Intelligent operation and maintenance method, system and device and storage medium

Abstract

The invention relates to an intelligent operation and maintenance method applied to an operation and maintenance platform, and the method comprises the steps: obtaining the operation data of a to-be-tested device; judging whether the to-be-tested equipment is abnormal or not based on the operation data, and if the to-be-tested equipment is abnormal, determining the operation data as to-be-tested fault data; inputting the to-be-detected fault data into a pre-trained fault analysis model, and outputting a target processing report corresponding to the to-be-detected fault data, the fault analysis model comprises a fault detection module for performing fault type detection on to-be-detected fault data, a retrieval module for retrieving a target solution corresponding to the to-be-detected fault data from a preset operation and maintenance knowledge base, and a scheme generation module for generating a corresponding target processing scheme according to the to-be-detected fault data; and sending the target processing report to a management terminal corresponding to the to-be-tested device. The problems that in the prior art, an intelligent operation and maintenance system excessively depends on manual processing and experience judgment, so that the fault processing efficiency is low, the response speed is low, and the error rate is high are solved.

Description

Technical Field

[0001] The present application relates to the field of intelligent operation and maintenance technology, and in particular to an intelligent operation and maintenance method, system, device and storage medium. Background Art

[0002] With the rapid development of information technology and the increasing complexity of enterprise business, operation and maintenance, as a key link to ensure the stable operation of enterprise information management systems, has become increasingly important. Intelligent operation and maintenance systems apply deep learning, machine learning or other big data analysis technologies in operation and maintenance tasks to improve the intelligence level of operation and maintenance systems. However, the intelligence level of intelligent operation and maintenance systems in related technologies is limited.

[0003] The traditional operation and maintenance system has the following defects:

[0004] 1. In traditional operation and maintenance systems, fault identification relies on the experience and manual analysis of operation and maintenance personnel, which leads to low efficiency and easy omission of problems;

[0005] 2. Different types of faults require different processing steps. Manual processing is prone to errors and time-consuming.

[0006] 3. When troubleshooting, maintenance personnel need to search for a large number of documents and records, and the information retrieval efficiency is low, which affects the troubleshooting speed;

[0007] 4. It is difficult to accumulate and share fault handling experience in a systematic and standardized manner, resulting in slow growth of novice operation and maintenance personnel. Summary of the invention

[0008] The present application provides an intelligent operation and maintenance method, system, device and storage medium to solve the problem in the prior art that the intelligent operation and maintenance system relies too much on manual processing and experience judgment, resulting in low efficiency in handling faults, slow response speed and high error rate.

[0009] In a first aspect, the present application provides an intelligent operation and maintenance method, which is applied to an operation and maintenance platform, and the method comprises:

[0010] Obtain the operating data of the device under test;

[0011] Determine whether the device under test has an abnormality based on the operating data, and if the device under test has an abnormality, determine the operating data as fault data to be tested;

[0012] The fault data to be tested is input into a pre-trained fault analysis model, and a target processing report corresponding to the fault data to be tested is output, wherein the pre-trained fault analysis model includes a fault detection module for detecting the fault type of the fault data to be tested, a retrieval module for retrieving the target solution corresponding to the fault data to be tested from a preset operation and maintenance knowledge base, and a solution generation module for generating a corresponding target processing solution according to the fault data to be tested;

[0013] The target processing report is sent to the management terminal corresponding to the device under test.

[0014] In a second aspect, the present application provides an intelligent operation and maintenance system, the system comprising: an operation and maintenance platform, a device under test, and a management terminal corresponding to the device under test;

[0015] The operation and maintenance platform is used to obtain the operation data of the equipment under test, analyze the operation data to form a corresponding target processing report, and send the target processing report to the management terminal corresponding to the equipment under test;

[0016] The equipment under test is connected to the operation and maintenance platform and transmits the operation data to the operation and maintenance platform in real time;

[0017] The management terminal is used to receive the target processing report sent by the operation and maintenance platform, and send the processing result of the target processing report to the operation and maintenance platform in response to the user's input.

[0018] In a third aspect, the present application provides an intelligent operation and maintenance device, the device comprising:

[0019] A data acquisition module is used to obtain the operating data of the device under test;

[0020] a fault determination module, configured to determine whether the device under test has an abnormality based on the operation data, and if the device under test has an abnormality, determine the operation data as the fault data under test;

[0021] A report determination module, used to input the fault data to be tested into a pre-trained fault analysis model, and output a target processing report corresponding to the fault data to be tested, wherein the pre-trained fault analysis model includes a fault detection module for detecting the fault type of the fault data to be tested, a retrieval module for retrieving the target solution corresponding to the fault data to be tested from a preset operation and maintenance knowledge base, and a solution generation module for generating a corresponding target processing solution according to the fault data to be tested;

[0022] The report sending module is used to send the target processing report to the management terminal corresponding to the device under test.

[0023] In a fourth aspect, the present application also provides a computer storage medium storing computer executable instructions, wherein the computer executable instructions are used to execute the intelligent operation and maintenance method described in any one of the above items of the present application.

[0024] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: the method provided by the embodiment of the present application obtains the operating data of the device under test in real time, and determines whether there is an abnormality in the operation of the device under test by analyzing the operating data. If there is an abnormality, the operating data with the abnormality is determined as the fault data to be tested. The fault data to be tested can be all the operating data, or data with abnormalities extracted from the operating data. The abnormal data is then input into a pre-trained fault analysis model, and the pre-trained fault analysis model analyzes the abnormal data. The fault data to be tested is analyzed by the fault detection module of the fault analysis model to obtain the fault data to be tested. The fault type corresponding to the target fault type of the fault data is determined; the fault analysis model pre-stores at least one historical fault type and the historical solution corresponding to the historical fault type in the preset operation and maintenance knowledge base, and the retrieval module searches and matches the target solution corresponding to the fault data to be tested in the preset operation and maintenance knowledge base; the solution generation module of the fault analysis model analyzes the fault data to be tested to generate the corresponding target processing solution, and then generates the corresponding target processing report in combination with the target fault type, the target solution and the target processing solution, and then sends the target processing report to the management terminal of the device to be tested, so that the operation and maintenance personnel can process the abnormality of the device to be tested according to the target processing report. By analyzing the fault data to be tested, the corresponding target fault type, the target solution retrieved from the preset operation and maintenance knowledge base, and the target processing solution generated according to the analysis of the fault data to be tested are determined, so as to obtain the target processing report corresponding to the fault data to be tested. When the target processing report is sent to the management terminal, the operation and maintenance personnel can clearly understand what the fault data to be tested corresponding to the abnormality is, and can process the abnormality of the device to be tested according to the target processing solution and the target solution, without formulating solutions, querying information, etc., thereby improving the efficiency and response rate of fault processing while ensuring accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0026] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0027] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0028] Figure 1 A schematic diagram of the architecture of an intelligent operation and maintenance system provided in an embodiment of the present application;

