Disk failure prediction method, device, readable storage medium and program product

Abstract

In the field of computer technology, this application discloses a disk failure prediction method, device, readable storage medium, and program product. The method includes: obtaining multiple pieces of test data information and a disk health score corresponding to each piece of test data information; using the disk health score to determine the attribution of each piece of test data information to obtain predicted data and direct estimation data; wherein the prediction difficulty of the predicted data is higher than that of the direct estimation data; using the disk health score corresponding to the test data information in the direct estimation data to determine a first fault prediction result; inputting the predicted data into a target model for fault prediction to obtain a second fault prediction result. The technical effect of this application is that it can not only improve the efficiency of disk failure prediction, but also improve the accuracy of fault prediction.

Description

Technical Field

[0001] The present application relates to the field of computer application technology, and in particular to a disk failure prediction method, device, readable storage medium, and program product. Background Art

[0002] Data centers provide powerful computing and storage capabilities for services across various industries. Data centers utilize a vast number of storage disks. Therefore, ensuring disk reliability and minimizing server downtime and losses caused by disk failures are becoming increasingly important.

[0003] Currently, solutions to disk failures fall into two main categories. One involves using software technology to provide data redundancy and other features to prevent data loss caused by failures. The other involves monitoring indicators related to the hard drive's health and applying specific strategies to analyze them to determine the drive's health status. The second category primarily includes two strategies. One involves developing hard drive diagnostic rules based on existing expert knowledge and performing predictive analysis based on the drive's real-time status. However, this approach often fails to accurately predict results. The other involves using machine learning algorithms to train a prediction model on hard drive data. This approach, however, incurs high computational overhead and is relatively time-consuming.

[0004] In summary, how to make disk failure prediction more efficient and accurate is a technical problem that those skilled in the art urgently need to solve. Summary of the Invention

[0005] The purpose of this application is to provide a disk failure prediction method, device, readable storage medium and program product to achieve efficient and accurate disk failure prediction.

[0006] To solve the above technical problems, this application provides the following technical solutions:

[0007] A disk failure prediction method, comprising:

[0008] Get multiple pieces of test data and the disk health score corresponding to each piece of test data;

[0009] The disk health score is used to determine the ownership of each piece of detection data information, and predictive data and direct estimation data are obtained; wherein the prediction difficulty of the predictive data is higher than that of the direct estimation data;

[0010] Determine a first fault prediction result using a disk health score corresponding to the detection data information in the direct estimation data;

[0011] The prediction data is input into the target model for fault prediction to obtain a second fault prediction result.

[0012] Preferably, it also includes:

[0013] Comparing the disk replacement record with the second fault prediction result to obtain a comparison result;

[0014] In the process of optimizing and training the target model using the training data, rewards and punishments are given based on the comparison results.

[0015] Preferably, in the process of optimizing and training the target model using the training data, rewards and penalties are performed based on the comparison results, including:

[0016] Determining reward and punishment values ​​using the comparison results;

[0017] In the process of optimizing the target model using the training data, the reward and penalty values ​​are used to indicate the optimization direction of the target model.

[0018] Preferably, determining the reward or punishment value using the comparison result includes:

[0019] If the comparison result corresponds to a match between the disk replacement record and the second fault prediction result, determining a preset reward value as the reward or penalty value;

[0020] In a case where the comparison result corresponds to that the disk replacement record does not match the second fault prediction result, a preset penalty value is determined as the reward and penalty value.

[0021] Preferably, when the comparison result corresponds to a match between the disk replacement record and the second fault prediction result, determining a preset reward value as the reward or penalty value includes:

[0022] In a case where the comparison result corresponds to that the disk replacement record matches the second fault prediction result, if the disk replacement record is a disk replacement, determining a preset first reward value as the reward or penalty value;

[0023] In the case where the comparison result corresponds to that the disk replacement record matches the second fault prediction result, if the disk replacement record indicates that the disk has not been replaced, determining a preset second reward value as the reward or penalty value;

[0024] Wherein, the first reward value is greater than the second reward value.

