Intelligent operation and maintenance management system and method

Abstract

The invention discloses an intelligent operation and maintenance management system and method, and relates to the technical field of operation and maintenance management. Comprising the steps of 1, deploying a data collection agent in an informatization operation and maintenance environment, and collecting original data through the data collection agent, 2, collecting and processing historical operation and maintenance data according to the original data, and 3, training an operation and maintenance decision big model by using a deep learning framework and utilizing the historical operation and maintenance data, the method comprises the following steps of 1, training a large operation and maintenance decision model and forming a threshold rule and an operation and maintenance alarm processing strategy according to historical operation and maintenance data, 4, integrating the trained large operation and maintenance decision model and the threshold rule into a real-time data analysis engine for real-time analysis and intelligent decision making of real-time data, and 5, establishing a decision generation engine according to output of the large decision model, and automatically generating an operation and maintenance decision suggestion, judging whether a threshold rule is triggered or not according to the change of the real-time data, automatically matching an operation and maintenance alarm processing strategy if the threshold rule is triggered, and executing the operation and maintenance alarm processing strategy.

Description

Technical Field

[0001] The invention discloses an intelligent operation and maintenance management system and method, and relates to the technical field of operation and maintenance management. Background Art

[0002] Informatization operation and maintenance work is increasingly becoming the key to maintaining normal operations and providing high-quality services for enterprises and institutions. However, as the scale and complexity of systems continue to increase, existing operation and maintenance methods are gradually becoming incapable of supporting big data analysis and real-time decision-making. Summary of the invention

[0003] In view of the problems of the prior art, the present invention provides an intelligent operation and maintenance management system and method, which analyzes information-based operation and maintenance historical data through big data tools, thereby automatically generating operation and maintenance decisions and automatically resolving software and hardware alarm situations encountered in operation and maintenance work based on the generated decisions.

[0004] The specific scheme proposed by the present invention is:

[0005] The present invention provides an intelligent operation and maintenance management method, comprising:

[0006] Step 1: Deploy data collection agents in the information operation and maintenance environment, and collect raw data through the data collection agents.

[0007] Step 2: Collect and process historical operation and maintenance data based on the original data.

[0008] Step 3: Use the deep learning framework to train the operation and maintenance decision-making model with historical operation and maintenance data, and form threshold rules and operation and maintenance alarm processing strategies based on historical operation and maintenance data.

[0009] Step 4: Integrate the trained operation and maintenance decision model and threshold rules into the real-time data analysis engine for instant analysis and intelligent decision-making of real-time data.

[0010] Step 5: Based on the output of the decision-making model, a decision generation engine is established to automatically generate operation and maintenance decision suggestions. At the same time, it is determined whether the threshold rules are triggered based on the changes in real-time data. If the threshold rules are triggered, the operation and maintenance alarm processing strategy is automatically matched and executed.

[0011] Furthermore, in step 2 of the intelligent operation and maintenance management method, historical operation and maintenance data is collected and processed based on the original data, including: cleaning the original data, filtering the historical operation and maintenance data from the cleaned original data, the historical operation and maintenance data including logs, performance indicators, and event records,

[0012] Integrate and process historical operation and maintenance data.

[0013] Furthermore, in step 3 of the intelligent operation and maintenance management method, the TensorFlow deep learning framework or the PyTorch deep learning framework is used to train the operation and maintenance decision-making model using historical operation and maintenance data.

[0014] Furthermore, the intelligent operation and maintenance management method also includes step 6: establishing a feedback mechanism to monitor the effects of operation and maintenance decisions after implementation, collecting result data of actual operation and maintenance decisions, and using the result data to iteratively optimize the decision-making model to improve the accuracy and adaptability of the decision-making model.

[0015] The present invention also provides an intelligent operation and maintenance management system, including a collection module, a processing module, a model management module, an engine management module and a decision management module.

[0016] The collection module deploys data collection agents in the information operation and maintenance environment, and collects raw data through the data collection agents.