[0029] Figure 2 A flowchart of an intelligent operation and maintenance method provided in an embodiment of the present application;

[0030] Figure 3 A flowchart of an intelligent operation and maintenance method provided in an embodiment of the present application;

[0031] Figure 4 A flowchart of an intelligent operation and maintenance method provided in an embodiment of the present application;

[0032] Figure 5 A schematic diagram of the structure of an intelligent operation and maintenance device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0034] The disclosure below provides many different embodiments or examples to implement different structures of the present invention. In order to simplify the disclosure of the present invention, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present invention. In addition, the present invention can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.

[0035] In order to solve the technical problems in the prior art that the intelligent operation and maintenance system relies too much on manual processing and experience judgment, resulting in low efficiency in fault handling, slow response speed and high error rate, the present application provides an intelligent operation and maintenance method that can improve the fault handling efficiency and response speed and ensure the accuracy of fault handling.

[0036] Figure 1A structural schematic diagram of an intelligent operation and maintenance system is provided for an embodiment of the present application. As shown in the figure, the intelligent operation and maintenance system includes an operation and maintenance platform, a device under test, and a management terminal corresponding to the device under test; the operation and maintenance platform is used to obtain the operation data of the device under test, analyze the operation data to form a corresponding target processing report, and send the target processing report to the management terminal corresponding to the device under test; the device under test is connected to the operation and maintenance platform in communication, and transmits the operation data to the operation and maintenance platform in real time; the management terminal is used to receive the target processing report sent by the operation and maintenance platform, and send the processing result of the target processing report to the operation and maintenance platform in response to the user's input.

[0037] In an embodiment of the present application, the device under test communicates with the operation and maintenance platform in real time. The communication method can be wired communication or wireless communication. The device under test transmits the operation data to the operation and maintenance platform in real time during operation. The operation and maintenance platform analyzes the operation data of the device under test to determine whether there is an abnormality in the operation data. When there is an abnormality, it indicates that the current device under test has a fault. The operation data with the abnormality is determined as the fault data to be tested, and then the fault data to be tested is input into a pre-trained fault analysis model. The pre-trained fault analysis model includes a fault detection module, a retrieval module and a solution generation module. The fault detection module analyzes the fault data to be tested to determine the target fault type of the fault data to be tested. In the process of fault type analysis, the target fault type can be determined by matching in a preset operation and maintenance knowledge base, or the corresponding target fault type can be determined by analyzing the data type of the fault data to be tested; the retrieval module is used to search in a preset The target solution corresponding to the fault data to be tested is determined by searching the operation and maintenance knowledge base. When searching, the retrieval module can use the historical solution corresponding to the target fault type in the preset operation and maintenance knowledge base as the target solution, or determine the target solution by matching the fault data to be tested with the historical solution; the solution generation module generates the corresponding target processing solution by analyzing the fault data to be tested. When the target fault type and the target solution are determined in the preset operation and maintenance knowledge base through the fault detection module and the retrieval module, the target processing solution generated by the solution generation module may be the same as or similar to the target solution; the pre-trained fault analysis model combines the target fault type, the target solution and the target processing solution to generate a target processing report corresponding to the fault data to be tested, and then sends the target processing report to the management terminal corresponding to the device to be tested, so that the operation and maintenance personnel can handle the abnormality of the device to be tested according to the target processing report of the management terminal.

[0038] The target processing report at least includes the fault data to be tested, the target fault type corresponding to the fault data to be tested, the target solution and target processing plan, and the identification code of the device to be tested corresponding to the fault data to be tested. The operation and maintenance personnel locate the device to be tested according to the identification code of the device to be tested, and then use the target solution and target processing plan in the target processing report to handle the fault of the device to be tested. The target solution and target processing plan include the operation steps for handling the exception, etc. This allows the operation and maintenance personnel to deal with the exception without having to formulate a processing plan after receiving the exception, and to spend time looking for information during the processing of the solution, which speeds up the efficiency and response time of fault handling. At the same time, the processing report is generated in combination with historical fault types and historical solutions, which can improve the accuracy of fault handling.

[0039] Figure 2 The following is a flow chart of an intelligent operation and maintenance method provided in an embodiment of the present application. Figure 2 As shown, the method comprises at least the following steps:

[0040] S101, obtaining operation data of the device under test.

[0041] In an embodiment of the present application, the device under test is communicatively connected to the operation and maintenance platform, and the device under test transmits operation data to the operation and maintenance platform in real time during operation, so that the operation and maintenance platform can monitor the operating status of the device under test.

[0042] Among them, the devices under test may include cloud servers, smart interactive tablets, mobile phones, tablets, laptops, desktop computers, all-in-one computers, in-vehicle media, server workstations or production equipment, etc.

[0043] Operation data includes but is not limited to system and application logs, monitoring data, alarm information, CPU usage, memory usage, hard disk read and write speeds, temperature sensor data, network traffic, bandwidth utilization, network latency and packet loss rate, application response time, request processing time, number of concurrent users, query response time, number of database connections, index usage; including alarm level, alarm time and detailed description of alarm information, recording system and application configuration parameters, etc.

[0044] The data transmission between the device under test and the operation and maintenance platform can be the operation data directly transmitted to the operation and maintenance platform. In order to reduce the processing matters of the operation and maintenance platform and speed up the processing efficiency of the operation and maintenance platform, the monitoring of the operation data of the device under test can be achieved by installing a data monitoring device between the operation and maintenance platform and the device under test. The data monitoring device can be a log collector such as Filebeat, a monitoring tool such as Prometheus, etc.