[0025] Preferably, in the process of optimizing the target model using the training data, using the reward and penalty values ​​to indicate the optimization direction of the target model includes:

[0026] In the process of optimizing the target model using the training data, substituting the reward and penalty values ​​into the advantage function to calculate the difference between the expected reward and the predicted reward;

[0027] The target model is updated based on the difference.

[0028] Preferably, the prediction data is input into a target model for fault prediction to obtain a second fault prediction result, including:

[0029] Add manufacturer information and disk attribute information to each piece of detection data information belonging to the predicted data;

[0030] After completing the data augmentation, each piece of detection data information is converted into a vector;

[0031] Group the obtained vectors to obtain a vector group;

[0032] The vector group is input into the target model for fault prediction to obtain the second fault prediction result; wherein the target model is a model that has learned the fault prediction capabilities of disks of different manufacturers and different attributes.

[0033] Preferably, inputting the vector group into the target model for fault prediction to obtain the second fault prediction result includes:

[0034] Inputting the vector group into the target model, and using the information cross-learning module in the target model to perform cross-learning between different feature dimensions in the vector group to obtain effective features;

[0035] Using the time series information module in the strategy network to sort out the effective features to obtain statistical characteristics;

[0036] The statistical characteristics are normalized using a normalization layer in the strategy network to obtain the second fault prediction result.

[0037] Preferably, the effective features are sorted using the time sequence information module in the strategy network to obtain statistical characteristics, including:

[0038] Determine the dependency relationship between different positions in the effective features using the encoder in the temporal information module to obtain a global feature representation;

[0039] The residual network in the temporal information module is used to perform residual processing on the global feature representation to obtain the statistical characteristics.

[0040] Preferably, before using the disk health score to determine the ownership of each piece of detection data information and obtaining the predicted data and the direct estimation data, the method further includes:

[0041] Searching for invalid indicators in each piece of detection data information, and if an invalid indicator is found, increasing the invalidity index of the piece of detection data information by one; wherein each piece of detection data information includes multiple indicators;

[0042] If the invalidity index exceeds a preset threshold, the detection data information is deleted.

[0043] Preferably, if the invalidity index exceeds a preset threshold, deleting the piece of detection data information includes:

[0044] If the invalidity indicator exceeds a preset threshold, after obtaining the disk information corresponding to the detection data information, the detection data information is deleted;

[0045] The disk information is used to output a prompt message indicating abnormal data collection.

[0046] Preferably, obtaining multiple pieces of detection data information and the disk health score corresponding to each piece of detection data information includes:

[0047] Using a disk self-test tool to test the disk, a plurality of test data information is obtained; wherein a piece of test data information includes a plurality of indicator data;

[0048] Obtaining the indicator threshold set corresponding to each piece of detection data information, and comparing the current state value of each indicator in the detection data information with the corresponding threshold in the indicator threshold set;

[0049] Based on the status comparison result, the disk health score corresponding to the detection data information is determined.

[0050] A disk failure prediction device, comprising:

[0051] A data acquisition unit is used to acquire multiple pieces of detection data information and a disk health score corresponding to each piece of detection data information;

[0052] a data screening unit, configured to determine the attribution of each piece of detection data information using the disk health score, and obtain predicted data and directly estimated data; wherein the predicted data has a higher prediction difficulty than the directly estimated data;

[0053] A first fault prediction unit is configured to determine a first fault prediction result by using a disk health score corresponding to the detection data information in the direct evaluation data;

[0054] The second fault prediction unit is used to input the prediction data into the target model to perform fault prediction and obtain a second fault prediction result.

[0055] An electronic device, comprising:

[0056] memory for storing computer programs;

[0057] A processor is configured to implement the steps of the above disk failure prediction method when executing the computer program.

[0058] A readable storage medium stores a computer program, which implements the steps of the disk failure prediction method when executed by a processor.

[0059] A computer program product includes a computer program / instruction, which, when executed by a processor, implements the steps of the above disk failure prediction method.

[0060] Apply the method provided in the embodiment of the present application to obtain multiple detection data information and the disk health score corresponding to each detection data information; use the disk health score to determine the attribution of each detection data information, and obtain predicted data and direct estimation data; wherein, the prediction difficulty of the predicted data is higher than that of the direct estimation data; use the disk health score corresponding to the detection data information in the direct estimation data to determine the first fault prediction result; input the predicted data into the target model for fault prediction to obtain the second fault prediction result.

