A method and system for real-time monitoring of hard disk anomalies

Abstract

The present invention provides a method and system for real-time monitoring of hard disk anomalies, relating to the technical field of storage monitoring. The method includes: obtaining the running data of the hard disk in real time through a preset monitoring system and outputting the original data; preprocessing the original data using a preset preprocessing method and outputting the data to be analyzed; extracting features from the data to be analyzed, selecting historical running data that matches the data to be analyzed from the historical database based on the extracted features, and training and optimizing a preset model based on the historical running data to obtain an anomaly monitoring model; using the anomaly monitoring model to perform anomaly analysis and prediction analysis on the data to be analyzed, outputting the anomaly-prediction analysis result, and obtaining an anomaly response strategy that matches the anomaly-prediction analysis result by combining a preset result-strategy comparison table. The present invention can achieve real-time monitoring and prediction of the running state of the hard disk, timely discover and handle potential hard disk problems, and ensure the stability of the system and the security of data.

Description

Technical Field

[0001] The present invention relates to the technical field of storage monitoring, and particularly to a method and system for real-time monitoring of hard disk anomalies. Background Art

[0002] Hard disk anomaly monitoring is of great significance for maintaining system stability, ensuring data security, saving maintenance costs, and extending the life of hard disks. Regularly monitoring the running data of hard disks and promptly handling abnormal situations are key steps in maintaining the healthy operation of computer systems.

[0003] Currently, hard disk monitoring usually uses methods such as interface monitoring or sensor monitoring to monitor hard disks. Although this traditional monitoring method can intuitively and quickly evaluate the hard disk status, its monitoring accuracy is low, and it is difficult to detect potential abnormal problems in hard disks. Therefore, it can often only detect hard disk failures that have occurred, which may affect the normal use of hard disks.

[0004] Therefore, the present invention provides a method and system for real-time monitoring of hard disk anomalies. Summary of the Invention

[0005] The present invention provides a method and system for real-time monitoring of hard disk anomalies, which are used to monitor the running parameters of hard disks in real time. It can not only detect the abnormal status of hard disks in real time, but also perform predictive analysis on hard disks, promptly discover potential abnormal situations of hard disks, and ensure the stable operation of hard disks.

[0006] On the one hand, the present invention provides a method for real-time monitoring of hard disk anomalies, including:

[0007] Step 1: Real-time obtain the running data of the hard disk through a preset monitoring system and output the original data;

[0008] Step 2: Preprocess the original data using a preset preprocessing method and output the data to be analyzed;

[0009] Step 3: Extract features from the data to be analyzed, select historical running data matching the data to be analyzed from the historical database based on the extracted features, and train and optimize a preset model based on the historical running data to obtain an anomaly monitoring model;

[0010] Step 4: Use the anomaly monitoring model to perform anomaly analysis and predictive analysis on the data to be analyzed, output the anomaly-predictive analysis result, and obtain an anomaly response strategy matching the anomaly-predictive analysis result in combination with a preset result-strategy comparison table.

[0011] Preferably, in Step 1, it includes:

[0012] Obtain the monitoring requirement information of the current hard disk, and combine it with the preset requirement-data comparison table to obtain the real-time operation data in the current hard disk that matches the monitoring requirement information;

[0013] At the same time, combine the device information of the current hard disk and the timestamp corresponding to the real-time operation data of the current hard disk to output the original data.

[0014] Preferably, in step 2, before preprocessing the original data using the preset preprocessing method, it includes:

[0015] Extract features from the monitoring requirement information, and construct a requirement feature set based on the extracted features;

[0016] Based on the requirement feature set, and in combination with the preset feature-method matching table, select the preset preprocessing method that matches the monitoring requirement information from the method database.

[0017] Preferably, in step 2, it further includes:

[0018] Match the original data with the preset preprocessing method, bind the original data and the preset preprocessing method that meet the preset matching conditions, and output a data-method matching table;

[0019] Based on the data-method matching table, use the preset preprocessing method to preprocess the corresponding original data, and output the data to be analyzed.

[0020] Preferably, extracting features from the data to be analyzed and selecting historical operation data that matches the data to be analyzed from the historical database includes:

[0021] Extract features from the data to be analyzed, and construct a data feature set based on the extracted features;

[0022] Based on the data feature set, select historical operation data that meets the preset screening conditions from the historical database, and output the historical operation data of the hard disk.