[0045] S102, judging whether the device under test has an abnormality based on the operation data, and if the device under test has an abnormality, determining the operation data as fault data to be tested.

[0046] In an embodiment of the present application, after receiving the operating data of the device under test, the operation and maintenance platform compares and analyzes the operating data of the device under test with the corresponding data generated during normal operation, so as to determine whether there is an abnormality in the operating data of the device under test. If there is an abnormality, it means that the device under test corresponding to the operating data may currently be in a fault state, and the operating data with the abnormality is determined as the fault data under test, so as to analyze and process the fault of the device under test.

[0047] Among them, the operation data can be the data transmitted to the operation and maintenance platform in real time during the operation of the equipment under test, or it can be the description of the abnormalities in the operation of the equipment under test that the operation and maintenance personnel find problems in the process of monitoring the equipment under test and feedback to the operation and maintenance platform through the mobile terminal or management terminal.

[0048] Among them, before performing abnormal analysis on the operating data, the operating data of the equipment under test can be pre-processed through data cleaning, data integration, data transformation, data reduction, etc., and the integrity and accuracy of the data can be ensured by processing missing values, abnormal values, etc. in the operating data; the data from multiple data sources are merged into a unified data storage to solve the entity recognition problem and attribute redundancy problem; the data is standardized, such as standardization and normalization, to meet different data analysis needs. On the premise of maintaining data integrity, the scale of data can be reduced and the efficiency of data analysis can be improved.

[0049] It is easy to imagine that when an abnormality is detected in the operating data of the device under test, the abnormal data can be extracted as the fault data under test, and the operating data containing the abnormality can also be used as the fault data under test for subsequent processing.

[0050] S103, input the fault data to be tested into the pre-trained fault analysis model, and output a target processing report corresponding to the fault data to be tested. The pre-trained fault analysis model includes a fault detection module for detecting the fault type of the fault data to be tested to obtain a target fault type corresponding to the fault data to be tested, a retrieval module for retrieving a target solution corresponding to the fault data to be tested from a preset operation and maintenance knowledge base, and a solution generation module for generating a corresponding target processing solution according to the fault data to be tested.

[0051] In an embodiment of the present application, the fault data to be tested is input into a pre-trained fault analysis model, and the pre-trained fault analysis model analyzes and processes the fault data to be tested to obtain a target processing report corresponding to the fault data to be tested. The pre-trained fault processing model includes a fault detection module, a retrieval module and a solution generation module. After the fault data to be tested is input into the pre-trained fault analysis model, the fault data to be tested is detected by the fault detection module to obtain the target fault data to be tested corresponding to the fault data to be tested, and the retrieval module is used to search in a preset operation and maintenance knowledge base to match the historical solutions corresponding to the fault data to be tested, and the corresponding historical solutions are used as the target solutions corresponding to the fault data to be tested, and the anomalies corresponding to the fault data to be tested are processed according to the target solutions; the fault data to be tested is analyzed by the solution generation module and a corresponding target processing solution is generated.

[0052] The target solution is a historical solution corresponding to historical fault data related to or similar to the fault data to be tested, determined by the retrieval module through retrieval and matching in a preset operation and maintenance knowledge base according to the fault data to be tested.

[0053] The target processing solution is that the solution generation module in the fault analysis model analyzes the fault data to be tested, determines the source of the fault data to be tested, determines the possible cause of the fault data to be tested, and thus determines the fault type corresponding to the fault data to be tested, thereby generating the corresponding target processing solution according to the fault type. The target processing solution can be to query the N historical solutions with the highest similarity in the preset operation and maintenance knowledge base, or it can be to clean, integrate, and mine the data through data mining and machine learning technology during the training process of the fault analysis model, and use algorithms to learn from the data to build a prediction model, and generate the target processing solution corresponding to the fault data to be tested through the prediction model of the prediction analysis of the data to be tested.

[0054] When the solution generation module generates a target processing solution based on the fault data to be tested, if relevant or similar historical fault data is retrieved from the preset operation and maintenance knowledge base, the historical data is determined as the target processing solution.

[0055] Before the fault analysis model is used, it needs to be trained so that when it is used, it can analyze the fault type corresponding to the fault data under test and the corresponding solution and processing plan according to the fault data under test of the device under test, such as Figure 3The pre-training method shown includes: S001, obtaining sample training data, the sample training data including sample operation data and the fault type and solution corresponding to the sample operation data; S002, inputting the sample training data into the fault analysis model to obtain a processing report corresponding to the sample training data; S003, judging whether the processing report satisfies the preset constraint conditions, if so, obtaining a fault analysis model that has completed the training, if not, obtaining the next sample training data, and executing the step of inputting the sample training data into the fault analysis model.

[0056] In an embodiment of the present application, sample training data is input into a fault analysis model, wherein the sample training data includes sample operation data and the fault type and solution corresponding to the sample operation data, and the sample operation data is used as the input of the fault analysis model, and the fault type and solution are used as the output of the sample to train the fault analysis model. During training, the output of the fault analysis model is compared with the preset fault type and solution to determine whether the preset constraints are met. If so, the training is completed to obtain a pre-trained fault analysis model. If not, the next sample operation data is input into the fault analysis model until the processing report output by the fault analysis model meets the preset constraints.

[0057] Among them, the preset constraint condition can be to calculate the loss function of the fault type and solution in the processing report output by the fault analysis model and the preset fault type and solution. If the calculated loss function is less than or equal to the preset loss function threshold, the preset constraint condition is met and the training of the fault analysis model is completed; if the calculated loss function is greater than the preset loss function threshold, the preset constraint condition is not met, and it is necessary to continue to input sample training data into the fault analysis model to train the model.