[0017] The processing module collects and processes historical operation and maintenance data based on the original data.

[0018] The model management module uses a deep learning framework to train the operation and maintenance decision-making model using historical operation and maintenance data, and forms threshold rules and operation and maintenance alarm processing strategies based on historical operation and maintenance data.

[0019] The engine management module integrates the trained operation and maintenance decision-making model and threshold rules into the real-time data analysis engine for instant analysis and intelligent decision-making of real-time data.

[0020] The engine management module establishes a decision generation engine based on the output of the decision model. The decision management module automatically generates operation and maintenance decision suggestions through the decision generation engine. At the same time, it determines whether the threshold rules are triggered based on the changes in real-time data. If the threshold rules are triggered, the operation and maintenance alarm processing strategy is automatically matched and executed.

[0021] Furthermore, the processing module of the intelligent operation and maintenance management system collects and processes historical operation and maintenance data based on the original data, including: cleaning the original data, filtering the historical operation and maintenance data from the cleaned original data, the historical operation and maintenance data including logs, performance indicators, and event records,

[0022] Integrate and process historical operation and maintenance data.

[0023] Furthermore, the model management module of the intelligent operation and maintenance management system uses the TensorFlow deep learning framework or the PyTorch deep learning framework to train the operation and maintenance decision-making model using historical operation and maintenance data.

[0024] Furthermore, the intelligent operation and maintenance management system also includes a feedback module, which establishes a feedback mechanism, monitors the effects of operation and maintenance decisions after implementation, collects result data of actual operation and maintenance decisions, and uses the result data to iteratively optimize the decision-making model to improve the accuracy and adaptability of the decision-making model.

[0025] The benefits of the present invention are:

[0026] Improve operation and maintenance efficiency: Reduce manual intervention. The introduction of an automated decision generation engine reduces the frequency of manual decision-making, allowing the operation and maintenance team to focus more on solving key problems, thereby improving overall operation and maintenance efficiency.

[0027] Real-time decision support: The combination of real-time data analysis engine and automated decision generation enables the system to provide instant intelligent decision support in scenarios with high real-time requirements, reducing problem response time.

[0028] Reduced risk: The big model can predict potential problems through comprehensive analysis of historical data, reducing the risk of system failure or performance degradation.

[0029] Real-time monitoring and optimization: By introducing a decision-making optimization feedback mechanism, the system can monitor the effect of decision implementation in real time, adjust decision-making strategies in a timely manner, and reduce the risk of bad decisions.

[0030] Real-time intelligent decision-making: Rapid response to operation and maintenance issues. The synergy of the real-time data analysis engine and automated decision generation enables the system to quickly respond to operation and maintenance issues, shortening the time to solve the problem and reducing the impact on the business.

[0031] Timely adjustment of operation and maintenance strategies: Real-time intelligent decision support enables the system to improve its adaptability in a rapidly changing environment.

[0032] Continuous learning and optimization: Able to adapt to system changes, the decision-making optimization feedback mechanism enables the large model to continuously learn and optimize, adapt to changes in system structure and operating characteristics, and keep the system in an efficient and stable state. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a schematic flow chart of the method of the present invention. DETAILED DESCRIPTION

[0034] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can better understand the present invention and implement it, but the embodiments are not intended to limit the present invention.

[0035] Example 1

[0036] The present invention provides an intelligent operation and maintenance management method, comprising:

[0037] Step 1: Deploy data collection agents in the information operation and maintenance environment, and collect raw data through the data collection agents.

[0038] Step 2: Collect and process historical operation and maintenance data based on the original data.

[0039] According to the original data, historical operation and maintenance data is collected and processed, including: cleaning the original data, filtering the historical operation and maintenance data from the cleaned original data, and the historical operation and maintenance data includes logs, performance indicators, and event records.

[0040] Integrate and process historical operation and maintenance data.

[0041] Step 3: Use a deep learning framework to train the operation and maintenance decision-making model using historical operation and maintenance data, and form threshold rules and operation and maintenance alarm processing strategies based on the historical operation and maintenance data. Use the TensorFlow deep learning framework or the PyTorch deep learning framework to train the operation and maintenance decision-making model using historical operation and maintenance data.