[0023] Preferably, training and optimizing the preset model based on the historical operation data to obtain an anomaly monitoring model includes:

[0024] Extract features from the historical operation data, and construct a historical data feature set based on the extracted features;

[0025] Based on the historical data feature set, and in combination with the feature-model mapping table, select a matching first model from the model database, and construct a model alternative pool based on at least two of the first models;

[0026] The acquisition system selects the first model according to the preset recommendation algorithm, outputs the system's self-selection instruction, and at the same time, obtains the model selection instruction input by humans through the preset IO port and outputs the manual selection instruction;

[0027] Obtain the priority information corresponding to the system's self-selection instruction and the manual selection instruction, conduct a comparative analysis, and output the first model selected from the model alternative pool based on the comparative analysis result as the preset model;

[0028] Obtain the data format requirements corresponding to the preset model and output the model format requirement information. At the same time, obtain the data formats corresponding to all the data in the historical operation data and output the data format information;

[0029] Based on the model format requirement information and the data format information, construct a format comparison table, and select a format conversion method that matches the format comparison table from the method database;

[0030] Perform format conversion on the historical operation data based on the format conversion method to obtain the first data that matches the model format requirement information;

[0031] Select a data partitioning method that matches the monitoring requirement information from the method database, and use the data partitioning method to partition the first data to obtain a historical data training data set, a historical data test data set, and a historical data validation data set;

[0032] Train and optimize the preset model based on the historical data training data set, the historical data test data set, and the historical data validation data set, and output the preset model that meets the preset performance conditions as the anomaly monitoring model.

[0033] Preferably, in step 4, it includes:

[0034] Based on the monitoring requirement information, select the corresponding evaluation indicators from the indicator database, and construct a first indicator set for real-time analysis of the hard disk and a second indicator set for predictive analysis of the hard disk;

[0035] Based on the first indicator set, and use the anomaly monitoring model to perform real-time analysis on the data to be analyzed and output the first analysis result;

[0036] At the same time, based on the second indicator set, use the anomaly monitoring model to perform predictive analysis on the data to be analyzed and output the second analysis result;

[0037] Based on the first analysis result, and construct a first change curve corresponding to each indicator in the first indicator set according to the preset first coordinate system, and construct a first curve graph based on each of the first change curves;

[0038] Meanwhile, based on the second analysis result and according to a preset second coordinate system, second variation curves corresponding to each index in the second index set are constructed, and a second curve graph is constructed based on each of the second variation curves;

[0039] Time alignment is performed on the first curve graph and the second curve graph, and comparative analysis is carried out to obtain a real-time - prediction curve comparison graph;

[0040] Based on the real-time - prediction curve comparison graph, the curves under the same index in the first index set and the second index set are analyzed to obtain a first sub-result for each index. Meanwhile, in combination with a preset index relationship graph, correlation analysis is carried out on the curves under different indexes in the first index set and the second index set to obtain a second sub-result for each index;

[0041] The anomaly monitoring model performs anomaly analysis on the first sub-results and the second sub-results at each time period in the real-time - prediction curve comparison graph, and outputs an anomaly analysis result;

[0042]

[0043] Among them, represents the anomaly analysis result value corresponding to the t-th time period in the real-time - prediction curve comparison graph; represents the total number of the same index existing in the first index set and the second index set in the t-th time period; represents the total number of the indexes that appear in both the first index set and the second index set in the t-th time period; represents the data offset corresponding to the i-th index in the t-th time period; represents the offset standard reference value corresponding to the i-th index in the t-th time period; represents the anomaly influence factor corresponding to the i-th index in the t-th time period; represents the data offset corresponding to the j-th index in the t-th time period; represents the offset standard reference value corresponding to the j-th index in the t-th time period; represents the cross-correlation coefficient between the j-th index and other indexes in the t-th time period;

[0044] In combination with a preset result - strategy comparison table, an anomaly response strategy matching the anomaly analysis result is obtained, and the hard disk is regulated based on the anomaly response strategy.

[0045] On the other hand, the present invention also provides a hard disk anomaly real-time monitoring system, including:

[0046] A data acquisition module, configured to obtain the running data of a hard disk in real time through a preset monitoring system and output the original data;

[0047] A preprocessing module, configured to preprocess the original data by using a preset preprocessing method and output the data to be analyzed;

[0048] A model training module, configured to extract features from the data to be analyzed, select historical running data matching the data to be analyzed from a historical database based on the extracted features, and train and optimize a preset model based on the historical running data to obtain an anomaly monitoring model;

[0049] An anomaly analysis module, configured to perform anomaly analysis and predictive analysis on the data to be analyzed by using the anomaly monitoring model, output an anomaly-predictive analysis result, and obtain an anomaly response strategy matching the anomaly-predictive analysis result by combining a preset result-strategy comparison table.

[0050] A method and system for real-time monitoring of hard disk anomalies provided by the present invention. The present invention obtains the running data of a hard disk in real time through a preset monitoring system. After preprocessing and feature extraction, an anomaly monitoring model is trained by using the data in a historical database, and anomaly analysis and predictive analysis are performed on the data to be analyzed. Finally, an anomaly-predictive analysis result is output, and a corresponding anomaly response strategy is determined by combining a preset result-strategy comparison table. The present invention can realize real-time monitoring and prediction of the running state of a hard disk, timely discover and handle potential hard disk problems, and ensure the stability of the system and the security of data. Description of the Drawings

[0051] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0052] Figure 1 is a flowchart of a method for real-time monitoring of hard disk anomalies provided by an embodiment of the present invention;

[0053] Figure 2 is a framework diagram of a system for real-time monitoring of hard disk anomalies provided by an embodiment of the present invention. Detailed Embodiments

[0054] To make the objectives, technical solutions and advantages of the present invention clearer, the following will clearly and completely describe the technical solutions in the present invention with reference to the accompanying drawings in the present invention. Obviously, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present invention without making creative efforts fall within the scope of protection of the present invention.