[0058] For example, the specific training process is as follows: collect and annotate the fault data to be tested related to operation and maintenance, including logs, error messages, fault descriptions, etc.; convert text data into a format that BERT can process, including tokenization, adding special tags (such as [CLS], [SEP]) and generating input masks; use BERT's tokenizer to tokenize the text data and generate the corresponding input ID, input mask and segment ID; send the processed input data to the pre-trained BERT model to obtain the hidden vector representation of each tag; use BERT to add a classification task, which can add a fully connected layer and a Softmax layer on the [CLS] tag for fault type prediction; use the annotated data for fine-tuning, and adjust the model parameters through the cross entropy loss function and the Adam optimizer. Evaluate the model performance on the validation set and test set, adjust the hyperparameters, and ensure the generalization ability of the model.

[0059] Failure types include but are not limited to hardware failures: hard disk failure, memory failure, CPU overheating; software failures: application crash, memory leak, deadlock; network failures: network delay, network interruption, insufficient bandwidth; security failures: unauthorized access, data leakage, malware infection; performance failures: system overload, long response time, excessive resource utilization; configuration failures: configuration errors, improper parameter settings, version incompatibility, etc.

[0060] The solution is to generate detailed processing suggestions for the current fault data to be tested based on the identification results of the fault analysis mode. The suggestions should include clear operating steps and precautions.

[0061] Here is an example:

[0062] Confirm the problem: Check the system logs and monitoring data to confirm whether there is a memory leak.

[0063] Restart Application: Restart the application that caused the memory leak.

[0064] Fix memory leaks: Locate and fix memory leaks in your application.

[0065] Monitor system: Continue to monitor system performance after restart to ensure that the problem is resolved.

[0066] S104: Send the target processing report to the management terminal corresponding to the device under test.

[0067] In an embodiment of the present application, a target processing report including the fault data to be tested, the target fault type and the target solution and the target processing solution is sent to the management terminal of the device to be tested, so that the operation and maintenance personnel can promptly discover the fault of the device to be tested and handle it in time according to the target processing report, thereby ensuring that the device to be tested can operate normally.

[0068] In an embodiment of the present application, the operation data of the device under test is acquired in real time, and the operation data is analyzed to determine whether there is an abnormality in the operation of the device under test. If there is an abnormality, the operation data with the abnormality is determined as the fault data under test. The fault data under test can be all the operation data, or the data with the abnormality extracted from the operation data. Then, the abnormal data is input into the pre-trained fault analysis model, and the pre-trained fault analysis model analyzes the abnormal data. The fault type corresponding to the target fault type corresponding to the fault data under test is determined by analyzing the fault data under test through the fault detection module of the fault analysis model; the fault analysis model pre-stores at least one historical fault type and the historical solution corresponding to the historical fault type in the preset operation and maintenance knowledge base, and the retrieval module searches and matches the target solution corresponding to the fault data under test in the preset operation and maintenance knowledge base; the solution generation module of the fault analysis model analyzes the fault data under test to generate a corresponding target processing solution, and then generates a corresponding target processing report in combination with the target fault type, the target solution and the target processing solution, and then sends the target processing report to the management terminal of the device under test so that the operation and maintenance personnel can process the abnormality of the device under test according to the target processing report. By analyzing the fault data to be tested, the corresponding target fault type, the target solution retrieved from the preset operation and maintenance knowledge base, and the target processing solution generated according to the analysis of the fault data to be tested are determined, so as to obtain a target processing report corresponding to the fault data to be tested. When the target processing report is sent to the management terminal, the operation and maintenance personnel can clearly understand what the fault data to be tested corresponds to the abnormality that has occurred, and can handle the abnormality of the equipment to be tested according to the target processing solution and the target solution, without the need to formulate solutions, query data, etc., thereby improving the efficiency and response rate of fault handling while ensuring accuracy.

[0069] like Figure 4 As shown, a flowchart of an intelligent method is provided for an embodiment of the present application. Figure 4 As shown, the method comprises at least the following steps:

[0070] S201, obtaining operation data of the device under test.

[0071] The specific implementation of this step can refer to step S101 and will not be described in detail here.

[0072] S202, determining whether the device to be tested has an abnormality based on the operating data, and if the device to be tested has an abnormality, determining the operating data corresponding to the abnormality as the fault data to be tested.

[0073] The specific implementation of this step can refer to step S102 and will not be described in detail here.

[0074] S203, input the fault data to be tested into the pre-trained fault analysis model, obtain the target fault type corresponding to the fault data to be tested based on the fault detection module, obtain the target solution corresponding to the fault data to be tested based on the retrieval module, and obtain the target processing solution corresponding to the fault data to be tested based on the solution generation module.

[0075] In an embodiment of the present application, the fault data to be tested is input into a fault analysis model, and the fault detection module of the fault analysis model performs analysis and detection to obtain a target fault type corresponding to the fault data to be tested, and the retrieval module performs search and analysis to obtain a target solution corresponding to the fault data to be tested, and the solution generation module performs analysis on the fault data to be tested to determine the source of the fault data to be tested, etc., thereby determining the type of the fault data to be tested, and then generating a target processing solution corresponding to the fault data to be tested.

[0076] The method for a fault detection module to determine the fault type corresponding to the fault data to be tested includes: obtaining the fault vector to be tested corresponding to the fault data to be tested, and obtaining the historical type vectors corresponding to each historical fault type in a preset knowledge base; calculating the similarity between the fault vector to be tested and each of the historical type vectors, and obtaining the first similarity to be tested corresponding to each fault vector to be tested; comparing each of the first similarities to be tested with a preset type similarity threshold, and determining the first similarity to be tested that is greater than or equal to the preset type similarity threshold as the first target similarity, and determining the historical fault type corresponding to the first target similarity as the target fault type of the fault data to be tested.

[0077] In the embodiment of the present application, the fault data to be tested is generated with the corresponding fault vector to be tested by using the natural language processing technology, and each historical fault type in the preset operation and maintenance knowledge base is obtained by using the natural language processing technology through the corresponding historical type vector, and the first similarity to be tested between the fault data to be tested and the historical type vector is calculated, and the first similarity to be tested is compared with the preset type similarity threshold to determine the similarity between the fault data to be tested and the historical fault type. When the first similarity to be tested between the data vector to be tested and the historical type vector is greater than or equal to the preset type similarity threshold, the historical fault type corresponding to the first similarity to be tested is determined as the target fault type corresponding to the fault data to be tested.