[0061] In the present application, when multiple pieces of detection data information and the disk health score corresponding to each piece of detection data information are obtained. For the disk health score, the score size is related to the prediction difficulty. For example, the more extreme the score, the more accurate the fault prediction result. Therefore, the attribution of each piece of detection data information can be determined based on the disk health score, thereby obtaining prediction data and direct estimation data. After the attribution division is completed, the prediction difficulty of the obtained prediction data is higher than that of the direct estimation data. Therefore, the detection data information in the direct estimation data can be directly based on the corresponding disk health score to obtain a first fault prediction result. For prediction data with high prediction difficulty, the target model is used to perform fault prediction, thereby obtaining a second fault prediction result. That is to say, for multiple pieces of detection data information to be predicted, the prediction difficulty can be screened and classified by the disk health score. For the part belonging to the direct estimation data, the disk fault prediction is directly performed based on the disk health score, and the first fault prediction result can be quickly obtained. For the part belonging to the prediction data, the fault prediction is performed with the help of the target model, thereby obtaining a second fault prediction result. Because the target model prediction is not simply based on the disk health score, but is directly based on the specific content of the detection data information, and the target model has been trained in advance, its accuracy can be higher than fault prediction based directly on the disk health score.

[0062] The technical effect of the present application is as follows: In general, relatively accurate data can be obtained based on the disk health score. Therefore, by dividing the detection data information into different categories based on the disk health score, a large amount of direct estimation data and a small amount of prediction data can be obtained. For a large amount of direct estimation data, an accurate first fault prediction result can be quickly determined based on the disk health score. For a small amount of prediction data that is difficult to obtain an accurate result based on the disk health score, a fault prediction is performed based on the target model to obtain an accurate second fault prediction result. It can be seen that the present application can not only improve the efficiency of disk fault prediction, but also improve the accuracy of fault prediction.

[0063] Accordingly, the embodiments of the present application also provide a disk failure prediction device, equipment, readable storage medium and computer program product corresponding to the above disk failure prediction method, which have the above technical effects and are not repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0065] Figure 1 This is a flowchart of an implementation method of a disk failure prediction method in an embodiment of the present application;

[0066] Figure 2 A schematic diagram of a strategy network in a target model in an embodiment of the present application;

[0067] Figure 3 This is a structural diagram of a disk failure prediction device in an embodiment of the present application;

[0068] Figure 4 A schematic diagram of a disk failure prediction system according to an embodiment of the present application;

[0069] Figure 5 This is a schematic structural diagram of an electronic device according to an embodiment of the present application;

[0070] Figure 6 This is a schematic diagram of the specific structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0071] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific embodiments. Obviously, the embodiments described are only a part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making any creative efforts are within the scope of protection of the present application.

[0072] Please refer to Figure 1 , Figure 1 This is a flowchart of a disk failure prediction method according to an embodiment of the present application, which includes the following steps:

[0073] S101: Obtain multiple pieces of detection data information and a disk health score corresponding to each piece of detection data information.

[0074] In the present application, the detection data information and its corresponding disk health score can be obtained by directly reading from the storage medium; the detection data information and its corresponding disk health score can also be obtained by receiving data; multiple detection data information can also be obtained first, and then scored according to the scoring strategy to obtain the disk health score; multiple detection data information can also be collected by calling some detection tools, and after obtaining the multiple detection data information, they can be scored to obtain the disk health score.

[0075] To make disk failure prediction more reliable, a piece of test data can include multiple disk-related metrics. In the acquired test data, one disk can correspond to one or more pieces of test data. One piece of test data corresponds to one disk.

[0076] In a specific embodiment of the present application, obtaining multiple pieces of test data information and a disk health score corresponding to each piece of test data information includes:

[0077] Step 1: Use a disk self-test tool to test the disk and obtain multiple test data information; wherein, one test data information includes multiple indicator data;

[0078] Step 2: Obtain the indicator threshold value set corresponding to each piece of detection data information, and compare the current state value of each indicator in the detection data information with the corresponding threshold value in the threshold value set;

[0079] Step 3: Determine the disk health score corresponding to the detection data information based on the status comparison result.

