Equipment fault alarm processing method and device, electronic equipment and medium

Abstract

The embodiment of the invention relates to the technical field of alarm processing, and provides an equipment fault alarm processing method and device, electronic equipment and a medium, and the method comprises the steps: obtaining current equipment fault alarm information; inputting the current equipment fault alarm information into a pre-trained equipment fault alarm prediction model, analyzing the equipment fault alarm information, and determining a target fault category corresponding to the equipment fault alarm information; determining a target alarm level corresponding to the target fault category based on a preset fault alarm level; and estimating a target fault reason based on the equipment fault alarm information and the target alarm level to generate a troubleshooting guidance scheme. Therefore, alarm data are automatically analyzed through the pre-trained artificial intelligence large model, automatic identification of fault equipment, intelligent inference of fault reasons and intelligent recommendation of a troubleshooting method are realized, the efficiency and accuracy of alarm processing are improved, the workload of operation and maintenance personnel is reduced, and the reliability and service quality of a network are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of alarm processing, and in particular to a method, device, electronic equipment and medium for processing an alarm of a device failure. Background Art

[0002] In modern communication systems, the Network Management System (NMS) is responsible for monitoring the status and performance of network devices and generating alarm information when a device fails. However, as the scale and complexity of networks increase, the number of alarms faced by the NMS increases dramatically, leading to the problem of alarm flooding.

[0003] The existing alarm processing methods rely on manual analysis and experience judgment. The manual analysis method is inefficient and easily affected by human factors, making it difficult to quickly and accurately locate the cause of the fault and formulate a troubleshooting plan. In addition, the large amount of alarm information also makes it difficult for operation and maintenance personnel to respond quickly, affecting the stability of the network and service quality. Summary of the invention

[0004] The present invention provides an alarm processing method, device, electronic device and medium for equipment failure, which are used to solve the defects of the alarm processing method in the prior art that relies on manual analysis and experience judgment, is affected by human factors and has low efficiency, thereby reducing manual intervention, improving the accuracy of fault diagnosis, and improving the speed and efficiency of alarm processing.

[0005] The present invention provides a method for processing an alarm of a device failure, comprising: Get current equipment fault alarm information; Inputting the current equipment fault alarm information into a pre-trained equipment fault alarm prediction model, analyzing the equipment fault alarm information through the equipment fault alarm prediction model, and determining a target fault category corresponding to the equipment fault alarm information; Determining a target alarm level corresponding to the target fault category based on a preset fault alarm level; estimating a target fault cause based on the equipment fault alarm information and the target alarm level; A troubleshooting guidance plan is generated based on the target fault cause.

[0006] In a possible implementation, the method further includes: Inputting the equipment fault alarm information into the equipment fault alarm prediction model, and calculating the probability of belonging to each fault category through the classification layer function of the equipment fault alarm prediction model; The fault category with the highest probability among the fault categories is used as the target fault category corresponding to the equipment fault alarm information.

[0007] In a possible implementation, the method further includes: Collect historical equipment failure alarm data; Processing the historical equipment fault alarm data, labeling the processed historical equipment fault alarm data, and obtaining labeled model training data, wherein the labeled content includes fault alarm category, alarm level, alarm occurrence time, faulty equipment, fault cause, and troubleshooting guidance plan; Training the artificial intelligence big model through the model training data; When the training results meet the preset conditions, it is determined that the training of the artificial intelligence big model is completed, and the trained artificial intelligence big model is used as the equipment fault alarm prediction model.

[0008] In a possible implementation, the method further includes: Set the fault alarm level in advance according to the impact of the equipment or fault type on the normal operation of the system; The target fault category is compared with the fault category corresponding to the preset fault alarm level to determine the target alarm level corresponding to the target fault category.

[0009] In a possible implementation, the method further includes: If the target alarm level is the first alarm level, obtaining other alarm information that occurs simultaneously with the current equipment failure alarm information or within a preset time range; Based on the current equipment fault alarm information and other alarm information, estimating the target fault cause through the equipment fault alarm prediction model; If the target alarm level is not the first alarm level, the target fault cause is estimated by the equipment fault alarm prediction model based on the current equipment fault alarm information.

[0010] In a possible implementation, the method further includes: Send the troubleshooting guidance plan to the operation and maintenance user end, and collect the equipment operation data in real time during the troubleshooting process; The equipment fault alarm prediction model is optimized based on the troubleshooting guidance plan and equipment operation data.