[0078] When each first similarity to be tested is less than the preset type similarity threshold, it is determined by the data type, data source and other data of the fault data to be tested, and then the target fault type of the fault data to be tested is determined according to the data type, data source and other data of the fault data to be tested. At this time, the target fault type can be a newly defined fault type, or it can be a target fault data type determined according to the historical fault data types and sources of historical fault data in the preset operation and maintenance knowledge base.

[0079] Among them, when comparing the first similarity to be tested with the preset type similarity threshold, the historical fault types corresponding to the first similarity to be tested that is greater than or equal to the preset type similarity threshold can be determined as target fault types, and the similarities between the first similarity to be tested and the preset type similarity threshold can be sorted, and M target fault types with higher similarity are determined from the target historical fault types, where M is an integer greater than or equal to 1.

[0080] It can be understood that historical fault types correspond to historical fault data. Therefore, the historical type vector contains historical fault types and historical fault data corresponding to the historical fault types. When calculating the similarity between the fault vector to be tested and the historical type vector, the similarity between the data vector to be tested and the vector corresponding to the historical fault data is also included.

[0081] It can be understood that between historical fault data, one historical data may correspond to one historical fault type, one historical fault data may correspond to multiple historical fault types, multiple historical fault data may correspond to one historical fault type, or multiple historical fault data may correspond to multiple historical fault types.

[0082] The method for a retrieval module to determine the fault type corresponding to the fault data to be tested includes: when the first similarity to be tested is greater than or equal to a preset type similarity threshold, determining the historical solution corresponding to the target fault type as the target solution corresponding to the fault data to be tested; when the first similarity to be tested is less than the preset type similarity threshold, obtaining the historical solution vectors of each historical solution in a preset operation and maintenance knowledge base; calculating the second similarity to be tested between the fault vector to be tested and each of the historical solution vectors; sorting the second similarities to be tested corresponding to each historical solution in order from large to small, and determining the target solution corresponding to the fault data to be tested with the historical solutions corresponding to the first N second similarities to be tested, wherein N is greater than or equal to 1.

[0083] In an embodiment of the present application, when the first similarity to be tested is greater than or equal to a preset type similarity threshold, the historical solution corresponding to the historical fault type corresponding to the first similarity to be tested can be determined as the target solution corresponding to the fault data to be tested, without the need to traverse and match with each historical solution in the preset operation and maintenance knowledge base, thereby saving the analysis time of the fault data to be tested; when the first similarity to be tested is less than the preset type similarity threshold, it indicates that there is no historical fault type similar to the fault data to be tested in the historical fault type. At this time, it can be determined from the historical solutions whether there is a historical solution related to the fault data to be tested, and the historical solution vector corresponding to each historical solution in the preset operation and maintenance knowledge base can be obtained by using natural language processing technology, and then the second similarity to be tested between the data vector to be tested and the historical solution vector is calculated, and the second similarity to be tested is compared with the preset solution similarity threshold to determine whether there is a solution corresponding to the fault data to be tested in the historical solution. If the second similarity to be tested is greater than or equal to the preset solution similarity threshold, the historical solution corresponding to the second similarity to be tested is determined as the target solution corresponding to the fault data to be tested. The fault data to be tested is traversed and searched with the historical fault types and historical solutions in the preset operation and maintenance knowledge base, so as to quickly determine the target solution corresponding to the fault data to be tested, save the analysis and processing time of the fault data to be tested, and quickly respond to the fault of the equipment to be tested.

[0084] Among them, in the process of traversing and searching for historical solutions corresponding to the fault data to be tested in the preset operation and maintenance knowledge base, the N historical fault types with the highest similarity in the traversal results can be determined as target solutions, so that historical solutions with higher similarity can be quickly determined, and the faults corresponding to the fault data to be tested can be processed in combination with the historical solutions.

[0085] In the process of processing the fault data to be tested, historical fault types and historical solutions to obtain corresponding vectors, preprocessing is first performed, including removal of stop words, tokenization, word form restoration, etc. In the process of searching for target fault types and target solutions in the preset operation and maintenance knowledge base, search engine technology such as Elasticsearch can be used for fast retrieval.

[0086] The process of vectorizing the fault data to be tested includes converting keywords such as "increased network delay", "check network configuration", "routing table settings" into vectors, calculating the similarity between these vectors and the vectors of existing network fault handling documents in the knowledge base, retrieving the documents most similar to these query vectors, for example, an article on how to diagnose and solve network delay problems, sorting related documents by similarity, and recommending the most relevant solutions to operation and maintenance personnel.

[0087] S2041, matching the target fault type corresponding to the fault data to be tested in the target processing report with the preset fault level to determine the target fault level corresponding to the fault data to be tested.

[0088] In an embodiment of the present application, preset fault levels corresponding to each historical fault type are preset in the operation and maintenance platform. After the corresponding target fault type is determined by analyzing the fault data to be tested, the target fault type is matched with the preset fault type to determine the target fault level corresponding to the fault data to be tested.

[0089] S2042: Send the target processing report to the management terminal corresponding to the device under test according to the preset reminder method corresponding to the target fault level.

[0090] In an embodiment of the present application, reminder methods corresponding to various fault levels are pre-set in the operation and maintenance platform. After the target fault type of the fault data to be tested is determined, the target fault type is matched with the preset reminder method to determine the reminder method for the device to be tested. The target processing report is sent to the corresponding device to be tested according to the preset reminder method, thereby reminding the operation and maintenance personnel to handle the fault of the device to be tested.

[0091] The preset reminder method includes but is not limited to sending the target report to the management terminal, sending the target processing report to the management terminal at a preset interval, sending a control signal to the management terminal while sending the target processing report to the management terminal, the control signal controls the management terminal to vibrate, the screen flashes, etc., and the target processing report can also be sent to a mobile terminal corresponding to the management terminal, the mobile terminal is used by operation and maintenance personnel, and the information of the mobile terminal is pre-stored in the management terminal.

