Intelligent operation and maintenance management method and system based on artificial intelligence data center

Abstract

The invention discloses an intelligent operation and maintenance management method and system based on an artificial intelligence data center, and relates to the technical field of data processing, and the operation and maintenance management system comprises a data collection module, a data classification storage module, a data prediction module, a data processing module and a data evaluation module. The data acquisition module is used for acquiring different hardware equipment data and software data in the operation and maintenance management system in real time. The data classification storage module is used for classifying and storing the data in the operation and maintenance management system, and then the importance of different data is determined by utilizing grades; and then the data prediction module analyzes the classified data, so that the operation and maintenance management system can predict different classification data conveniently, after fault data occurs in the operation and maintenance management system, judgment is performed between the fault data and the classification, and the position of the fault data in the operation and maintenance management system is effectively and quickly positioned.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and specifically to an intelligent operation and maintenance management method and system based on an artificial intelligence data center. Background Art

[0002] At present, with the rapid development of my country's Internet technology, the data interaction of data network platforms is increasing, which leads to an increasing amount of data that data centers need to process, and the requirements for data center staff and data processing devices are also getting higher and higher;

[0003] Although different operation and maintenance management systems can predict fault data in advance, they cannot quickly locate and adjust fault data after it occurs because the data is too large and messy. Therefore, we propose an intelligent operation and maintenance management method and system based on artificial intelligence data center. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent operation and maintenance management method and system based on an artificial intelligence data center.

[0005] To achieve the above object, the present invention provides the following technical solution: an intelligent operation and maintenance management system based on an artificial intelligence data center, the operation and maintenance management system comprising a data acquisition module, a data classification storage module, a data prediction module, a data processing module and a data evaluation module;

[0006] The data acquisition module is used to collect different hardware equipment data and software data in the operation and maintenance management system in real time;

[0007] The data classification storage module is used to classify and store different hardware device data and software data according to the pre-set data level standards of different hardware devices and software, and then store the classified data in time sequence, while storing the historical data in the operation and maintenance management system;

[0008] The data prediction module predicts the data classified by the grade standard according to the time series, extracts features according to the historical data, uses the data prediction module to analyze the trend of the feature data, and then predicts the fault data after the time series storage;

[0009] A data processing module is used to generate a repair plan for fault data. When the data predicted by the data prediction module fails, the data processing module obtains the fault data stored in time series, and the data processing module generates a repair plan for the acquired fault data stored in time series;

[0010] The data evaluation module is used to evaluate the different hardware equipment data, software data and repair solutions in the operation and maintenance management system, and adjust the repair solutions based on the evaluated data.

[0011] As a further solution of the present invention: a real-time monitoring unit is set in the data acquisition module, and the real-time monitoring unit is used to monitor different hardware equipment data and software data in the operation and maintenance management system in real time. When the real-time monitoring unit detects fault data, the real-time monitoring unit creates fault instruction data, and the data acquisition module transmits the fault data and the fault instruction data to the data processing module and the data classification storage module respectively. When the real-time monitoring unit does not detect fault data, the data acquisition module transmits the collected data to the data classification storage module.

[0012] As a further solution of the present invention: the data classification storage module includes a classification unit, a temporary storage unit and a historical storage unit. The classification unit is used to classify the data transmitted by the data acquisition module, and then transmit the classified data to the temporary storage unit. The historical storage unit is used to store the time-series stored data in the operation and maintenance management system. When the data prediction module calls the time-series stored data in the temporary storage unit for prediction, the temporary storage unit transfers the time-series stored data to the historical storage unit.

[0013] As a further solution of the present invention: a neural network model is set in the data prediction module, and the neural network model is used to retrieve data from the historical storage unit as a hidden layer, and then the data in different classification storage units are input into the neural network model position. Whenever the neural network model completes the prediction task of the data in the temporary storage unit of the current classification, it will automatically turn and retrieve the data in the temporary storage unit of the next classification for processing.