[0042] Step 4: Integrate the trained operation and maintenance decision model and threshold rules into the real-time data analysis engine for instant analysis and intelligent decision-making of real-time data.

[0043] Step 5: Based on the output of the decision-making model, a decision generation engine is established to automatically generate operation and maintenance decision suggestions. At the same time, it is determined whether the threshold rules are triggered based on the changes in real-time data. If the threshold rules are triggered, the operation and maintenance alarm processing strategy is automatically matched and executed.

[0044] Step 6: Establish a feedback mechanism to monitor the effects of operation and maintenance decisions after implementation, collect the result data of actual operation and maintenance decisions, and use the result data to iteratively optimize the decision-making model to improve the accuracy and adaptability of the decision-making model.

[0045] Example 2

[0046] The present invention also provides an intelligent operation and maintenance management system, including a collection module, a processing module, a model management module, an engine management module and a decision management module.

[0047] The collection module deploys data collection agents in the information operation and maintenance environment, and collects raw data through the data collection agents.

[0048] The processing module collects and processes historical operation and maintenance data based on the original data.

[0049] The model management module uses a deep learning framework to train the operation and maintenance decision-making model using historical operation and maintenance data, and forms threshold rules and operation and maintenance alarm processing strategies based on historical operation and maintenance data.

[0050] The engine management module integrates the trained operation and maintenance decision-making model and threshold rules into the real-time data analysis engine for instant analysis and intelligent decision-making of real-time data.

[0051] The engine management module establishes a decision generation engine based on the output of the decision model. The decision management module automatically generates operation and maintenance decision suggestions through the decision generation engine. At the same time, it determines whether the threshold rules are triggered based on the changes in real-time data. If the threshold rules are triggered, the operation and maintenance alarm processing strategy is automatically matched and executed.

[0052] As the information interaction and execution process between the modules of the above-mentioned system are based on the same concept as the embodiment of the method of the present invention, the specific contents can be found in the description of the embodiment of the method of the present invention and will not be repeated here.

[0053] Likewise, the benefits of the system of the present invention are:

[0054] Improve operation and maintenance efficiency: Reduce manual intervention. The introduction of an automated decision generation engine reduces the frequency of manual decision-making, allowing the operation and maintenance team to focus more on solving key problems, thereby improving overall operation and maintenance efficiency.

[0055] Real-time decision support: The combination of real-time data analysis engine and automated decision generation enables the system to provide instant intelligent decision support in scenarios with high real-time requirements, reducing problem response time.

[0056] Reduced risk: The big model can predict potential problems through comprehensive analysis of historical data, reducing the risk of system failure or performance degradation.

[0057] Real-time monitoring and optimization: By introducing a decision-making optimization feedback mechanism, the system can monitor the effect of decision implementation in real time, adjust decision-making strategies in a timely manner, and reduce the risk of bad decisions.

[0058] Real-time intelligent decision-making: Rapid response to operation and maintenance issues. The synergy of the real-time data analysis engine and automated decision generation enables the system to quickly respond to operation and maintenance issues, shortening the time to solve the problem and reducing the impact on the business.

[0059] Timely adjustment of operation and maintenance strategies: Real-time intelligent decision support enables the system to improve its adaptability in a rapidly changing environment.

[0060] Continuous learning and optimization: Able to adapt to system changes, the decision-making optimization feedback mechanism enables the large model to continuously learn and optimize, adapt to changes in system structure and operating characteristics, and keep the system in an efficient and stable state.

[0061] It should be noted that not all steps and modules in the above-mentioned processes and system structures are necessary, and some steps or modules can be ignored according to actual needs. The execution order of each step is not fixed and can be adjusted as needed. The system structure described in the above-mentioned embodiments can be a physical structure or a logical structure, that is, some modules may be implemented by the same physical entity, or some modules may be implemented by multiple physical entities, or some components in multiple independent devices may be implemented together.