[0055] As Figure 1 shown, a method for real-time monitoring of hard disk anomalies provided by an embodiment of the present invention includes:

[0056] Step 1: Real-time obtain the operation data of the hard disk through a preset monitoring system and output the original data;

[0057] Step 2: Preprocess the original data using a preset preprocessing method and output the data to be analyzed;

[0058] Step 3: Extract features from the data to be analyzed, select historical operation data that matches the data to be analyzed from the historical database based on the extracted features, and train and optimize a preset model based on the historical operation data to obtain an anomaly monitoring model;

[0059] Step 4: Use the anomaly monitoring model to perform anomaly analysis and prediction analysis on the data to be analyzed, output the anomaly-prediction analysis result, and obtain an anomaly response strategy that matches the anomaly-prediction analysis result in combination with a preset result-strategy comparison table.

[0060] In this embodiment, the preset monitoring system: a system preset for monitoring the operation data of the hard disk;

[0061] In this embodiment, the original data: the data obtained in real time from the hard disk without processing, including temperature, read and write speed, SMART parameters, etc.;

[0062] In this embodiment, the preset preprocessing method: a method for preprocessing the original data to prepare the data for subsequent analysis, including data cleaning, data conversion, data normalization, etc.;

[0063] In this embodiment, the data to be analyzed: the data prepared for feature extraction and anomaly analysis after preprocessing;

[0064] In this embodiment, the historical database: a database storing the past operation data of the hard disk, used for comparison and analysis with the current data;

[0065] In this embodiment, the historical operation data: the data selected from the historical database that matches the data to be analyzed, used for training and optimizing the anomaly monitoring model;

[0066] In this embodiment, the preset model: a model trained and optimized based on historical operation data, used for anomaly monitoring;

[0067] In this embodiment, the anomaly monitoring model: a model obtained by training according to the preset model, used for performing anomaly analysis and predictive analysis on the data to be analyzed;

[0068] In this embodiment, the anomaly-prediction analysis result: the result obtained by performing anomaly analysis and prediction on the data to be analyzed;

[0069] In this embodiment, the preset result-strategy comparison table: a table containing the mapping relationship between the anomaly-prediction analysis result and the anomaly response strategy;

[0070] In this embodiment, the anomaly response strategy: specific response measures or strategies formulated for different anomaly situations, used to handle hard disk anomaly situations.

[0071] The implementation principle and beneficial effects of this embodiment: The present invention obtains the operation data of the hard disk in real time through a preset monitoring system. After preprocessing and feature extraction, an anomaly monitoring model is trained using the data in the historical database to perform anomaly analysis and predictive analysis on the data to be analyzed, and finally outputs the anomaly-prediction analysis result, and determines the corresponding anomaly response strategy in combination with the preset result-strategy comparison table. The present invention can realize real-time monitoring and prediction of the hard disk operation state, timely discover and handle potential hard disk problems, and ensure the stability of the system and the security of data.

[0072] For a method for real-time monitoring of hard disk anomalies provided by an embodiment of the present invention, in step 1, it includes:

[0073] Obtain the monitoring requirement information of the current hard disk, and in combination with the preset requirement-data comparison table, obtain the real-time operation data in the current hard disk that matches the monitoring requirement information;

[0074] At the same time, in combination with the device information of the current hard disk and the time stamp corresponding to the real-time operation data of the current hard disk, output the original data.

[0075] In this embodiment, the monitoring requirement information: refers to the specific information or parameters required for hard disk monitoring set by the user or the system, such as temperature, read / write speed, SMART parameters, accuracy, response time, etc.;

[0076] In this embodiment, the preset requirement-data comparison table: a comparison table containing the corresponding relationship between the monitoring requirement information and the data, used to determine the data to be obtained according to the monitoring requirement information;

[0077] In this embodiment, the real-time operation data: the unprocessed data obtained from the current hard disk, including the data that matches the monitoring requirement information;

[0078] In this embodiment, the device information includes information about the hard disk device itself, such as the model, capacity, interface type, etc. of the hard disk;

[0079] In this embodiment, the timestamp is a marker that records the time when the data is generated or acquired, and is used to identify the time sequence or chronological relationship of the data.

[0080] The implementation principle and beneficial effects of this embodiment: The present invention obtains the monitoring requirement information, and obtains the real-time operation data that matches the monitoring requirements according to the preset requirement-data comparison table. At the same time, by combining the device information of the hard disk and the timestamp, the original data can be obtained, which can ensure that the data related to the monitoring requirements is obtained from the hard disk, and the time information of the data can be traced. By monitoring the operation data of the hard disk in real time and combining the device information and the timestamp, the present invention can realize the real-time tracking and monitoring of the hard disk status, can detect hard disk anomalies in time, prevent data loss or hard disk failures, and improve the stability and reliability of the system.