[0014] As a further solution of the present invention: the neural network model predicts the fault data in the temporary storage unit through a formula, and the specific formula is as follows:

[0015]

[0016] Among them, S T(t+1) represents the fault data of the Tth classification at the next (t+1) moment, n represents the number of historical data points of the predicted value, S i represents the predicted value of the i-th item in the historical data, W i Represents the weight coefficient of the i-th predicted value in the historical data, S 总 represents the fault data of all temporary storage units, L represents the total number of temporary storage units, and then predicts the different classified data. After the neural network model has finished predicting in turn, the data in the temporary storage unit is retrieved again for prediction, and the predicted data is updated.

[0017] As a further solution of the present invention: after receiving the fault instruction data, the data classification storage module uses a classification unit to classify the data of the fault instruction, and then transmits the classified data to the data processing module, and a decision unit is set in the data processing module, and the decision unit is used to generate a maintenance plan and a repair plan according to the repair plan.

[0018] As a further solution of the present invention: an optimization evaluation unit is set in the data evaluation module. After the data evaluation module receives the maintenance plan data and the repair plan data transmitted by the decision unit, the optimization evaluation unit uses the maintenance plan data and the repair plan data to real-time schedule the response time of the equipment in the operation and maintenance management system when running tasks.

[0019] As a further solution of the present invention: the optimization evaluation unit obtains the average response time through a formula, and the specific formula is as follows:

[0020]

[0021] Among them, R a represents the average response time, m represents the maximum number of tasks, R q represents the response time of the qth task, f q It represents the weight coefficient of the qth task affected by the current device failure, thereby adjusting the number of tasks between different devices and optimizing the response speed of different devices.

[0022] In addition, the present invention also provides an intelligent operation and maintenance management method based on an artificial intelligence data center, which is suitable for the intelligent operation and maintenance management system based on the artificial intelligence data center.

[0023] By adopting the above technical solution, compared with the prior art, the beneficial effects of the present invention are:

[0024] 1. The present invention classifies and stores the data in the operation and maintenance management system through a data classification storage module, and then uses the level to determine the importance of different data, and then the data prediction module analyzes the classified data, so that the operation and maintenance management system can make predictions for different classified data. After fault data appears in the operation and maintenance management system, the fault data and the classification are judged, and the location of the faulty data in the operation and maintenance management system is effectively and quickly located;

[0025] 2. The present invention cooperates with the real-time monitoring unit and the classification unit, so that after the real-time monitoring unit detects the fault data, the classification unit quickly obtains the classification data of the fault data, so that the subsequent data processing module quickly locates the position of the fault data;

[0026] 3. The present invention sets a neural network model through a data prediction module, retrieves data from a historical storage unit as hidden layer data of the neural network model, and then the neural network model sequentially retrieves data from different classification storage units for prediction, thereby reducing the computing power of the overall operation and maintenance management system for prediction, and then the neural network model performs cyclic prediction, so that the neural network model predicts the updated data again after one week of prediction, thereby improving the prediction accuracy of the neural network model;

[0027] 4. The present invention classifies and stores different data through a data classification storage module, and then uses a decision-making unit to generate corresponding maintenance plans for different data, and reasonably adjusts the task data between different devices through formulas, thereby ensuring the response speed of the operation and maintenance management system.

[0028] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 This is a flow chart of the operation and maintenance management system in an embodiment of the present invention;

[0030] Figure 2 This is a specific flow chart of the data classification storage module in an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The specific embodiments of the present invention will be further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0032] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0033] Embodiment 1:

[0034] Please see attached Figure 1 -Attached Figure 2 The present invention is based on an intelligent operation and maintenance management system for an artificial intelligence data center, and the operation and maintenance management system includes a data acquisition module, a data classification storage module, a data prediction module, a data processing module, and a data evaluation module;

[0035] The data acquisition module is used to collect different hardware equipment data and software data in the operation and maintenance management system in real time;

[0036] The data classification storage module is used to classify and store different hardware equipment data and software data, classify them according to the pre-set data level standards of different hardware equipment and software, and then store them according to the time series of the classified data, and store the historical data in the operation and maintenance management system at the same time;

[0037] The data prediction module predicts the data classified by the grade standard according to the time series, extracts features based on historical data, uses the data prediction module to analyze the trend of feature data, and then predicts the fault data after time series storage;

[0038] A data processing module is used to generate a repair plan for fault data. When the data predicted by the data prediction module fails, the data processing module obtains the fault data stored in time series, and the data processing module generates a repair plan for the acquired fault data stored in time series;

[0039] The data evaluation module is used to evaluate the different hardware equipment data, software data and repair solutions in the operation and maintenance management system, and adjust the repair solutions based on the evaluated data.