[0011] The present invention also provides an alarm processing device for equipment failure, comprising the following modules: Acquisition module, used to obtain current equipment fault alarm information; An analysis and determination module, used for inputting the current equipment fault alarm information into a pre-trained equipment fault alarm prediction model, analyzing the equipment fault alarm information through the equipment fault alarm prediction model, and determining a target fault category corresponding to the equipment fault alarm information; An analysis and determination module, configured to determine a target alarm level corresponding to the target fault category based on a preset fault alarm level; An estimation module, used for estimating a target fault cause based on the equipment fault alarm information and the target alarm level; A solution generation module is used to generate a troubleshooting guidance solution based on the target fault cause.

[0012] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for processing an alarm of a device failure as described above is implemented.

[0013] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for processing an alarm of a device failure as described in any one of the above is implemented.

[0014] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for processing an alarm of a device failure as described above is implemented.

[0015] The alarm processing method, device, electronic device and medium of equipment failure provided by the present invention obtain the current equipment failure alarm information; input the current equipment failure alarm information into a pre-trained equipment failure alarm prediction model, analyze the equipment failure alarm information through the equipment failure alarm prediction model, and determine the target fault category corresponding to the equipment failure alarm information; determine the target alarm level corresponding to the target fault category based on the preset fault alarm level; estimate the target fault cause based on the equipment failure alarm information and the target alarm level; and generate a troubleshooting guidance plan based on the target fault cause. Compared with the defects of the alarm processing method in the prior art that relies on manual analysis and experience judgment, is affected by human factors, and has low efficiency, this solution automatically analyzes the alarm data through a pre-trained artificial intelligence large model to realize automatic identification of faulty equipment, intelligent inference of fault causes, and intelligent recommendation of troubleshooting methods, which can improve the efficiency and accuracy of alarm processing, reduce the workload of operation and maintenance personnel, and improve network reliability and service quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 This is one of the flow charts of the method for handling equipment failure alarms provided by the present invention.

[0018] Figure 2 This is the second flow chart of the method for handling equipment failure alarms provided by the present invention.

[0019] Figure 3 This is the third flow chart of the method for handling equipment failure alarms provided by the present invention.

[0020] Figure 4 It is a structural schematic diagram of the alarm processing device for equipment failure provided by the present invention.

[0021] Figure 5 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0022] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] To facilitate understanding of the embodiments of the present invention, specific embodiments will be further explained below in conjunction with the accompanying drawings. The embodiments do not constitute a limitation on the embodiments of the present invention.

[0024] Figure 1 This is one of the flow charts of the method for handling equipment failure alarms provided by the present invention, such as Figure 1 As shown, the method includes the following: S11. Obtain current equipment fault alarm information.

[0025] During the operation of the equipment, its built-in monitoring system or external monitoring system will monitor the status of the equipment in real time or regularly. When the equipment has abnormal conditions, such as performance degradation, component damage, etc., the monitoring system will immediately capture these abnormalities and generate corresponding equipment failure alarm information. This information usually includes basic information of the equipment (such as equipment type, location, serial number, etc.), alarm time, alarm code or description, alarm parameters (such as temperature, pressure, current, etc.) and possible error logs.

[0026] S12: input the current equipment fault alarm information into a pre-trained equipment fault alarm prediction model, analyze the equipment fault alarm information through the equipment fault alarm prediction model, and determine a target fault category corresponding to the equipment fault alarm information.

[0027] After obtaining the equipment fault alarm information, the system needs to analyze the information. The purpose of this step is to extract key features from the alarm information and match these features with preset fault categories. Fault categories are usually pre-defined based on the structure, working principle and common failure modes of the equipment, such as power failure, communication failure, sensor failure, etc. Through comparison and analysis, the system can determine the target fault category corresponding to the alarm information.

[0028] In the embodiment of the present invention, a large artificial intelligence model can also be pre-trained to receive alarm information and perform preliminary screening and classification.

[0029] S13. Determine a target alarm level corresponding to the target fault category based on a preset fault alarm level.

