type 1, preset anomaly type 2, ..., preset anomaly type M;

[0130] The above abnormal information is corrected by the correction method corresponding to the first preset abnormal type to obtain the first correction result, and the first correction result is verified based on the verification method corresponding to the first preset abnormal type. If the verification passes, the first preset abnormal type is taken as the target abnormal type.

[0131] If the verification fails, the above abnormal information will be corrected using the correction method corresponding to the second preset abnormal type to obtain the second correction result. The second correction result will then be verified based on the verification method corresponding to the second preset abnormal type. If the verification passes, the second preset abnormal type will be used as the target abnormal type. If the verification fails, the above correction and verification process will continue until the preset abnormal type that passes the verification is determined.

[0132] Optionally, a batch asynchronous task framework based on Spring Batch (a data processing framework) and Quartz (a job scheduling framework) can be used to sequentially initiate the above-mentioned list of tasks of the preset exception types (repair, verification, etc.) and record the relevant results.

[0133] The above scheme sorts all preset anomaly types from highest to lowest target fit, selects the target anomaly type that can be verified to correct the above anomaly information, and the target anomaly type that ranks highest in the sort. The correction method corresponding to the target anomaly type can correctly correct the above anomaly information, and the target fit between the anomaly information and the target anomaly type is high.

[0134] This application provides a fifth method for handling operational and maintenance anomalies, such as... Figure 7 As shown, it includes the following steps:

[0135] Step S701: For any abnormal information in the operation and maintenance message, determine the key information corresponding to the abnormal information.

[0136] Step S702: Based on the abnormal information and the key information, determine the target fit between the abnormal information and the preset abnormal type.

[0137] Step S703: Select a target anomaly type from the preset anomaly types based on the target fit degree, and correct the anomaly information using the correction method corresponding to the target anomaly type.

[0138] The specific implementation of steps S701 to S703 can be found in the above embodiments, and will not be repeated here.

[0139] Step S704: Notify the operation and maintenance message, the anomaly information, the target anomaly type, and the correction method through a preset notification method.

[0140] As shown above, in some embodiments, the process of determining the target anomaly type (including repairing the anomaly information using repair methods corresponding to some or all preset anomaly types, and verifying the repair results) is recorded. Based on this, the data generated by this process can also be notified. This allows for subsequent manual approval, self-verification, and investigation, i.e., manually reviewing whether the problem has been correctly resolved and choosing between manual processing or submission for resolution. This process can record data generated during manual processing, including reviewer information.

[0141] The above solution reduces the occurrence of system errors by notifying users of maintenance messages, anomaly information, target anomaly types, and correction methods, allowing for manual reconfirmation of maintenance anomaly handling.

[0142] Based on the same inventive concept, this application provides an operation and maintenance anomaly handling device, see reference. Figure 8 As shown, the maintenance anomaly handling device 800 includes:

[0143] The key information determination module 801 is used to determine the key information corresponding to any abnormal information in the operation and maintenance message;

[0144] The goodness-of-fit determination module 802 is used to determine the target goodness-of-fit between the abnormal information and the preset abnormality type based on the abnormal information and the key information.

[0145] The correction module 803 is used to select a target anomaly type from the preset anomaly types based on the target fit degree, and correct the anomaly information through the correction method corresponding to the target anomaly type.

[0146] In some optional implementations, the key information determination module 801 is specifically used for:

[0147] Determine the adjacent information of the abnormal information in the operation and maintenance message;

[0148] The key information representing anomalous content is determined through NLP; wherein, the anomalous content includes the anomalous information and the adjacent information.

[0149] In some optional implementations, the goodness-of-fit determination module 802 is specifically used for:

[0150] Feature extraction is performed on the abnormal information and the key information at each level to obtain the target features of the abnormal information at each level;

[0151] For any level, determine the fit between the target feature of the level and the preset feature of the preset anomaly type at the level;

[0152] For any preset anomaly type, the second fitting degree of the preset anomaly type is adjusted based on the first fitting degree of the preset anomaly type to obtain the target fitting degree between the anomaly information and the preset anomaly type; wherein, the first fitting degree is the fitting degree between the target feature at the nth level and the preset feature of the preset anomaly type at the nth level, and the second fitting degree is the fitting degree between the target feature at the Nth level and the preset feature of the preset anomaly type at the Nth level, n≤N-1, and N is the total number of levels.