[0040] Specific workflow: Use the data acquisition module to collect data on hardware devices and software in the operation and maintenance management system in real time. For example, install sensors on the server to collect data on hardware temperature, voltage, and other data, and obtain software operating status, error logs, and other data through the software interface. The data classification and storage module receives the collected data and performs a first classification on the data according to the type of device and software. For example, server data, network device data, operating system data, application data, etc. are classified separately, and the data after the first classification is classified again according to the level of the data (such as key data, important data, and general data). The classified data is stored in time series for subsequent analysis. The data prediction module obtains data from the classification storage module. For different types of data, features are extracted based on historical data. For example, for server CPU usage data, its features in different time periods are extracted. The average value, peak value, fluctuation amplitude and other characteristics are analyzed to analyze the trend of these characteristic data, and then predict the possible fault data of different types of data. Then, when a fault occurs in the intelligent operation and maintenance management system, the data processing module obtains the fault data, classifies and analyzes the fault data, retrieves the corresponding predicted fault data from the data prediction module, locates and troubleshoots the fault location according to the predicted fault data, and generates a repair plan. Finally, the data evaluation module obtains the repair plan-related data generated by the data processing module, as well as the operation data of the entire operation and maintenance management system, and evaluates the overall operation status of the operation and maintenance management system. The evaluation indicators may include fault occurrence rate, fault repair time, resource utilization, etc. The repair plan is adjusted according to the evaluation results. If it is found that the repair time of a certain fault is too long, the cause is analyzed and the repair plan is optimized, such as adding spare resources or improving the fault troubleshooting algorithm.

[0041] Furthermore, the data in the operation and maintenance management system are classified and stored through the data classification storage module, and then the importance of different data is determined by using levels. The data prediction module then analyzes the classified data to facilitate the operation and maintenance management system to make predictions for different classified data. When fault data appears in the operation and maintenance management system, a judgment is made between the fault data and the classification, so as to effectively and quickly locate the location of the faulty data in the operation and maintenance management system.

[0042] Embodiment 2:

[0043] Based on the first embodiment, please refer to the attached Figure 1 -Attached Figure 2 As shown, a real-time monitoring unit is set in the data acquisition module, and the real-time monitoring unit is used to monitor different hardware equipment data and software data in the operation and maintenance management system in real time. When the real-time monitoring unit detects fault data, the real-time monitoring unit creates fault instruction data, and the data acquisition module transmits the fault data and the fault instruction data to the data processing module and the data classification storage module respectively. When the real-time monitoring unit does not detect the fault data, the data acquisition module transmits the collected data to the data classification storage module. The data classification storage module includes a classification unit, a temporary storage unit and a historical storage unit. The classification unit is used to classify the data transmitted by the data acquisition module, and then transmit the classified data to the temporary storage unit. The historical storage unit is used to store the time-series stored data in the operation and maintenance management system. When the data prediction module calls the time-series stored data in the temporary storage unit for prediction, the temporary storage unit transmits the time-series stored data to the historical storage unit.

[0044] Specific workflow: The data transmitted by the data acquisition module is classified through the classification unit in the data classification storage module. For example, the hardware data and software data are separated, and the hardware data is further subdivided according to categories such as servers and network equipment. The software data is subdivided according to categories such as operating systems and applications. The classified data is transmitted to the corresponding temporary storage unit. The historical storage unit is used to store data of different time periods in the operation and maintenance management system. A threshold is set in the temporary storage unit so that when the temporary storage unit reaches a certain threshold, the data prediction module retrieves the data in the temporary storage unit for prediction.