[0030] Different fault categories have different impacts and urgency on the equipment. Therefore, the system usually presets one or more alarm levels for each fault category, such as severe, moderate, and minor. After determining the target fault category, the system will determine the target alarm level corresponding to the target fault category based on the preset alarm level rules and the specific content of the alarm information (such as the abnormality of the alarm parameters, the frequency of the fault, etc.).

[0031] S14: estimating a target fault cause based on the device fault alarm information and the target alarm level.

[0032] After determining the target fault category and target alarm level, the system needs to further analyze the alarm information to estimate the cause of the target fault. This step may involve an in-depth understanding of the working principle of the equipment, analysis of historical fault data, and application of expert systems. By integrating this information, the system can estimate one or more possible causes of the fault and provide guidance for subsequent troubleshooting.

[0033] S15. Generate a troubleshooting guidance plan based on the target fault cause.

[0034] Generate a troubleshooting plan based on the estimated target fault cause. Troubleshooting plans usually include a series of specific steps, such as checking the power connection of the device, restarting the device, replacing the faulty parts, etc. These steps are designed to help maintenance personnel quickly locate and solve the problem. When generating a troubleshooting plan, the system will consider factors such as the maintenance personnel's technical level, the specific location of the device, and the available maintenance resources to ensure the feasibility and effectiveness of the plan.

[0035] The alarm processing method for equipment failure provided by the present invention obtains the current equipment failure alarm information; inputs the current equipment failure alarm information into a pre-trained equipment failure alarm prediction model, analyzes the equipment failure alarm information through the equipment failure alarm prediction model, and determines the target fault category corresponding to the equipment failure alarm information; determines the target alarm level corresponding to the target fault category based on the preset fault alarm level; estimates the target fault cause based on the equipment failure alarm information and the target alarm level; and generates a troubleshooting guidance plan based on the target fault cause. Compared with the defects of the alarm processing method in the prior art that relies on manual analysis and experience judgment, is affected by human factors, and has low efficiency, this method automatically analyzes the alarm data through a pre-trained artificial intelligence large model, realizes automatic identification of faulty equipment, intelligent inference of fault causes, and intelligent recommendation of troubleshooting methods, which can improve the efficiency and accuracy of alarm processing, reduce the workload of operation and maintenance personnel, and improve network reliability and service quality.

[0036] Figure 2 This is one of the flow charts of the method for handling equipment failure alarms provided by the present invention, such as Figure 2 As shown, the method includes the following: S21. Collect historical equipment failure alarm data.

[0037] In the embodiment of the present invention, the equipment fault alarm prediction model is first pre-trained. The training method is as follows: First, collect historical equipment failure alarm data generated by various equipment, components and related software platforms in the telecommunications and communication systems.

[0038] S22. Process the historical equipment fault alarm data, and annotate the processed historical equipment fault alarm data to obtain annotated model training data, wherein the annotated content includes fault alarm category, alarm level, alarm occurrence time, faulty equipment, fault cause, and troubleshooting guidance plan.

[0039] Then, the collected historical equipment fault alarm data is screened to remove duplicate, incomplete or obviously erroneous data. The data is labeled, including the fault alarm category, alarm level (such as urgent, important, general, etc.), alarm occurrence time, faulty equipment, fault cause and troubleshooting guidance plan. The labeled historical equipment fault alarm data is converted into a format acceptable to the artificial intelligence large model and divided into training set, verification set and test set.

[0040] S23. Train the artificial intelligence big model using the model training data.

[0041] S24. When the training result meets the preset conditions, it is determined that the training of the artificial intelligence big model is completed, and the trained artificial intelligence big model is used as the equipment fault alarm prediction model.

[0042] Then, set appropriate training parameters for the AI ​​model, such as learning rate, number of training rounds, batch size, etc. Use the prepared training set to train the AI ​​model. During the model training process, the model will learn the features and patterns in the data, and try to predict the output (such as fault category, alarm level, etc.) based on the input data. Through multiple iterations of training, the performance of the model will gradually improve. During the model training process, it is necessary to monitor the progress of the training and the performance of the model in real time. If it is found that the model performs well on the training set but poorly on the validation set, it may indicate that the model is overfitting, and corresponding measures need to be taken, such as increasing the amount of data, adding regularization terms, and adjusting the model structure.