[0092] Among them, the preset reminder method can also set different preset reminder methods according to the source and type of the fault data to be tested. The source of data includes hardware, network, application, database, configuration data, etc. Different preset reminder methods are set for different sources. For example, an abnormality is detected in the operation data of the device to be tested, and the abnormal data is analyzed to determine that it is a performance failure, which is manifested as system overload, continuous increase in CPU usage, and longer system response time, affecting the normal use of the device to be tested. The data source is the CPU response time, and the CPU response time affects the working status of all applications of the device to be tested. Therefore, in this case, the preset reminder method corresponding to the fault data to be tested can be set to the highest level of reminder method, which can be sending a control signal to the management terminal while sending a target processing report to the management terminal, controlling the management terminal display screen to flash or vibrate, etc., or sending a target processing report to the management terminal at a preset interval.

[0093] S205, obtaining a target processing report corresponding to the fault data to be tested based on the target fault type, the target solution and the target processing solution.

[0094] In an embodiment of the present application, a target processing report corresponding to the fault data to be tested is generated in combination with the target fault type, target solution and target processing solution, so that operation and maintenance personnel can handle the anomalies of the device to be tested according to the target processing report.

[0095] The target processing report includes the fault data to be tested, the analysis process of multiple fault data to be tested, and the target solution and target processing plan corresponding to the fault data to be tested. When the operation and maintenance personnel are processing the equipment to be tested, they can also quickly understand the cause of the current fault of the equipment to be tested through the source of the fault data to be tested, so as to quickly understand how to handle it. In addition, the target solution and target processing plan also include specific operation steps for exception handling. The operation and maintenance personnel can just follow the operation steps without specifying the processing plan, thereby improving the efficiency and response speed of exception handling.

[0096] S206, receiving the processing result of the target processing report from the management terminal.

[0097] In an embodiment of the present application, after sending the target processing report to the management terminal, the operation and maintenance personnel can input the processing results into the management terminal, and the management terminal synchronizes the processing results to the operation and maintenance platform in real time.

[0098] It is understandable that after the operation and maintenance personnel handle the exception of the equipment under test, the equipment under test will start to run, and the operation data will be transmitted to the operation and maintenance platform in real time during the operation of the equipment under test. The operation and maintenance platform can also determine whether the exception of the equipment under test has been handled based on the real-time operation data of the equipment under test, and whether other exceptions occur during the processing.

[0099] S207: If the exception corresponding to the fault data to be tested is completed based on the target processing report, the preset operation and maintenance knowledge base is updated based on the fault data to be tested, the target fault type and the target solution.

[0100] In an embodiment of the present application, after completing the exception handling, the operation and maintenance personnel will feedback the processing results to the operation and maintenance platform, and synchronize whether an exception occurs during the processing process, and the processing process is also synchronized to the operation and maintenance platform, so as to synchronize the fault data to be tested with the target fault type, target solution and target processing fee plan to the preset operation and maintenance knowledge base, and update the operation and maintenance knowledge base.

[0101] The process of updating the preset operation and maintenance knowledge base is as follows: when there are target fault types and target solutions corresponding to the fault data to be tested in the preset operation and maintenance knowledge base, the fault data to be tested is matched and bound with the corresponding historical fault types and historical solutions in the preset operation and maintenance knowledge base; if the processing of the fault data to be tested is solved by the target processing solution generated by the solution generation module, the corresponding relationship between the fault data to be tested and the target processing solution is added to the preset operation and maintenance knowledge base, thereby increasing the data of the preset operation and maintenance knowledge base; the data in the preset operation and maintenance knowledge base can also be used to train the fault analysis model.

[0102] S208, if the exception corresponding to the fault data to be tested is not completed based on the target processing report, receiving the final fault type and final solution corresponding to the fault data to be tested, and updating the preset operation and maintenance knowledge base based on the fault data to be tested, the final fault type and the final solution.

[0103] In an embodiment of the present application, if other exceptions arise or the exception of the equipment under test cannot be handled due to the handling of the exception by the fault personnel in the process of handling the exception of the equipment under test according to the target processing report, the operation and maintenance personnel can determine the final solution based on their own experience and existing data queries, and input the final solution on the management terminal or mobile terminal to synchronize it to the operation and maintenance management platform, and update the correspondence between the fault data to be tested, the final solution and the final fault type to the preset operation and maintenance knowledge base.

[0104] In an embodiment of the present application, the operation data of the device to be tested is acquired in real time, and the operation data is analyzed to determine whether the device to be tested has an abnormality. When an abnormality exists, the operation data with the abnormality is determined as the fault data to be tested, and the fault data to be tested is input into a pre-trained fault analysis model. The fault data to be tested is converted into a corresponding data vector to be tested, and the historical fault types in a preset operation and maintenance knowledge base are converted into corresponding historical type vectors, and then a first similarity to be tested between the data vector to be tested and the historical type vector is calculated, and the first similarity to be tested is compared with a preset type similarity threshold to determine the historical fault type corresponding to the first similarity to be tested that is greater than or less than the preset type similarity threshold as the target fault type, and at the same time, the historical solution corresponding to the target fault type is determined as the target solution for the fault data to be tested. If the first similarities to be tested are all less than the preset type similarity threshold, the basic information such as the source and type of the fault data to be tested is analyzed to determine the fault data to be tested. The corresponding target fault type is then processed by natural language processing technology to process each historical solution in the preset operation and maintenance knowledge base, and the historical solution vector corresponding to each historical solution is obtained, and the similarity between the data vector to be tested and the historical solution vector is calculated to obtain the second similarity to be tested corresponding to each historical solution, and the historical solutions corresponding to the N highest second similarities to be tested are determined as the target solutions corresponding to the fault data to be tested. At the same time, the fault data to be tested is analyzed by the solution generation module to obtain the corresponding target processing solution, and the target processing report is obtained by combining the fault data to be tested, the target solution and the target processing solution. Then, the target fault level of the fault data to be tested is determined, and the target processing report is sent to the management terminal according to the preset reminder method corresponding to the target fault level, so as to remind the operation and maintenance personnel, and the operation and maintenance personnel can directly handle the fault of the equipment to be tested according to the operation steps of the target solution and the target processing solution in the target processing report, thereby improving the response speed to the fault of the equipment to be tested.