[0045] Furthermore, through the cooperation between the real-time monitoring unit and the classification unit, after the real-time monitoring unit detects the fault data, the classification unit quickly obtains the classification data of the fault data, so that the subsequent data processing module can quickly locate the position of the fault data.

[0046] Embodiment three:

[0047] Based on the second embodiment, please refer to the attached Figure 1 -Attached Figure 2 As shown, a neural network model is set in the data prediction module, and the neural network model is used to retrieve the data in the historical storage unit as a hidden layer, and then the data in the different classification storage units are input into the neural network model position. Whenever the neural network model completes the prediction task of the data in the temporary storage unit of the current classification, it will automatically turn and retrieve the data in the temporary storage unit of the next classification for processing. The neural network model predicts the fault data in the temporary storage unit through the formula. The specific formula is as follows:

[0048]

[0049] Among them, S T(t+1) represents the fault data of the Tth classification at the next (t+1) moment, n represents the number of historical data points of the predicted value, S i represents the predicted value of the i-th item in the historical data, W i Represents the weight coefficient of the i-th predicted value in the historical data, S 总 represents the fault data of all temporary storage units, L represents the total number of temporary storage units, and then predicts the different classified data. After the neural network model has finished predicting in turn, the data in the temporary storage unit is retrieved again for prediction, and the predicted data is updated.

[0050] Specific workflow: The hidden layer is improved by retrieving data from the historical storage unit through the neural network model, and then the neural network model is used to predict faults of the data in the temporary storage unit. After the prediction is completed, the data in the temporary storage unit is transferred to the corresponding historical storage unit to improve the hidden layer data of the neural network.

[0051] Furthermore, a neural network model is set up through a data prediction module, and data is retrieved from historical storage units as hidden layer data of the neural network model. Then, the neural network model sequentially retrieves data from different classification storage units for prediction, thereby reducing the computing power of the overall operation and maintenance management system for prediction. The neural network model is then used for cyclic prediction, so that the neural network model predicts the updated data again one week later, thereby improving the prediction accuracy of the neural network model.

[0052] Embodiment 4:

[0053] Based on the third embodiment, please refer to the attached Figure 1 -Attached Figure 2As shown, after receiving the fault instruction data, the data classification storage module uses the classification unit to classify the data of the fault instruction, and then transmits the classified data to the data processing module. A decision unit is set in the data processing module, and the decision unit is used to generate a maintenance plan and a repair plan according to the repair plan. After some data reaches the set threshold, the decision unit also generates a maintenance plan and a repair plan. An optimization evaluation unit is set in the data evaluation module. After the data evaluation module receives the maintenance plan data and the repair plan data transmitted by the decision unit, the optimization evaluation unit uses the maintenance plan data and the repair plan data to real-time schedule the response time of the equipment in the operation and maintenance management system when running the task. The optimization evaluation unit obtains the average response time through a formula. The specific formula is as follows:

[0054]

[0055] Among them, R a represents the average response time, m represents the maximum number of tasks, R q represents the response time of the qth task, f q It represents the weight coefficient of the qth task affected by the current device failure, thereby adjusting the number of tasks between different devices and optimizing the response speed of different devices.

[0056] Furthermore, different data are classified and stored through the data classification storage module, and then the decision unit is used to generate corresponding maintenance plans for different data, and the task data between different devices are reasonably adjusted through formulas to ensure the response speed of the operation and maintenance management system.

[0057] The above shows and describes the basic principles, main features and advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. Intelligent operation and maintenance management system based on artificial intelligence data center, characterized by: The operation and maintenance management system includes a data acquisition module, a data classification storage module, a data prediction module, a data processing module and a data evaluation module; The data acquisition module is used to collect different hardware equipment data and software data in the operation and maintenance management system in real time; The data classification storage module is used to classify and store different hardware device data and software data according to the pre-set data level standards of different hardware devices and software, and then store the classified data in time sequence, while storing the historical data in the operation and maintenance management system; The data prediction module predicts the data classified by the grade standard according to the time series, extracts features according to the historical data, uses the data prediction module to analyze the trend of the feature data, and then predicts the fault data after the time series storage; A data processing module is used to generate a repair plan for fault data. When the data predicted by the data prediction module fails, the data processing module obtains the fault data stored in time series, and generates a repair plan for the acquired fault data stored in time series; The data evaluation module is used to evaluate the different hardware equipment data, software data and repair solutions in the operation and maintenance management system, and adjust the repair solutions based on the evaluated data.