[0043] Use the test set to evaluate the trained model. You can set some evaluation indicators (such as accuracy, recall, F1 score, etc.) to evaluate the performance of the model, calculate the accuracy of the model on the test set and other indicators, and evaluate the generalization ability and performance of the model. If the performance of the model does not meet the requirements, you need to analyze the reasons. You may need to readjust the model structure, training parameters, or increase the amount of data, and then retrain and evaluate until the requirements are met.

[0044] S25. Obtain current equipment failure alarm information.

[0045] Combination Figure 3 As shown in the figure, during the operation of the equipment, its built-in monitoring system or external monitoring system will monitor the status of the equipment in real time or regularly. When the equipment has abnormal conditions, such as performance degradation, component damage, etc., the monitoring system will immediately capture these abnormalities and generate corresponding equipment failure alarm information. This information usually includes basic information of the equipment (such as equipment type, location, serial number, etc.), alarm time, alarm code or description, alarm parameters (such as temperature, pressure, current, etc.) and possible error logs.

[0046] S26. Input the equipment fault alarm information into the equipment fault alarm prediction model, and calculate the probability of belonging to each fault category through the classification layer function of the equipment fault alarm prediction model; and use the fault category with the highest probability as the target fault category corresponding to the equipment fault alarm information.

[0047] The currently acquired equipment fault alarm information is input into the trained equipment fault alarm prediction model. The model will analyze and predict based on the input information and output the corresponding fault category. This fault category is the target fault category, which indicates the possible type of the current equipment fault.

[0048] Take the OTN (Optical Transport Network) alarm as an example: the alarm information is "At 17:00 on November 7, 2024, a frame loss (LOF) alarm occurred in the ODUk (k = 4) channel of the OTN device OTN-789. At the same time, an abnormality was detected in the overhead bytes (SM, PM), and the number of error blocks continued to increase in the past 5 minutes, reaching 100."

[0049] The AI ​​model will associate "Loss of Frame (LOF) alarm" with "Overhead Byte Detected Abnormality" and "Error Block Count Continued to Increase in the Past 5 Minutes" based on the logical relationship and sequence between frame loss, overhead byte abnormality, and increase in the number of error blocks. Through further extraction and transformation of features by neural networks, the model may learn that this situation may be caused by line card failure or network configuration error. Assume that OTN alarms are divided into four categories: card failure, network configuration error, external interference, and software failure. In the final classification layer, the probability of belonging to each category is calculated by function. For example, the probability of this alarm belonging to card failure is 0.35, the probability of network configuration error is 0.4, the probability of external interference is 0.1, and the probability of software failure is 0.05. If the probability threshold is set to 0.4, it is classified as a network configuration error category because the probability of belonging to network configuration error is 0.4, which is equal to 0.4.

[0050] S27. Set the fault alarm level in advance according to the impact of the equipment or fault type on the normal operation of the system.

[0051] Before or after model training, it is necessary to set the fault alarm level according to the impact of the equipment or fault category on the normal operation of the system. These levels usually include severe, moderate, and minor, which are used to indicate the urgency and importance of the fault. The setting of these levels will serve as the basis for determining the target alarm level later.

[0052] S28: Compare the target fault category with the fault category corresponding to the preset fault alarm level to determine the target alarm level corresponding to the target fault category.

[0053] After determining the target fault category, you need to compare it with the preset fault alarm level. By looking up the preset fault alarm level table or rules, you can determine the target alarm level corresponding to the target fault category. This level will be used for subsequent fault handling and troubleshooting guidance.

[0054] Specifically, if the target alarm level is the first alarm level (critical alarm or severe alarm), other alarm information that occurs simultaneously with the current equipment failure alarm information or within a preset time range is obtained; based on the current equipment failure alarm information and other alarm information, the target fault cause is estimated through the equipment failure alarm prediction model.

[0055] Alternatively, if the target alarm level is not the first alarm level (minor alarm or slight alarm), the target fault cause is estimated through the equipment fault alarm prediction model based on the current equipment fault alarm information.

[0056] Critical alarms can refer to those that have a serious impact on the normal operation of the system, which may cause service interruption, data loss, or cause great damage to user experience. Critical alarms are rarely isolated and are usually associated with other alarms or other data (such as performance data). Analyze other alarms and data that occur at the same time as the current critical alarm or in a short period of time to determine the root cause of the failure.

[0057] Minor alarms may refer to those that indicate that there are some abnormal conditions in the system but will not immediately cause serious impact on the core functions or services of the system.