[0153] In some optional implementations, the goodness-of-fit determination module 802 is specifically used for:

[0154] Determine the weight coefficients corresponding to the first degree of fit of the preset anomaly type;

[0155] The second fit of the preset anomaly type is adjusted based on the weighting coefficient to obtain the target fit between the anomaly information and the preset anomaly type.

[0156] In some optional implementations, the correction module 803 is specifically used for:

[0157] Sort all preset anomaly types in descending order of target fit.

[0158] If the verification result of the first correction result based on the first verification method is a successful verification, then the first preset anomaly type in the sorting result is determined as the target anomaly type; wherein, the first verification method is the verification method corresponding to the first preset anomaly type, and the first correction result is obtained by correcting the anomaly information through the correction method corresponding to the first preset anomaly type;

[0159] Otherwise, the m-th preset anomaly type in the sorting results is determined as the target anomaly type; wherein, the verification result of verifying the i-th correction result based on the i-th verification method is verification failure, the i-th verification method is the verification method corresponding to the i-th preset anomaly type, and the i-th correction result is obtained by correcting the anomaly information through the correction method corresponding to the i-th preset anomaly type; and the verification result of verifying the m-th correction result based on the m-th verification method is verification success, the m-th verification method is the verification method corresponding to the m-th preset anomaly type, and the m-th correction result is obtained by correcting the anomaly information through the correction method corresponding to the m-th preset anomaly type; i < m.

[0160] In some alternative implementations, a notification module 804 is also included, for:

[0161] The operation and maintenance message, the anomaly information, the target anomaly type, and the correction method are notified through a preset notification method.

[0162] Since this device is the same as the device in the method of this application embodiment, and the principle of the device in solving the problem is similar to that of the method, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be described again.

[0163] Based on the same technical concept, this application also provides an electronic device 900, such as... Figure 9 As shown, it includes at least one processor 901 and a memory 902 connected to at least one processor. In this embodiment, the specific connection medium between the processor 901 and the memory 902 is not limited. Figure 9 Taking the connection between processor 901 and memory 902 via bus 903 as an example, the bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, Figure 9 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0164] The processor 901 is the control center of the electronic device, capable of connecting various parts of the device via various interfaces and lines. It performs data processing by running or executing instructions stored in the memory 902 and retrieving data stored in the memory 902. Optionally, the processor 901 may include one or more processing units. The processor 901 may integrate an application processor and a modem processor. The application processor primarily handles the operating system, user interface, and applications, while the modem processor primarily handles issuing instructions. It is understood that the modem processor may not be integrated into the processor 901. In some embodiments, the processor 901 and the memory 902 may be implemented on the same chip; in other embodiments, they may be implemented on separate chips.

[0165] The processor 901 can be a general-purpose processor, such as a central processing unit (CPU), digital signal processor, application-specific integrated circuit (ASIC), field-programmable gate array (FPGA), or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of the operation and maintenance anomaly handling method can be directly manifested as being executed by a hardware processor, or being executed by a combination of hardware and software modules within the processor.

[0166] Memory 902, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. Memory 902 may include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic storage, magnetic disk, optical disk, etc. Memory 902 can be any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer, but is not limited thereto. In the embodiments of this application, memory 902 can also be a circuit or any other device capable of implementing storage functions for storing program instructions and / or data.

[0167] In this embodiment, the memory 902 stores a computer program, which, when executed by the processor 901, causes the processor 901 to perform the following:

[0168] For any abnormal information in the operation and maintenance message, determine the key information corresponding to the abnormal information;

[0169] Based on the abnormal information and the key information, determine the target fit between the abnormal information and the preset abnormal type;

[0170] Based on the target fit, a target anomaly type is selected from the preset anomaly types, and the anomaly information is corrected using the correction method corresponding to the target anomaly type.

[0171] In some optional implementations, processor 901 specifically performs:

[0172] Determine the adjacent information of the abnormal information in the operation and maintenance message;

[0173] The key information representing anomalous content is determined through NLP; wherein, the anomalous content includes the anomalous information and the adjacent information.

[0174] In some optional implementations, processor 901 specifically performs:

[0175] Feature extraction is performed on the abnormal information and the key information at each level to obtain the target features of the abnormal information at each level;

[0176] For any level, determine the fit between the target feature of the level and the preset feature of the preset anomaly type at the level;

[0177] For any preset anomaly type, the second fitting degree of the preset anomaly type is adjusted based on the first fitting degree of the preset anomaly type to obtain the target fitting degree between the anomaly information and the preset anomaly type; wherein, the first fitting degree is the fitting degree between the target feature at the nth level and the preset feature of the preset anomaly type at the nth level, and the second fitting degree is the fitting degree between the target feature at the Nth level and the preset feature of the preset anomaly type at the Nth level, n≤N-1, and N is the total number of levels.