2. The intelligent operation and maintenance management system based on artificial intelligence data center according to claim 1 is characterized in that: A real-time monitoring unit is set in the data acquisition module, and the real-time monitoring unit is used to monitor different hardware equipment data and software data in the operation and maintenance management system in real time. When the real-time monitoring unit detects fault data, the real-time monitoring unit creates fault instruction data, and the data acquisition module transmits the fault data and the fault instruction data to the data processing module and the data classification storage module respectively. When the real-time monitoring unit does not detect fault data, the data acquisition module transmits the collected data to the data classification storage module.

3. The intelligent operation and maintenance management system based on artificial intelligence data center according to claim 2 is characterized in that: The data classification storage module includes a classification unit, a temporary storage unit and a historical storage unit. The classification unit is used to classify the data transmitted by the data acquisition module, and then transmit the classified data to the temporary storage unit. The historical storage unit is used to store the time-series stored data in the operation and maintenance management system. When the data prediction module calls the time-series stored data in the temporary storage unit for prediction, the temporary storage unit transfers the time-series stored data to the historical storage unit.

4. The intelligent operation and maintenance management system based on artificial intelligence data center according to claim 3 is characterized by: A neural network model is set in the data prediction module, and the neural network model is used to retrieve data from historical storage units as a hidden layer, and then the data in different classification storage units are input into the neural network model position. Whenever the neural network model completes the prediction task of the data in the temporary storage unit of the current classification, it will automatically turn and retrieve the data in the temporary storage unit of the next classification for processing.

5. The intelligent operation and maintenance management system based on artificial intelligence data center according to claim 4 is characterized in that: The neural network model predicts the fault data in the temporary storage unit through a formula, and the specific formula is as follows: Among them, S T(t+1) represents the fault data of the Tth classification at the next (t+1) moment, n represents the number of historical data points of the predicted value, S i represents the predicted value of the i-th item in the historical data, W i Represents the weight coefficient of the i-th predicted value in the historical data, S 总 represents the fault data of all temporary storage units, L represents the total number of temporary storage units, and then predicts the different classified data. After the neural network model has finished predicting in turn, the data in the temporary storage unit is retrieved again for prediction, and the predicted data is updated.

6. The intelligent operation and maintenance management system based on artificial intelligence data center according to claim 5 is characterized in that: After receiving the fault instruction data, the data classification storage module uses a classification unit to classify the data of the fault instruction, and then transmits the classified data to the data processing module. A decision unit is set in the data processing module, and the decision unit is used to generate a maintenance plan and a repair plan according to the repair plan.

7. The intelligent operation and maintenance management system based on artificial intelligence data center according to claim 6 is characterized in that: An optimization evaluation unit is set in the data evaluation module. After the data evaluation module receives the maintenance plan data and the repair plan data transmitted by the decision unit, the optimization evaluation unit uses the maintenance plan data and the repair plan data to real-time schedule the response time of the equipment in the operation and maintenance management system when running tasks.

8. The intelligent operation and maintenance management system based on artificial intelligence data center according to claim 7 is characterized in that: The optimization evaluation unit obtains the average response time through a formula, and the specific formula is as follows: Among them, R a represents the average response time, m represents the maximum number of tasks, R q represents the response time of the qth task, f q It represents the weight coefficient of the qth task affected by the current device failure, thereby adjusting the number of tasks between different devices and optimizing the response speed of different devices.

9. An intelligent operation and maintenance management method based on an artificial intelligence data center, characterized in that: This intelligent operation and maintenance management method is applicable to the intelligent operation and maintenance management system based on artificial intelligence data center described in any one of claims 1-8.

Images