[0080] For ease of description, the above three steps are combined and explained below.

[0081] In this embodiment, the disk self-test tool may be a tool capable of collecting disk index data. The following description will be made using SMART (Self-Monitoring Analysis And Reporting Technology) as an example.

[0082] According to the set frequency (Freq1), the relevant SMART information (detection data information) of the disk is continuously collected from the server. The 10 indicator data with the highest correlation with the disk failure can be selected, for example: (001) Raw Read Error Rate, (004) Start / Stop Count, (005) Relocated Sector Count, (009) Power-On Time Count, (010) Spin up Retry Count, (011) Calibration Retry Count, (012) Power Cycle Count, (194) Temperature, (199) ULTRAATA CRC Error Rate, (200) Write Error Rate.

[0083] Among them, 001: underlying data read error rate, Raw Read Error Rate;

[0084] 004: Start / Stop Count;

[0085] 005: Relocated Sector Count;

[0086] 009: Power-On Time Count (POH);

[0087] 010: Spinup Retry Count (i.e., the number of hard disk spindle motor start retries).

[0088] 011: Disk calibration retry count, Calibration Retry Count;

[0089] 012: Number of times the disk is powered on, Power Cycle Count;

[0090] 194: Temperature;

[0091] 199: Parity error rate, ULTRAATACRC Error Rate;

[0092] 200: Write error rate, Write ErrorRate.

[0093] In practical applications, indicators can be replaced or the weight of an indicator can be increased according to actual conditions.

[0094] When scoring, a heuristic preliminary disk fault diagnosis strategy (HS, Heuristic Strategy) can be used to score the collected data. Specifically: Set the initial score Score1 (disk health score) to 0. According to the disk model, you can select the indicator threshold set of the corresponding model from the expert knowledge base, and then compare the current status value of the indicator with the threshold of the indicator in the knowledge base (if the threshold of the model is missing, a similar model from the same manufacturer can be used as a reference). If the current value of the indicator is not within the health threshold range, Score1 is determined to be minus a specified value, such as 5 (of course, other values ​​can also be used in actual applications); if the current value of the indicator is within the health range, Score1 is added to the specified value, such as 10 (of course, other values ​​can also be used in actual applications). Compare all indicator data in a detection data information with the corresponding threshold, and add or subtract the disk health score to obtain the final disk health score. The calculation formula for the disk health score (Score) is as follows:

[0095]

[0096] Among them, score i is the score of the i-th indicator data, S i It is an addition or subtraction operator, and the addition or subtraction is determined based on the comparison between the indicator data and the threshold.

[0097] S102: Use the disk health score to determine the ownership of each piece of detection data information, and obtain predicted data and direct estimation data.

[0098] Among them, the difficulty of predicting the predicted data is higher than that of the directly estimated data. The directly estimated data and the predicted data are equivalent ion sets.

[0099] In this embodiment, the test data needed for fault prediction using the target model is used as prediction data, while the test data that can directly draw accurate conclusions based on the disk health score is used as direct estimation data. Both the prediction data and the direct estimation data can be used as training data for further optimization and training of the target model.

[0100] The more extreme the disk health score, the more accurate the failure prediction based on that disk health score. For example, the higher the disk health score exceeds the health threshold, the more accurately the disk is judged to be healthy. Conversely, the lower the disk health score falls below the health threshold, the more accurately the disk is judged to be faulty.

[0101] Based on this, in this embodiment, the prediction difficulty of each detection data information can be determined based on the disk health score, and the detection data information with a high accuracy rate of fault judgment directly determined based on the score can be determined as direct estimation data, and the detection data information with a low accuracy rate of fault judgment determined based on the score can be determined as prediction data.

[0102] Therefore, after obtaining the disk health score, the attribution of each piece of test data can be determined based on the mapping between the disk health score and the difficulty of determining disk failure. For example, disk health score ranges can be determined for both direct estimation data and predicted data. Based on the disk health score, the attribution of each piece of test data can be directly determined.