[0178] In some optional implementations, processor 901 specifically performs:

[0179] Determine the weight coefficients corresponding to the first degree of fit of the preset anomaly type;

[0180] The second fit of the preset anomaly type is adjusted based on the weighting coefficient to obtain the target fit between the anomaly information and the preset anomaly type.

[0181] In some optional implementations, processor 901 specifically performs:

[0182] Sort all preset anomaly types in descending order of target fit.

[0183] If the verification result of the first correction result based on the first verification method is a successful verification, then the first preset anomaly type in the sorting result is determined as the target anomaly type; wherein, the first verification method is the verification method corresponding to the first preset anomaly type, and the first correction result is obtained by correcting the anomaly information through the correction method corresponding to the first preset anomaly type;

[0184] Otherwise, the m-th preset anomaly type in the sorting results is determined as the target anomaly type; wherein, the verification result of verifying the i-th correction result based on the i-th verification method is verification failure, the i-th verification method is the verification method corresponding to the i-th preset anomaly type, and the i-th correction result is obtained by correcting the anomaly information through the correction method corresponding to the i-th preset anomaly type; and the verification result of verifying the m-th correction result based on the m-th verification method is verification success, the m-th verification method is the verification method corresponding to the m-th preset anomaly type, and the m-th correction result is obtained by correcting the anomaly information through the correction method corresponding to the m-th preset anomaly type; i < m.

[0185] In some alternative implementations, processor 901 also performs:

[0186] The operation and maintenance message, the anomaly information, the target anomaly type, and the correction method are notified through a preset notification method.

[0187] Since the electronic device is the same as the electronic device in the method of this application embodiment, and the principle of the electronic device in solving the problem is similar to that of the method, the implementation of the electronic device can refer to the implementation of the method, and the repeated parts will not be described again.

[0188] Based on the same technical concept, embodiments of this application also provide a computer-readable storage medium storing a computer program executable by a computer, which, when run on the computer, causes the computer to perform the steps of the above-described operation and maintenance anomaly handling method.

[0189] In some alternative implementations, various aspects of the operation and maintenance anomaly handling method provided in this application can also be implemented as a program product containing computer-executable instructions. When the program product is run on a computer device, the computer-executable instructions are used to cause the computer device to perform the steps of the operation and maintenance anomaly handling method according to various exemplary embodiments of this application described above.

[0190] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0191] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0192] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0193] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0194] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0195] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for handling operational and maintenance anomalies, characterized in that, The method includes: For any abnormal information in the operation and maintenance message, determine the key information corresponding to the abnormal information; Feature extraction is performed on the abnormal information and the key information at each level to obtain the target features of the abnormal information at each level; For any level, determine the fit between the target feature of the level and the preset feature of the preset anomaly type at the level; For any preset anomaly type, based on the correspondence of the preset anomaly type at the level, the weight coefficient corresponding to the first fit of each preset anomaly type at the level is determined; the correspondence of the levels includes: the correspondence between the first fit and the weight coefficient at the level. The product of all weight coefficients corresponding to the preset anomaly type and the second degree of fit is determined as the target degree of fit between the anomaly information and the preset anomaly type. Wherein, the first fitting degree is the fitting degree between the target feature at the nth level and the preset feature of the preset anomaly type at the nth level, and the second fitting degree is the fitting degree between the target feature at the Nth level and the preset feature of the preset anomaly type at the Nth level, n≤N-1, and N is the total number of levels. Based on the target fit, a target anomaly type is selected from the preset anomaly types, and the anomaly information is corrected using the correction method corresponding to the target anomaly type.

2. The method as described in claim 1, characterized in that, The key information corresponding to the abnormal information includes: Determine the adjacent information of the abnormal information in the operation and maintenance message; The key information representing anomalous content is determined using Neuro-Linguistic Programming (NLP); wherein, the anomalous content includes the anomalous information and the adjacent information.