[0081] In the method for real-time monitoring of hard disk anomalies provided by the embodiment of the present invention, before step 2, when using the preset preprocessing method to preprocess the original data, it includes:

[0082] Extract features from the monitoring requirement information, and construct a requirement feature set based on the extracted features;

[0083] Based on the requirement feature set, and in combination with the preset feature-method matching table, select the preset preprocessing method that matches the monitoring requirement information from the method database.

[0084] In this embodiment, the requirement feature set is a set of features extracted from the monitoring requirement information, and is used to describe the features of the hard disk monitoring requirements;

[0085] In this embodiment, the preset feature-method matching table is a table that contains the mapping relationship between the requirement features and the preset preprocessing methods, so as to select the preset preprocessing method that matches the monitoring requirement information;

[0086] In this embodiment, the method database is a database that contains various preset preprocessing methods, and is used to store the processing logics, algorithms or processes of different methods.

[0087] Implementation principle and beneficial effects of this embodiment: The present invention first extracts features from the monitoring requirement information to construct a requirement feature set. Then, according to the requirement feature set and in combination with a preset feature-method matching table, a preset preprocessing method matching the monitoring requirement information is selected from the method database. In this way, according to the characteristics of the hard disk monitoring requirements, an appropriate preprocessing method can be selected to process the original data, providing preparation for subsequent analysis and modeling. By using the preset preprocessing method to preprocess the original data, the present invention can improve the quality and usability of the data, providing a more reliable data basis for subsequent anomaly analysis and prediction.

[0088] In a hard disk anomaly real-time monitoring method provided by an embodiment of the present invention, in step 2, it further includes:

[0089] Match the original data with the preset preprocessing method, bind the original data and the preset preprocessing method that meet the preset matching conditions, and output a data-method matching table;

[0090] Based on the data-method matching table, use the preset preprocessing method to preprocess the corresponding original data and output the data to be analyzed.

[0091] In this embodiment, the preset matching condition: the condition used to determine whether the original data matches the preset preprocessing method can be specific data attributes, features or other rules, which are used to screen suitable preprocessing methods;

[0092] In this embodiment, the data-method matching table: used to record the matching relationship between the original data and the preset preprocessing method, bind the original data and the preset preprocessing method that meet the preset matching conditions, so as to facilitate subsequent data processing and analysis.

[0093] Implementation principle and beneficial effects of this embodiment: The present invention matches the original data with the preset preprocessing method, determines whether the matching condition is met according to the preset matching condition, binds the original data and the preset preprocessing method that meet the conditions, and outputs a data-method matching table. Then, based on the data-method matching table, use the preset preprocessing method to preprocess the corresponding original data and output the data to be analyzed. The present invention can ensure that appropriate preprocessing methods are adopted for the original data, making the data more analyzable and usable. At the same time, by matching the original data and the preset preprocessing method, the most suitable processing method can be selected according to the actual situation, improving the efficiency and accuracy of data processing.

[0094] A hard disk anomaly real-time monitoring method provided by an embodiment of the present invention extracts features from the data to be analyzed and selects historical operation data matching the data to be analyzed from the historical database based on the extracted features, including:

[0095] Extract features from the data to be analyzed, and construct a data feature set based on the extracted features;

[0096] Based on the data feature set, select historical operation data that meets the preset screening conditions from the historical database, and output the hard disk historical operation data.

[0097] In this embodiment, the data feature set: a set of features extracted from the data to be analyzed, used to describe the features of the data to be analyzed, which can be the operating state, performance indicators, or other relevant information of the hard disk;

[0098] In this embodiment, the preset screening conditions: the conditions for screening historical operation data, which can be specific data features, attributes, or other rules to ensure that the selected historical data matches the data to be analyzed;

[0099] In this embodiment, the hard disk historical operation data: refers to the operation data records of the past hard disk, including various operation information of the hard disk at different time periods, such as temperature, read / write speed, fault records, etc.

[0100] The implementation principle and beneficial effects of this embodiment: The present invention first extracts features from the data to be analyzed, constructs a data feature set, and then based on the data feature set, selects historical operation data that meets the preset screening conditions from the historical database and outputs the hard disk historical operation data. By analyzing the historical operation data, the present invention can comprehensively understand the operation of the hard disk, thereby better evaluating the state and potential problems of the current data to be analyzed. At the same time, selecting historical operation data that matches the data to be analyzed helps to establish a more accurate model and prediction, improving the accuracy and efficiency of anomaly monitoring.