[0103] In a specific embodiment of the present application, the health level of the disk is determined based on the disk health score;

[0104] According to the correspondence between the disk health level and various types of data, the ownership of each detection data information is determined to obtain training data, prediction data and direct estimation data.

[0105] You can define the health level of the disk, which is divided into four levels and corresponding processing strategies.

[0106] Level 1: Damaged disk, meaning it cannot be read or written normally. The disk is marked as damaged and the damage time and SMART information for a period of time before the damage are reported.

[0107] Level 2, high-risk disk, generates a high-risk disk alarm, records the current and previous disk information and reports it to the data center;

[0108] Level 3, general disk, generates a general disk warning, records the disk information at this moment and in the past period of time, and reports it to the data center.

[0109] Level 4, healthy disk, no alarm is generated.

[0110] The main purpose of collecting the SMART information of the problem disk for a period of time is to facilitate the subsequent learning of the algorithm model. The data center needs to use the reported data as training data.

[0111] According to the mapping relationship that the more normal the disk indicator data is, the higher the disk health score is, in this embodiment, the relationship between the score and the disk level is determined as follows:

[0112] Disk health scores above 90 indicate a health level of 4. This type of disk data is included in subsequent model training, but the model does not need to determine its health; instead, the heuristic strategy determines its health status. This approach effectively filters health data and reduces the decision-making pressure on the machine learning algorithm.

[0113] The disk health score is between 90 and 70, and the health level is 3. This type of disk data information is involved in subsequent model training and model decision-making.

[0114] The disk health score is between 70 and 50, and the health level is 2. This type of disk data information is involved in subsequent model training and model decision-making.

[0115] The disk health score is below 50, and the health level is 1. This type of disk data information participates in subsequent model training and does not need to participate in the model decision-making of subsequent models (the level can be adjusted according to the score classification).

[0116] That is, disk data with health levels of 1 and 4 is considered direct estimation data, while disk data with health levels of 2 and 3 is considered predicted data. Data with health levels of 1 to 4 is considered training data. Furthermore, data from the previous period corresponding to disks with health levels of 1 to 3 can also be considered training data.

[0117] In a specific embodiment of the present application, the disk health score is used to determine the ownership of each piece of detection data information, and before obtaining the predicted data and the direct estimation data, the following steps are also included:

[0118] Step 1: Search for invalid indicators in each piece of detection data information, and if an invalid indicator is found, increase the invalidity index of the piece of detection data information by one; wherein each piece of detection data information includes multiple indicators;

[0119] Step 2: If the invalidity index exceeds the preset threshold, the detection data information is deleted.

[0120] For ease of description, the above steps are combined and explained below.

[0121] Considering that in actual applications, the collection of a certain indicator may be abnormal due to various reasons, such as the collection of a certain indicator is empty or the collection fails. When there are too many indicator collection abnormalities in a piece of detection data information, it means that the detection data information does not have the function of disk health status assessment, and it can be deleted at this time. Specifically, an invalid index (Num1) can be set for each piece of detection data information, with its initial value being 0. After each unnecessary indicator with collection abnormality is found, it is added by 1. If the invalid index exceeds a preset threshold value such as 3 (of course, other values ​​can also be used in actual applications), the detection data information can be deleted.

[0122] The main function of Num1 here is to observe whether the characteristics of the sampled data are sufficient to represent the health status of the disk. If Num1 is greater than 3, it is considered that the information cannot assist in accurate prediction.

[0123] In a specific embodiment of the present application, if the invalidity index exceeds a preset threshold, deleting the detection data information includes:

[0124] If the invalidity index exceeds the preset threshold, the detection data information is deleted after obtaining the disk information corresponding to the detection data information;

[0125] Use disk information to output prompt information of data collection abnormalities.

[0126] In other words, when a piece of test data is found to be abnormally collected, the corresponding disk information can be obtained first and then deleted. In addition, the disk information can be used to output a prompt message indicating data collection anomalies to facilitate subsequent location of the disk with abnormal collection.

[0127] S103: Determine a first fault prediction result by using the disk health score corresponding to the detection data information in the direct estimation data.