[0105] like Figure 5 As shown, a schematic diagram of the structure of an intelligent operation and maintenance device is provided in an embodiment of the present application. Figure 5 As shown, the device comprises:

[0106] A data acquisition module is used to obtain the operating data of the device under test;

[0107] A fault determination module is used to determine whether the device under test has an abnormality based on the operating data, and if the device under test has an abnormality, the operating data is determined as the fault data to be tested.

[0108] A report determination module, used for inputting the fault data to be tested into a pre-trained fault analysis model, and outputting a target processing report corresponding to the fault data to be tested, wherein the pre-trained fault analysis model includes a fault detection module for performing fault type detection on the fault data to be tested to obtain a target fault type corresponding to the fault data to be tested, a retrieval module for retrieving a target solution corresponding to the fault data to be tested from a preset operation and maintenance knowledge base, and a solution generation module for generating a corresponding target processing solution according to the fault data to be tested;

[0109] The report sending module is used to send the target processing report to the management terminal corresponding to the device under test.

[0110] Further, the report determination module includes:

[0111] A data analysis unit, configured to input the fault data to be tested into a pre-trained fault analysis model, obtain a target fault type corresponding to the fault data to be tested based on the fault detection module, obtain a target solution corresponding to the fault data to be tested based on the retrieval module, and obtain a target processing solution corresponding to the fault data to be tested based on the solution generation module;

[0112] A report determining unit is used to obtain a target processing report corresponding to the fault data to be tested based on the target fault type, the target solution and the target processing solution.

[0113] Further, the data analysis unit comprises:

[0114] A vector acquisition subunit, used to acquire the fault vector to be tested corresponding to the fault data to be tested, and to acquire the historical type vector corresponding to each historical fault type in a preset knowledge base;

[0115] A first calculation subunit, configured to calculate the similarity between the fault vector to be tested and each of the historical type vectors, and obtain a first similarity to be tested corresponding to each fault vector to be tested;

[0116] The type determination subunit is used to compare each of the first similarities to be tested with a preset type similarity threshold, and determine the first similarity to be tested that is greater than or equal to the preset type similarity threshold as the first target similarity, and determine the historical fault type corresponding to the first target similarity as the target fault type of the fault data to be tested.

[0117] Furthermore, the data analysis unit also includes:

[0118] A first solution determination subunit is configured to determine the historical solution corresponding to the target fault type as the target solution corresponding to the fault data to be tested when the first similarity to be tested is greater than or equal to a preset type similarity threshold;

[0119] A second vector acquisition subunit is used to acquire a historical solution vector of each historical solution in a preset operation and maintenance knowledge base when the first similarity to be measured is less than a preset type similarity threshold;

[0120] A second calculation subunit, configured to calculate a second similarity to be tested between the fault vector to be tested and each of the historical solution vectors;

[0121] The second solution determination subunit is used to determine the target solution corresponding to the fault data to be tested by using the highest N historical solutions corresponding to the second similarities to be tested, wherein N is greater than or equal to 1.

[0122] Further, the report sending module includes:

[0123] A level determination unit, configured to match a target fault type corresponding to the fault data to be tested in the target processing report with a preset fault level to determine a target fault level corresponding to the fault data to be tested;

[0124] The report sending unit is used to send the target processing report to the management terminal corresponding to the device under test according to the preset reminder method corresponding to the target fault level.

[0125] Furthermore, the intelligent operation and maintenance device also includes:

[0126] A sample acquisition module, used to acquire sample training data, wherein the sample training data includes sample operation data and fault types and solutions corresponding to the sample operation data;

[0127] A model training module, used to input the sample training data into a fault analysis model to obtain a processing report corresponding to the sample training data;

[0128] The model determination module is used to determine whether the processing report meets the preset constraint conditions; if so, a fault analysis model that has completed training is obtained; if the model training does not meet the constraints, the next sample training data is obtained, and the step of inputting the sample training data into the fault analysis model is executed.

[0129] Furthermore, the intelligent operation and maintenance device also includes:

[0130] A result determination module, used for receiving the processing result of the target processing report by the management terminal;

[0131] A first updating module, configured to update the preset operation and maintenance knowledge base based on the fault data to be tested, a target fault type and a target solution if the exception corresponding to the fault data to be tested is completed based on the target processing report;

[0132] The second updating module is used to receive the final fault type and the final solution corresponding to the fault data to be tested if the exception corresponding to the fault data to be tested is not completed based on the target processing report, and update the preset operation and maintenance knowledge base based on the fault data to be tested, the final fault type and the final solution.

[0133] In an embodiment of the present application, the operation data of the device under test is acquired in real time, and the operation data is analyzed to determine whether there is an abnormality in the operation of the device under test. If there is an abnormality, the operation data with the abnormality is determined as the fault data under test. The fault data under test can be all the operation data, or the data with the abnormality extracted from the operation data. Then, the abnormal data is input into the pre-trained fault analysis model, and the pre-trained fault analysis model analyzes the abnormal data. The fault type corresponding to the target fault type corresponding to the fault data under test is determined by analyzing the fault data under test through the fault detection module of the fault analysis model; the fault analysis model pre-stores at least one historical fault type and the historical solution corresponding to the historical fault type in the preset operation and maintenance knowledge base, and the retrieval module searches and matches the target solution corresponding to the fault data under test in the preset operation and maintenance knowledge base; the solution generation module of the fault analysis model analyzes the fault data under test to generate a corresponding target processing solution, and then generates a corresponding target processing report in combination with the target fault type, the target solution and the target processing solution, and then sends the target processing report to the management terminal of the device under test so that the operation and maintenance personnel can process the abnormality of the device under test according to the target processing report. By analyzing the fault data to be tested, the corresponding target fault type, the target solution retrieved from the preset operation and maintenance knowledge base, and the target processing solution generated according to the analysis of the fault data to be tested are determined, so as to obtain a target processing report corresponding to the fault data to be tested. When the target processing report is sent to the management terminal, the operation and maintenance personnel can clearly understand what the fault data to be tested corresponds to the abnormality that has occurred, and can handle the abnormality of the equipment to be tested according to the target processing solution and the target solution, without the need to formulate solutions, query data, etc., thereby improving the efficiency and response rate of fault handling while ensuring accuracy.