[0101] A method for real-time monitoring of hard disk anomalies provided by an embodiment of the present invention trains and optimizes a preset model based on historical operation data to obtain an anomaly monitoring model, including:

[0102] Extract features from the historical operation data, and construct a historical data feature set based on the extracted features;

[0103] Based on the historical data feature set, and in combination with the feature-model mapping table, select a matching first model from the model database, and construct a model alternative pool based on at least two first models;

[0104] Obtain the first model selected by the system according to the preset recommendation algorithm, output the system self-selection instruction, and at the same time, obtain the model selection instruction input by the human through the preset IO port and output the manual selection instruction;

[0105] Obtain the priority information corresponding to the system self-selection instruction and the manual selection instruction, and conduct a comparative analysis. Output the first model selected from the model alternative pool based on the comparative analysis result as the preset model;

[0106] Obtain the data format requirements corresponding to the preset model, and output the model format requirement information. At the same time, obtain the data formats corresponding to all the data in the historical operation data, and output the data format information;

[0107] Based on the model format requirement information and the data format information, construct a format comparison table, and select a format conversion method that matches the format comparison table from the method database;

[0108] Perform format conversion on the historical operation data based on the format conversion method to obtain the first data that matches the model format requirement information;

[0109] Select a data partitioning method that adapts to the monitoring requirement information from the method database, and use the data partitioning method to partition the first data to obtain a historical data training data set, a historical data test data set, and a historical data validation data set;

[0110] Train and optimize the preset model based on the historical data training data set, the historical data test data set, and the historical data validation data set, and output the preset model that meets the preset performance conditions as the anomaly monitoring model.

[0111] In this embodiment, the historical data feature set: a feature set extracted from the historical operation data, used to describe the features of the historical data, which can be the running state of the hard disk, performance indicators, or other relevant information;

[0112] In this embodiment, the feature-model mapping table: a table containing the mapping relationship between data features and models, so as to select a suitable model for training and optimization to obtain the anomaly monitoring model;

[0113] In this embodiment, the model database: a database containing various models, used to store different types of models;

[0114] In this embodiment, the first model: a model selected from the model database, used to construct the model alternative pool;

[0115] In this embodiment, the model alternative pool: an alternative model set composed of at least two first models;

[0116] In this embodiment, the preset recommendation algorithm: a recommendation algorithm used for the system to perform model self-selection, which can be selected according to the historical data feature set and performance conditions;

[0117] In this embodiment, the system self-selection instruction: an instruction for the system to select the first model according to the preset recommendation algorithm;

[0118] In this embodiment, the preset IO port: an input / output port for receiving a model selection instruction input manually;

[0119] In this embodiment, the manual selection instruction: a model selection instruction input manually obtained through the preset IO port;

[0120] In this embodiment, the priority information: the priority information corresponding to the system self-selection instruction and the manual selection instruction, used to determine the finally selected model;

[0121] In this embodiment, the data format requirement: the data format requirement corresponding to the preset model;

[0122] In this embodiment, the data format information: the data format information corresponding to all the data in the historical operation data;

[0123] In this embodiment, the format comparison table: a table used to compare the data format requirements of the preset model with the actual format of the historical data for format conversion;

[0124] In this embodiment, the format conversion method: according to the information in the format comparison table, select a suitable method to perform data format conversion to meet the data format requirements of the preset model;

[0125] In this embodiment, the first data: the data that meets the data format requirements of the preset model obtained after format conversion;

[0126] In this embodiment, the data partitioning method: used to partition the first data into a historical data training dataset, a historical data test dataset, and a historical data validation dataset for training, testing, and validating the preset model;

[0127] In this embodiment, the historical data training dataset, the historical data test dataset, and the historical data validation dataset: are datasets used for training, testing, and validating the preset model respectively

[0128] In this embodiment, the preset performance condition: the preset model performance indicators or conditions used to evaluate whether the trained model meets the requirements, for example, response time, calculation accuracy, etc.

[0129] Implementation principle and beneficial effects of this embodiment: The present invention extracts features from historical operation data, constructs a historical data feature set based on the features, selects a suitable model from the model database, constructs a model alternative pool, and selects the first model according to a preset recommendation algorithm. The system selects the first model according to the preset recommendation algorithm and outputs a self-selection instruction, and at the same time receives a manual selection instruction, and determines the final preset model through comparative analysis. The present invention can select a suitable model for training and optimization according to the characteristics of historical data and model requirements, and finally output an anomaly monitoring model that meets the performance conditions, which can improve the accuracy and efficiency of anomaly monitoring, so as to timely detect abnormal conditions of the hard disk and ensure the stability of the system and the security of data.

[0130] A method for real-time monitoring of hard disk anomalies provided by an embodiment of the present invention, in step 4, includes:

[0131] Based on the monitoring requirement information, corresponding evaluation indicators are selected from the indicator database, and a first indicator set for real-time analysis of the hard disk and a second indicator set for predictive analysis of the hard disk are constructed;

[0132] Based on the first indicator set, the data to be analyzed is subjected to real-time analysis through an anomaly monitoring model, and a first analysis result is output;

[0133] At the same time, based on the second indicator set, the data to be analyzed is subjected to predictive analysis through an anomaly monitoring model, and a second analysis result is output;

[0134] Based on the first analysis result, and according to a preset first coordinate system, a first change curve corresponding to each indicator in the first indicator set is constructed, and a first curve graph is constructed based on each first change curve;

[0135] At the same time, based on the second analysis result, and according to a preset second coordinate system, a second change curve corresponding to each indicator in the second indicator set is constructed, and a second curve graph is constructed based on each second change curve;