[0128] For detection data in direct estimation data, the first fault prediction result can be directly derived based on the corresponding disk health score. For example, if the score is greater than a certain value, the disk is considered healthy and does not need to be replaced. If the score is less than a certain value, the disk is considered faulty and needs to be replaced.

[0129] The first fault prediction result may be a conclusion of whether the disk is faulty, or may include a suggestion of whether the disk should be replaced.

[0130] S104: Input the predicted data into the target model to perform fault prediction and obtain a second fault prediction result.

[0131] In an embodiment, a target model may be pre-trained or trained during use, and the target model may perform fault prediction based on input prediction data, thereby obtaining a second fault prediction result.

[0132] In this embodiment, the specific structure and training process of the target model are not limited.

[0133] In a specific embodiment of the present application, the prediction data is input into the target model for fault prediction to obtain a second fault prediction result, including:

[0134] Step 1: Add manufacturer information and disk attribute information to each piece of detection data belonging to the predicted data;

[0135] Step 2: After completing the data addition, convert each piece of detection data information into a vector;

[0136] Step 3: Group the obtained vectors to obtain a vector group;

[0137] Step 4: Input the vector group into the target model for fault prediction to obtain a second fault prediction result; wherein the target model is a model that has learned the fault prediction capabilities of disks of different manufacturers and different attributes.

[0138] For ease of description, the above steps are combined and explained below.

[0139] In this embodiment, a reinforcement learning model can be used as the core model of secondary training (optimization training).

[0140] In order to facilitate the target model to predict disk failures based on the detection data information, manufacturer information and disk attribute information can be added to each detection data information in the prediction data. Then, each detection data information after the data addition is converted into a vector. In order to ensure the optimal efficiency of the target model, the obtained vectors can be grouped, and the number of vectors in each group of vectors is controlled within Size1 (size). The Size1 can be processed based on different numbers of vector groups, and the corresponding performance is statistically analyzed to select the optimal number. In this way, the number of states that can be observed each time is limited to a certain range, such as the number of vectors in each group is Size1, which is the maximum number of SMART information. If the number of vectors at the current moment is less than Size1, empty nodes (all-zero vectors) are used to fill this group of vectors; if it is greater than Size1, the first Size1 inputs are selected for training according to the first-come, first-served principle, and subsequent information waits.

[0141] After completing the vector grouping, the vector group can be directly input into the target model for fault prediction to obtain the second fault prediction result. It should be noted that the target model is a model that has learned the fault prediction capabilities of disks of different manufacturers and different attributes.

[0142] In a specific embodiment of the present application, the above step 4, inputting the vector group into the target model for fault prediction to obtain a second fault prediction result, includes:

[0143] Step 1: Input the vector group into the target model, and use the information cross-learning module in the target model to perform cross-learning between different feature dimensions in the vector group to obtain effective features;

[0144] Step 2: Use the temporal information module in the strategy network to sort out the effective features and obtain statistical characteristics;

[0145] Step 3: Use the normalization layer in the strategy network to normalize the statistical characteristics to obtain the second fault prediction result.

[0146] Among them, step 2 uses the temporal information module in the policy network to organize the effective features and obtain statistical characteristics, including:

[0147] Using the encoder in the temporal information module, the dependencies between different positions in the effective features are determined to obtain the global feature representation;

[0148] The residual network in the temporal information module is used to perform residual processing on the global feature representation to obtain statistical characteristics.

[0149] For ease of description, the above steps are combined and explained below.

[0150] In this embodiment, the model algorithm architecture of the target model includes a network model, which is a policy network and a value network. The policy network is used to learn the current SMART sequence information and perform training and decision-making. The value network adjusts the policy network based on the decision of the policy network and the reward returned by the environment, guiding the agent to update its next action in the correct direction. The input of the model is a group of SMART information vectors, each of which contains Size1 information. In order to better enable the agent to learn the temporal change characteristics of the SMART information status of the disk before failure, an encoder module can be introduced in the policy network. The settings of the two networks are described in detail below.