[0058] S29: Send the troubleshooting guidance plan to the operation and maintenance user terminal, and collect the equipment operation data during the troubleshooting process in real time.

[0059] After determining the target alarm level, troubleshooting suggestions can be generated based on the model. During model training, historical troubleshooting data has been associated with fault cause descriptions and repair measures. The model calculates the specific fault cause probability of each alarm based on the current alarm data, and gives the most likely fault cause and troubleshooting solution based on the threshold.

[0060] Furthermore, the troubleshooting guidance plan is sent to the operation and maintenance user end. At the same time, the equipment operation data during the troubleshooting process is collected in real time to monitor and evaluate the troubleshooting process.

[0061] S210: Optimize the equipment fault alarm prediction model based on the troubleshooting guidance plan and equipment operation data.

[0062] During or after troubleshooting, more equipment operation data and troubleshooting result information can be collected. This information can be used to optimize the equipment fault alarm prediction model. By comparing the fault category and alarm level predicted by the model with the actual troubleshooting results and equipment operation data, the performance of the model can be evaluated and deficiencies can be found. Then, this new data and information can be used to further train and optimize the model to improve its prediction accuracy and reliability.

[0063] The artificial intelligence alarm processing method of the embodiment of the present invention has the following advantages: Automated processing: Reduce manual intervention and improve the speed and efficiency of alarm processing. Improved accuracy: Improve the accuracy of fault diagnosis through big data analysis and machine learning technology. Intelligent recommendation: Provide scientific troubleshooting solutions to reduce misoperation and troubleshooting time. Continuous learning: The model can be continuously optimized according to new data to adapt to changes in the network environment. Reduced operation and maintenance burden: Enables operation and maintenance personnel to focus on dealing with more complex problems and improve the overall operation and maintenance quality.

[0064] The following is a description of the device for handling an alarm of a device failure provided by the present invention. The device for handling an alarm of a device failure described below and the method for handling an alarm of a device failure described above can be referred to in correspondence with each other.

[0065] Figure 4 It is a structural diagram of the alarm processing device for equipment failure provided by the present invention, which specifically includes: The acquisition module 401 is used to acquire the current device fault alarm information. For detailed description, please refer to the relevant description of the above method embodiment, which will not be repeated here.

[0066] The analysis and determination module 402 is used to input the current equipment fault alarm information into a pre-trained equipment fault alarm prediction model, analyze the equipment fault alarm information through the equipment fault alarm prediction model, and determine the target fault category corresponding to the equipment fault alarm information. For detailed description, please refer to the relevant description corresponding to the above method embodiment, which will not be repeated here.

[0067] The analysis and determination module 402 is used to determine the target alarm level corresponding to the target fault category based on the preset fault alarm level. For detailed description, please refer to the relevant description corresponding to the above method embodiment, which will not be repeated here.

[0068] The estimation module 403 is used to estimate the target fault cause based on the device fault alarm information and the target alarm level. For detailed description, please refer to the relevant description corresponding to the above method embodiment, which will not be repeated here.

[0069] The solution generation module 404 is used to generate a troubleshooting guidance solution based on the target fault cause. For detailed description, please refer to the relevant description corresponding to the above method embodiment, which will not be repeated here.

[0070] Figure 5 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 5 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the alarm processing method of the equipment fault, the method comprising: obtaining the current equipment fault alarm information; inputting the current equipment fault alarm information into the pre-trained equipment fault alarm prediction model, analyzing the equipment fault alarm information through the equipment fault alarm prediction model, and determining the target fault category corresponding to the equipment fault alarm information; determining the target alarm level corresponding to the target fault category based on the preset fault alarm level; estimating the target fault cause based on the equipment fault alarm information and the target alarm level; and generating a troubleshooting guidance plan based on the target fault cause.

[0071] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0072] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the equipment fault alarm processing method provided by the above-mentioned methods, and the method includes: obtaining current equipment fault alarm information; inputting the current equipment fault alarm information into a pre-trained equipment fault alarm prediction model, analyzing the equipment fault alarm information through the equipment fault alarm prediction model, and determining a target fault category corresponding to the equipment fault alarm information; determining a target alarm level corresponding to the target fault category based on a preset fault alarm level; estimating a target fault cause based on the equipment fault alarm information and the target alarm level; and generating a troubleshooting guidance plan based on the target fault cause.