[0134] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the intelligent operation and maintenance method provided in any of the aforementioned method embodiments are implemented.

[0135] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0136] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0137] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.

[0138] The foregoing is merely a specific embodiment of the present invention, which enables those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. An intelligent operation and maintenance method, characterized in that: Applied to the operation and maintenance platform, the method includes: Obtain the operating data of the device under test; Determine whether the device under test has an abnormality based on the operating data, and if the device under test has an abnormality, determine the operating data as fault data to be tested; The fault data to be tested is input into a pre-trained fault analysis model, and a target processing report corresponding to the fault data to be tested is output, wherein the pre-trained fault analysis model includes a fault detection module for performing fault type detection on the fault data to be tested to obtain a target fault type corresponding to the fault data to be tested, a retrieval module for retrieving a target solution corresponding to the fault data to be tested from a preset operation and maintenance knowledge base, and a solution generation module for generating a corresponding target processing solution according to the fault data to be tested; The target processing report is sent to the management terminal corresponding to the device under test.

2. The method according to claim 1, characterized in that The step of inputting the fault data to be tested into a pre-trained fault analysis model and outputting a processing report corresponding to the fault data to be tested includes: Input the fault data to be tested into a pre-trained fault analysis model, obtain the target fault type corresponding to the fault data to be tested based on the fault detection module, obtain the target solution corresponding to the fault data to be tested based on the retrieval module, and obtain the target processing solution corresponding to the fault data to be tested based on the solution generation module; A target processing report corresponding to the fault data to be tested is obtained based on the target fault type, the target solution and the target processing solution.

3. The method according to claim 2, characterized in that The obtaining the fault type corresponding to the fault data to be tested based on the fault detection module includes: Obtaining a fault vector to be tested corresponding to the fault data to be tested, and obtaining a historical type vector corresponding to each historical fault type in a preset knowledge base; Calculating the similarity between the fault vector to be tested and each of the historical type vectors to obtain a first similarity to be tested corresponding to each fault vector to be tested; Each of the first similarities to be tested is compared with a preset type similarity threshold, and the first similarity to be tested that is greater than or equal to the preset type similarity threshold is determined as the first target similarity, and the historical fault type corresponding to the first target similarity is determined as the target fault type of the fault data to be tested.

4. The method according to claim 3, characterized in that Obtaining a target solution corresponding to the fault data to be tested based on the retrieval module includes: Determine the historical solution corresponding to the target fault type as the target solution corresponding to the fault data to be tested; When the first similarity to be measured is less than a preset type similarity threshold, obtaining a historical solution vector of each historical solution in a preset operation and maintenance knowledge base; Calculating a second similarity between the fault vector to be tested and each of the historical solution vectors; The second similarities to be tested corresponding to the historical solutions are sorted in descending order, and the historical solutions corresponding to the first N second similarities to be tested are used to determine the target solution corresponding to the fault data to be tested, where N is greater than or equal to 1.

5. The method according to claim 1, characterized in that The sending of the target processing report to the management terminal corresponding to the fault data to be tested includes: Matching the target fault type corresponding to the fault data to be tested in the target processing report with a preset fault level to determine the target fault level corresponding to the fault data to be tested; According to the preset reminder method corresponding to the target fault level, the target processing report is sent to the management terminal corresponding to the device under test.

6. The method according to claim 1, characterized in that Before obtaining the operating data of the device under test, the method further includes: Acquire sample training data, where the sample training data includes sample operation data and fault types and solutions corresponding to the sample operation data; Inputting the sample training data into a fault analysis model to obtain a processing report corresponding to the sample training data; Determine whether the processing report satisfies the preset constraint conditions. If so, obtain a trained fault analysis model. If not, obtain the next sample training data and execute the step of inputting the sample training data into the fault analysis model.

7. The method according to claim 1, characterized in that After sending the target processing report to the management terminal corresponding to the device under test, the following step further includes: receiving a processing result of the target processing report by the management terminal; If the anomaly corresponding to the fault data to be tested is completed based on the target processing report, the preset operation and maintenance knowledge base is updated based on the fault data to be tested, the target fault type and the target solution; If the exception corresponding to the fault data to be tested is not completed based on the target processing report, the final fault type and final solution corresponding to the fault data to be tested are received, and the preset operation and maintenance knowledge base is updated based on the fault data to be tested, the final fault type and the final solution.

8. An intelligent operation and maintenance system, characterized in that: The system comprises: an operation and maintenance platform, a device under test, and a management terminal corresponding to the device under test; The operation and maintenance platform is used to obtain the operation data of the equipment under test, analyze the operation data to form a corresponding target processing report, and send the target processing report to the management terminal corresponding to the equipment under test; The equipment under test is connected to the operation and maintenance platform and transmits the operation data to the operation and maintenance platform in real time; The management terminal is used to receive the target processing report sent by the operation and maintenance platform, and send the processing result of the target processing report to the operation and maintenance platform in response to the user's input.

9. An intelligent operation and maintenance device, characterized in that: The device comprises: A data acquisition module is used to obtain the operating data of the device under test; A fault determination module is used to determine whether the device under test has an abnormality based on the operating data, and if the device under test has an abnormality, the operating data is determined as the fault data to be tested. A report determination module, used for inputting the fault data to be tested into a pre-trained fault analysis model, and outputting a target processing report corresponding to the fault data to be tested, wherein the pre-trained fault analysis model includes a fault detection module for performing fault type detection on the fault data to be tested to obtain a target fault type corresponding to the fault data to be tested, a retrieval module for retrieving a target solution corresponding to the fault data to be tested from a preset operation and maintenance knowledge base, and a solution generation module for generating a corresponding target processing solution according to the fault data to be tested; The report sending module is used to send the target processing report to the management terminal corresponding to the device under test.

10. A storage medium, characterized in that: Computer executable instructions are stored, and the computer executable instructions are used to execute the intelligent operation and maintenance method described in any one of the above items of the present application.

Images