[0136] The first curve graph and the second curve graph are time-aligned and subjected to comparative analysis to obtain a real-time-prediction curve comparison graph;

[0137] Based on the real-time-prediction curve comparison graph, the curves under the same indicator in the first indicator set and the second indicator set are analyzed to obtain a first sub-result for each indicator. At the same time, in combination with a preset indicator relationship graph, the curves under different indicators in the first indicator set and the second indicator set are subjected to correlation analysis to obtain a second sub-result for each indicator;

[0138] The first sub-result and the second sub-result at each time period in the real-time-prediction curve comparison graph are subjected to anomaly analysis through an anomaly monitoring model, and an anomaly analysis result is output;

[0139]

[0140] Among them, represents the abnormal analysis result value corresponding to the t-th period in the real-time - prediction curve comparison graph; represents the total number of the same indicators existing in the first indicator set and the second indicator set within the t-th period; represents the total number of indicators that have appeared in both the first indicator set and the second indicator set within the t-th period; represents the data offset corresponding to the i-th indicator within the t-th period; represents the offset standard reference value corresponding to the i-th indicator within the t-th period; represents the abnormal influence factor corresponding to the i-th indicator within the t-th period; represents the data offset corresponding to the j-th indicator within the t-th period; represents the offset standard reference value corresponding to the j-th indicator within the t-th period; represents the j-th indicator within the t-th period and other correlation coefficient between the indicators;

[0141] Combined with the preset result - strategy comparison table, obtain the abnormal coping strategy matching the abnormal analysis result, and regulate the hard disk based on the abnormal coping strategy.

[0142] In this embodiment, the indicator database: contains a set of evaluation indicators for real-time analysis and predictive analysis of the hard disk;

[0143] In this embodiment, the evaluation indicators: are the indicators selected from the indicator database for real-time analysis and predictive analysis of the hard disk, for example, transfer speed, seek time, bad track rate, read-write consistency, etc.;

[0144] In this embodiment, the first indicator set: is a set of evaluation indicators for real-time analysis;

[0145] In this embodiment, the second indicator set: is a set of evaluation indicators for predictive analysis;

[0146] In this embodiment, the first analysis result: is the real-time analysis result;

[0147] In this embodiment, the second analysis result: is the predictive analysis result;

[0148] In this embodiment, the preset first coordinate system: is a coordinate system for constructing the first change curve;

[0149] In this embodiment, the preset second coordinate system: is a coordinate system for constructing the second change curve;

[0150] In this embodiment, the first change curve: a curve constructed based on the data changes corresponding to the indicators in the first indicator set. For example, the real-time curve of the hard disk read speed;

[0151] In this embodiment, the second change curve: a curve constructed based on the predicted data changes corresponding to the indicators in the second indicator set. For example, the predicted curve of the hard disk read speed, etc.;

[0152] In this embodiment, the first curve graph: a curve graph obtained based on each first change curve;

[0153] In this embodiment, the second curve graph: a curve graph obtained based on each second change curve;

[0154] In this embodiment, time alignment: aligning the time axes of different data curves for effective comparative analysis;

[0155] In this embodiment, the real-time - prediction curve comparison graph: a comparison graph showing the results of real-time analysis and prediction analysis, which helps users understand the real-time status and future prediction of the hard disk performance;

[0156] In this embodiment, the first sub-result: the result obtained from the curve analysis under the same indicator;

[0157] In this embodiment, the second sub-result: the result obtained from the correlation analysis under different indicators;

[0158] In this embodiment, the anomaly analysis result: the result obtained by performing anomaly analysis on the first sub-result and the second sub-result at each time period in the real-time - prediction curve comparison graph, which is used to indicate possible anomalies of the hard disk.

[0159] The implementation principle and beneficial effects of this embodiment: The present invention selects evaluation indicators according to the monitoring requirement information, constructs the first and second indicator sets, performs real-time analysis and prediction analysis, and generates corresponding analysis results. Based on these results, change curves are constructed, time alignment and comparative analysis are performed to obtain the real-time - prediction curve comparison graph. The anomaly analysis result is calculated through formulas, and the anomaly response strategy is obtained according to the preset result - strategy comparison table, and finally the hard disk is regulated. By comprehensively considering the results of real-time analysis and prediction analysis, combined with anomaly analysis and anomaly response strategies, the present invention can timely detect hard disk anomalies and take corresponding measures, improving the accuracy and real-time performance of hard disk anomaly monitoring, thereby ensuring system stability and data security.

[0160] As Figure 2 shown, a hard disk anomaly real-time monitoring system provided by an embodiment of the present invention includes:

[0161] A data acquisition module, configured to obtain the running data of the hard disk in real time through a preset monitoring system and output the original data;

[0162] A preprocessing module, configured to preprocess the original data by using a preset preprocessing method and output the data to be analyzed;

[0163] A model training module, configured to extract features from the data to be analyzed, select historical operation data matching the data to be analyzed from the historical database based on the extracted features, and train and optimize a preset model based on the historical operation data to obtain an anomaly monitoring model;

[0164] An anomaly analysis module, configured to perform anomaly analysis and prediction analysis on the data to be analyzed by using the anomaly monitoring model, output an anomaly-prediction analysis result, and obtain an anomaly response strategy matching the anomaly-prediction analysis result by combining with a preset result-strategy comparison table.