[0073] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the equipment fault alarm processing method provided by the above-mentioned methods, the method comprising: obtaining current equipment fault alarm information; inputting the current equipment fault alarm information into a pre-trained equipment fault alarm prediction model, analyzing the equipment fault alarm information through the equipment fault alarm prediction model, and determining a target fault category corresponding to the equipment fault alarm information; determining a target alarm level corresponding to the target fault category based on a preset fault alarm level; estimating a target fault cause based on the equipment fault alarm information and the target alarm level; and generating a troubleshooting guidance plan based on the target fault cause.

[0074] 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 displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0075] 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 necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art 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.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for processing an alarm of a device failure, characterized in that: include: Get current equipment fault alarm information; Inputting the current equipment fault alarm information into a pre-trained equipment fault alarm prediction model, analyzing the equipment fault alarm information through the equipment fault alarm prediction model, and determining a target fault category corresponding to the equipment fault alarm information; Determining a target alarm level corresponding to the target fault category based on a preset fault alarm level; estimating a target fault cause based on the equipment fault alarm information and the target alarm level; A troubleshooting guidance plan is generated based on the target fault cause.

2. The method according to claim 1, characterized in that The step of inputting the current equipment fault alarm information into a pre-trained equipment fault alarm prediction model, analyzing the equipment fault alarm information by means of the equipment fault alarm prediction model, and determining a target fault category corresponding to the equipment fault alarm information includes: Inputting the equipment fault alarm information into the equipment fault alarm prediction model, and calculating the probability of belonging to each fault category through the classification layer function of the equipment fault alarm prediction model; The fault category with the highest probability among the fault categories is used as the target fault category corresponding to the equipment fault alarm information.

3. The method according to claim 1, characterized in that The equipment fault alarm prediction model is trained based on the following method: Collect historical equipment failure alarm data; Processing the historical equipment fault alarm data, labeling the processed historical equipment fault alarm data, and obtaining labeled model training data, wherein the labeled content includes fault alarm category, alarm level, alarm occurrence time, faulty equipment, fault cause, and troubleshooting guidance plan; Training the artificial intelligence big model through the model training data; When the training results meet the preset conditions, it is determined that the training of the artificial intelligence big model is completed, and the trained artificial intelligence big model is used as the equipment fault alarm prediction model.

4. The method according to claim 2, characterized in that: The determining the target alarm level corresponding to the target fault category based on the preset fault alarm level includes: Set the fault alarm level in advance according to the impact of the equipment or fault type on the normal operation of the system; The target fault category is compared with the fault category corresponding to the preset fault alarm level to determine the target alarm level corresponding to the target fault category.

5. The method according to claim 4, characterized in that The estimating the target fault cause based on the equipment fault alarm information and the target alarm level includes: If the target alarm level is the first alarm level, then obtaining other alarm information that occurs simultaneously with the current equipment failure alarm information or within a preset time range; Based on the current equipment fault alarm information and other alarm information, estimating the target fault cause through the equipment fault alarm prediction model; If the target alarm level is not the first alarm level, the target fault cause is estimated by the equipment fault alarm prediction model based on the current equipment fault alarm information.

6. The method according to claim 1, characterized in that After generating a troubleshooting guidance plan based on the target fault cause, the method includes: Send the troubleshooting guidance plan to the operation and maintenance user end, and collect the equipment operation data in real time during the troubleshooting process; The equipment fault alarm prediction model is optimized based on the troubleshooting guidance plan and equipment operation data.

7. An alarm processing device for equipment failure, characterized in that: include: Acquisition module, used to obtain current equipment fault alarm information; An analysis and determination module, used for inputting the current equipment fault alarm information into a pre-trained equipment fault alarm prediction model, analyzing the equipment fault alarm information through the equipment fault alarm prediction model, and determining a target fault category corresponding to the equipment fault alarm information; An analysis and determination module, configured to determine a target alarm level corresponding to the target fault category based on a preset fault alarm level; An estimation module, used for estimating a target fault cause based on the equipment fault alarm information and the target alarm level; A solution generation module is used to generate a troubleshooting guidance solution based on the target fault cause.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for processing an alarm of a device failure as described in any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for processing an alarm of a device failure as claimed in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for processing an alarm of a device failure as claimed in any one of claims 1 to 6 is implemented.

Images