3. The method as described in claim 1, characterized in that, Selecting a target anomaly type from the preset anomaly types based on the target fit includes: Sort all preset anomaly types in descending order of target fit. If the verification result of the first correction result based on the first verification method is a successful verification, then the first preset anomaly type in the sorting result is determined as the target anomaly type; wherein, the first verification method is the verification method corresponding to the first preset anomaly type, and the first correction result is obtained by correcting the anomaly information through the correction method corresponding to the first preset anomaly type; Otherwise, the m-th preset anomaly type in the sorting results is determined as the target anomaly type; wherein, the verification result of verifying the i-th correction result based on the i-th verification method is verification failure, the i-th verification method is the verification method corresponding to the i-th preset anomaly type, and the i-th correction result is obtained by correcting the anomaly information through the correction method corresponding to the i-th preset anomaly type; and the verification result of verifying the m-th correction result based on the m-th verification method is verification success, the m-th verification method is the verification method corresponding to the m-th preset anomaly type, and the m-th correction result is obtained by correcting the anomaly information through the correction method corresponding to the m-th preset anomaly type; i < m.

4. The method according to any one of claims 1 to 3, characterized in that, Also includes: The operation and maintenance message, the anomaly information, the target anomaly type, and the correction method are notified through a preset notification method.

5. A device for handling operational and maintenance anomalies, characterized in that, The device includes: The key information determination module is used to determine the key information corresponding to any abnormal information in the operation and maintenance message; The goodness-of-fit determination module is used to determine the target goodness-of-fit between the abnormal information and the preset abnormality type based on the abnormal information and the key information. The correction module is used to select a target anomaly type from the preset anomaly types based on the target fit degree, and correct the anomaly information through the correction method corresponding to the target anomaly type; The fitting degree determination module is specifically used for: Feature extraction is performed on the abnormal information and the key information at each level to obtain the target features of the abnormal information at each level; For any level, determine the fit between the target feature of the level and the preset feature of the preset anomaly type at the level; For any preset anomaly type, based on the correspondence of the preset anomaly type at the level, the weight coefficient corresponding to the first fit of each preset anomaly type at the level is determined; the correspondence of the levels includes: the correspondence between the first fit and the weight coefficient at the level. The product of all weight coefficients corresponding to the preset anomaly type and the second fitting degree is determined as the target fitting degree between the anomaly information and the preset anomaly type; wherein, the first fitting degree is the fitting degree between the target feature at the nth level and the preset feature of the preset anomaly type at the nth level, and the second fitting degree is the fitting degree between the target feature at the Nth level and the preset feature of the preset anomaly type at the Nth level, n≤N-1, and N is the total number of levels.

6. The apparatus as claimed in claim 5, characterized in that, The key information determination module is specifically used for: Determine the adjacent information of the abnormal information in the operation and maintenance message; The key information representing anomalous content is determined through NLP; wherein, the anomalous content includes the anomalous information and the adjacent information.

7. The apparatus as claimed in claim 5, characterized in that, The correction module is specifically used for: Sort all preset anomaly types in descending order of target fit. If the verification result of the first correction result based on the first verification method is a successful verification, then the first preset anomaly type in the sorting result is determined as the target anomaly type; wherein, the first verification method is the verification method corresponding to the first preset anomaly type, and the first correction result is obtained by correcting the anomaly information through the correction method corresponding to the first preset anomaly type; Otherwise, the m-th preset anomaly type in the sorting results is determined as the target anomaly type; wherein, the verification result of verifying the i-th correction result based on the i-th verification method is verification failure, the i-th verification method is the verification method corresponding to the i-th preset anomaly type, and the i-th correction result is obtained by correcting the anomaly information through the correction method corresponding to the i-th preset anomaly type; and the verification result of verifying the m-th correction result based on the m-th verification method is verification success, the m-th verification method is the verification method corresponding to the m-th preset anomaly type, and the m-th correction result is obtained by correcting the anomaly information through the correction method corresponding to the m-th preset anomaly type; i < m.

8. The apparatus according to any one of claims 5 to 7, characterized in that, It also includes a notification module for: The operation and maintenance message, the anomaly information, the target anomaly type, and the correction method are notified through a preset notification method.

9. An electronic device, characterized in that, It includes at least one processor and at least one memory, wherein the memory stores a computer program that, when executed by the processor, causes the processor to perform the method as described in any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, It stores a computer program executable by a computer, which, when run on the computer, causes the computer to perform the method as described in any one of claims 1 to 4.

11. A computer program product, characterized in that, It includes computer-executable instructions for causing a computer to perform the method as described in any one of claims 1 to 4.

Images