[0165] The implementation principle and beneficial effects of this embodiment: The present invention obtains the operation data of the hard disk in real time through a preset monitoring system. After preprocessing and feature extraction, an anomaly monitoring model is trained by using the data in the historical database to perform anomaly analysis and prediction analysis on the data to be analyzed. Finally, an anomaly-prediction analysis result is output, and the corresponding anomaly response strategy is determined by combining with a preset result-strategy comparison table. The present invention can realize the real-time monitoring and prediction of the operation state of the hard disk, timely discover and handle potential hard disk problems, and ensure the stability of the system and the security of the data.

[0166] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A real-time monitoring method for hard disk anomalies, characterized in that, Including: Step 1: Obtain the running data of the hard disk in real time through a preset monitoring system, and output the original data; Step 2: Preprocess the original data by using a preset preprocessing method, and output the data to be analyzed; Step 3: Extract features from the data to be analyzed, select historical running data matching the data to be analyzed from the historical database based on the extracted features, and train and optimize a preset model based on the historical running data to obtain an anomaly monitoring model; Step 4: Use the anomaly monitoring model to perform anomaly analysis and predictive analysis on the data to be analyzed, output the anomaly-prediction analysis result, and obtain an anomaly response strategy matching the anomaly-prediction analysis result by combining a preset result-strategy comparison table, including: Based on the monitoring requirement information, select the corresponding evaluation indicators in the indicator database, and construct a first indicator set for real-time analysis of the hard disk and a second indicator set for predictive analysis of the hard disk; Based on the first indicator set, and perform real-time analysis on the data to be analyzed through the anomaly monitoring model, and output the first analysis result; Meanwhile, based on the second indicator set, perform predictive analysis on the data to be analyzed through the anomaly monitoring model, and output the second analysis result; Based on the first analysis result, and construct a first change curve corresponding to each indicator in the first indicator set according to a preset first coordinate system, and construct a first curve graph based on each first change curve; Meanwhile, based on the second analysis result, and construct a second change curve corresponding to each indicator in the second indicator set according to a preset second coordinate system, and construct a second curve graph based on each second change curve; Align the time of the first curve graph and the second curve graph, and perform comparative analysis to obtain a real-time-prediction curve comparison graph; Based on the real-time-prediction curve comparison graph, analyze the curves under the same indicator in the first indicator set and the second indicator set to obtain a first sub-result for each indicator. Meanwhile, combine a preset indicator relationship graph to perform correlation analysis on the curves under different indicators in the first indicator set and the second indicator set to obtain a second sub-result for each indicator; Perform anomaly analysis on the first sub-result and the second sub-result at each time period in the real-time-prediction curve comparison graph through the anomaly monitoring model, and output the anomaly analysis result; Among them, represents the abnormal analysis result value corresponding to the t-th period in the real-time - prediction curve comparison graph; represents the total number of the same indicators existing in the first indicator set and the second indicator set within the t-th period; represents the total number of indicators that have appeared in both the first indicator set and the second indicator set within the t-th period; represents the data offset corresponding to the i-th indicator within the t-th period; represents the offset standard reference value corresponding to the i-th indicator within the t-th period; represents the abnormal influence factor corresponding to the i-th indicator within the t-th period; represents the data offset corresponding to the j-th indicator within the t-th period; represents the offset standard reference value corresponding to the j-th indicator within the t-th period; represents the cross-correlation coefficient between the j-th indicator and other indicators within the t-th period; Combine a preset result-strategy comparison table, obtain an anomaly response strategy matching the anomaly analysis result, and regulate the hard disk based on the anomaly response strategy.

2. The real-time hard disk anomaly monitoring method according to claim 1, characterized in that In Step 1, it includes: Obtain the monitoring requirement information of the current hard disk, and combine a preset requirement-data comparison table to obtain the real-time running data in the current hard disk matching the monitoring requirement information; Meanwhile, combine the device information of the current hard disk and the time stamp corresponding to the real-time running data of the current hard disk, and output the original data.

3. The real-time hard disk anomaly monitoring method according to claim 2, characterized in that, Before the step of preprocessing the original data by using a preset preprocessing method in Step 2, it includes: Extract features from the monitoring requirement information, and construct a requirement feature set based on the extracted features; Based on the above demand feature set, and in combination with a preset feature-method matching table, a preset preprocessing method matching the monitoring demand information is selected from the method database.

4. A real-time hard disk anomaly monitoring method according to claim 1, characterized in that In step 2, it further includes: Matching the original data with the preset preprocessing method, binding the original data and the preset preprocessing method that meet the preset matching conditions, and outputting a data-method matching table; Based on the data-method matching table, using the preset preprocessing method to preprocess the corresponding original data, and outputting the data to be analyzed.