[0062] The above-described embodiments are only preferred embodiments for fully illustrating the present invention, and the protection scope of the present invention is not limited thereto. Equivalent substitutions or changes made by those skilled in the art based on the present invention are within the protection scope of the present invention. The protection scope of the present invention shall be subject to the claims.

Claims

1. An intelligent operation and maintenance management method, characterized by include: Step 1: Deploy data collection agents in the information operation and maintenance environment, and collect raw data through the data collection agents. Step 2: Collect and process historical operation and maintenance data based on the original data. Step 3: Use the deep learning framework to train the operation and maintenance decision-making model with historical operation and maintenance data, and form threshold rules and operation and maintenance alarm processing strategies based on historical operation and maintenance data. Step 4: Integrate the trained operation and maintenance decision model and threshold rules into the real-time data analysis engine for instant analysis and intelligent decision-making of real-time data. Step 5: Based on the output of the decision-making model, a decision generation engine is established to automatically generate operation and maintenance decision suggestions. At the same time, it is determined whether the threshold rules are triggered based on the changes in real-time data. If the threshold rules are triggered, the operation and maintenance alarm processing strategy is automatically matched and executed.

2. According to the intelligent operation and maintenance management method of claim 1, it is characterized by In step 2, historical operation and maintenance data is collected and processed based on the original data, including: cleaning the original data, filtering the historical operation and maintenance data from the cleaned original data, and the historical operation and maintenance data includes logs, performance indicators, and event records. Integrate and process historical operation and maintenance data.

3. According to the intelligent operation and maintenance management method of claim 1, it is characterized in that in step 3, the TensorFlow deep learning framework or the PyTorch deep learning framework is used to train the operation and maintenance decision-making model using historical operation and maintenance data.

4. The intelligent operation and maintenance management method according to claim 1 is characterized in that It also includes step 6: establishing a feedback mechanism to monitor the effects of operation and maintenance decisions after implementation, collecting the result data of actual operation and maintenance decisions, and using the result data to iteratively optimize the decision-making model to improve the accuracy and adaptability of the decision-making model.

5. An intelligent operation and maintenance management system, characterized by It includes acquisition module, processing module, model management module, engine management module and decision management module. The collection module deploys data collection agents in the information operation and maintenance environment, and collects raw data through the data collection agents. The processing module collects and processes historical operation and maintenance data based on the original data. The model management module uses a deep learning framework to train the operation and maintenance decision-making model using historical operation and maintenance data, and forms threshold rules and operation and maintenance alarm processing strategies based on historical operation and maintenance data. The engine management module integrates the trained operation and maintenance decision-making model and threshold rules into the real-time data analysis engine for instant analysis and intelligent decision-making of real-time data. The engine management module establishes a decision generation engine based on the output of the decision model. The decision management module automatically generates operation and maintenance decision suggestions through the decision generation engine. At the same time, it determines whether the threshold rules are triggered based on the changes in real-time data. If the threshold rules are triggered, the operation and maintenance alarm processing strategy is automatically matched and executed.

6. The intelligent operation and maintenance management system according to claim 5 is characterized in that The processing module collects and processes historical operation and maintenance data based on the original data, including: cleaning the original data, filtering the historical operation and maintenance data from the cleaned original data, and the historical operation and maintenance data includes logs, performance indicators, and event records. Integrate and process historical operation and maintenance data.

7. According to claim 5, an intelligent operation and maintenance management system is characterized in that the model The management module uses the TensorFlow deep learning framework or the PyTorch deep learning framework to train the operation and maintenance decision-making model using historical operation and maintenance data.

8. The intelligent operation and maintenance management system according to claim 5 is characterized by: It also includes a feedback module, which establishes a feedback mechanism to monitor the effects of operation and maintenance decisions after implementation, collects result data of actual operation and maintenance decisions, and uses the result data to iteratively optimize the decision-making model to improve the accuracy and adaptability of the decision-making model.

Images