5. A real-time hard disk anomaly monitoring method according to claim 1, characterized in that, Performing feature extraction on the data to be analyzed, and based on the extracted features, selecting historical operation data matching the data to be analyzed from the historical database, including: Performing feature extraction on the data to be analyzed, and constructing a data feature set based on the extracted features; Based on the data feature set, selecting historical operation data that meets the preset screening conditions from the historical database, and outputting the hard disk historical operation data.

6. A real-time hard disk anomaly monitoring method according to claim 2, characterized in that Training and optimizing a preset model based on the historical operation data to obtain an anomaly monitoring model, including: Performing feature extraction on the historical operation data, and constructing a historical data feature set based on the extracted features; Based on the historical data feature set, and in combination with a feature-model mapping table, selecting a matching first model from the model database, and constructing a model alternative pool based on at least two of the first models; Obtaining the first model selected by the system according to a preset recommendation algorithm, outputting a system self-selection instruction, and at the same time, obtaining a model selection instruction manually input through a preset IO port, and outputting an artificial selection instruction; Obtaining the priority information corresponding to the system self-selection instruction and the artificial selection instruction, and performing a comparative analysis, and outputting the first model selected from the model alternative pool based on the comparative analysis result as the preset model; Obtaining the data format requirements corresponding to the preset model, outputting model format requirement information, and at the same time, obtaining the data formats corresponding to all the data in the historical operation data, and outputting data format information; Based on the model format requirement information and the data format information, constructing a format comparison table, and selecting a format conversion method matching the format comparison table from the method database; Based on the format conversion method, performing format conversion on the historical operation data to obtain the first data matching the model format requirement information; Selecting a data partitioning method matching the monitoring demand information from the method database, and using the data partitioning method to partition the first data to obtain a historical data training data set, a historical data test data set, and a historical data verification data set; Training and optimizing the preset model based on the historical data training data set, the historical data test data set, and the historical data verification data set, and outputting the preset model that meets the preset performance conditions as the anomaly monitoring model.

7. A real-time hard disk anomaly monitoring system, characterized in that, Including: A data acquisition module, configured to obtain the operation data of the hard disk in real time through a preset monitoring system, and output the original data; A preprocessing module, configured to preprocess the original data by using a preset preprocessing method, and output the data to be analyzed; A model training module, which is used to extract features from the data to be analyzed, select historical operation data that matches the data to be analyzed from a historical database based on the extracted features, and train and optimize a preset model based on the historical operation data to obtain an anomaly monitoring model; An anomaly analysis module, which is used to perform anomaly analysis and predictive analysis on the data to be analyzed by using the anomaly monitoring model, output an anomaly-prediction analysis result, and obtain an anomaly response strategy that matches the anomaly-prediction analysis result by combining a preset result-strategy comparison table; Among them, the anomaly analysis module is used for: Based on the monitoring requirement information, select corresponding evaluation indicators in the index database, and construct a first index set for real-time analysis of the hard disk and a second index set for predictive analysis of the hard disk; Based on the first index set, and perform real-time analysis on the data to be analyzed through the anomaly monitoring model, and output a first analysis result; At the same time, based on the second index set, perform predictive analysis on the data to be analyzed through the anomaly monitoring model, and output a second analysis result; Based on the first analysis result, and construct a first change curve corresponding to each index in the first index set according to a preset first coordinate system, and construct a first curve graph based on each of the first change curves; At the same time, based on the second analysis result, and construct a second change curve corresponding to each index in the second index set according to a preset second coordinate system, and construct a second curve graph based on each of the second change curves; Align the time of the first curve graph and the second curve graph, and perform a comparative analysis to obtain a real-time-prediction curve comparison graph; Based on the real-time-prediction curve comparison graph, analyze the curves under the same index in the first index set and the second index set to obtain a first sub-result under each index. At the same time, combine a preset index relationship graph to perform a correlation analysis on the curves under different indexes in the first index set and the second index set to obtain a second sub-result under each index; Perform anomaly analysis on the first sub-result and the second sub-result in each time period in the real-time-prediction curve comparison graph through the anomaly monitoring model, and output an anomaly analysis result; Among them, represents the abnormal analysis result value corresponding to the t-th period in the real-time - prediction curve comparison graph; represents the total number of the same indicators existing in the first indicator set and the second indicator set within the t-th period; represents the total number of indicators that have appeared in both the first indicator set and the second indicator set within the t-th period; represents the data offset corresponding to the i-th indicator within the t-th period; represents the offset standard reference value corresponding to the i-th indicator within the t-th period; represents the abnormal influence factor corresponding to the i-th indicator within the t-th period; represents the data offset corresponding to the j-th indicator within the t-th period; represents the offset standard reference value corresponding to the j-th indicator within the t-th period; represents the j-th indicator within the t-th period and other correlation coefficient between the indicators; Combine a preset result-strategy comparison table, obtain an anomaly response strategy that matches the anomaly analysis result, and perform regulation on the hard disk based on the anomaly response strategy.

Images