[0151] Strategy network such as Figure 2 First, the information of the input vector group and the updated environmental information after the decision is made, Info={i0,i1,…,i A}, Info∈R A*B,The vector group set is labeled as Info, i represents a single state, A is the length of the vector group, and B is the number of features of the vector, that is, the number of attributes of SMART information. The internal structure of the policy network includes an information cross-learning module and a temporal information module.

[0152] Among them, the information cross-learning module adopts a two-layer MLP (multi-layer perceptron) structure, with 32 neurons in each layer, to perform cross-learning between different dimensions of feature vectors, learn effective features and pass them to the next module.

[0153] The time series information module can use an encoder and a residual network. The encoder is mainly used to learn the dependencies between different positions in the sequence, thereby forming a global feature representation. The residual is the residual operation of the front and back vectors of the encoder layer, which can encode the statistical characteristics of the entire data set and avoid bias towards a specific token in the sequence. That is, the role of the residual network is to ensure that the previous information is not forgotten during the training process. The role of the Class_Token (category feature) in it is to take the information of the 0th dimension as the feature information extracted by the network, encode the statistical characteristics of the entire data set, and avoid bias towards a specific token (feature) in the sequence. The final normalization layer (which contains a normalization function and a Softmax function) will output a set of probabilities about the vector group, and choose whether to replace the disk based on this, that is, the second fault prediction result is obtained. The probability calculation formula is as follows:

[0154]

[0155] Where yi represents the i-th category, K represents the total number of categories, e represents the exponential function converted from a single category, and the denominator on the right side of the equal sign is the sum of all category exponents, ensuring that the total probability is 1, thereby converting it into a valid probability distribution. o(yi) represents the calculated probability corresponding to the category.

[0156] In a specific embodiment of the present application, the target model can be further optimized and trained in the use environment to further improve its prediction accuracy. The optimization training process includes:

[0157] Step 1: Compare the disk replacement record with the second fault prediction result to obtain a comparison result.

[0158] Step 2: When optimizing the target model using the training data, rewards and punishments are given based on the comparison results.

[0159] For ease of description, the above two steps are combined for explanation below.

[0160] A disk status update module can be configured. If an administrator replaces a disk, the module removes the disk's alarm information from the alarm list and re-adds it to the environment, collecting information while the fault prediction model predicts the health level of the new disk. The module can also obtain disk replacement records.

[0161] After obtaining the disk replacement record, the second fault prediction result can be compared with the disk replacement record to obtain a comparison result. The comparison result can indicate whether the model prediction is accurate. Generally, if the prediction is accurate, the second fault prediction result indicates that the disk is faulty and requires replacement, and the disk replacement record corresponds to the replacement disk. If the second fault prediction result indicates that the disk is normal and does not require replacement, the disk replacement record corresponds to the unreplaced disk. An inaccurate prediction means that the second fault prediction result does not match the disk replacement record.

[0162] It's important to note that the second fault prediction result is a partial prediction, while the disk replacement record corresponds to the global replacement record. Therefore, when comparing, only the relevant disk replacement records corresponding to the second fault prediction result can be compared. For the disk replacement records not included in the second fault prediction result, the accuracy of the model's prediction is not compared.

[0163] In order to optimize the target model, the target model can be trained regularly or irregularly, and the training can be performed in an offline training manner.

[0164] In this embodiment, the training data is the most comprehensive, so it can be used to optimize the target model. Since disk problems are common in real-world scenarios, the proportion of different prediction results in the training samples is uneven. To ensure that the target model can effectively learn to judge low-probability events, rewards and penalties are applied based on the comparison results in this embodiment to guide the optimization direction of the model.

[0165] Specifically, based on the comparison results and combined with the reward function, the optimization training direction of the target model can be guided.

[0166] In a specific embodiment of the present application, during the process of optimizing the target model using the training data, rewards and penalties are given based on the comparison results, including:

[0167] Step 1: Use the comparison results to determine the reward and punishment values;

[0168] Step 2: When optimizing the target model using the training data, the reward and penalty values ​​are used to indicate the optimization direction of the target model.

[0169] Among them, the reward and punishment values ​​are determined by using the comparison results, including:

[0170] Step 1: When the disk replacement record corresponding to the comparison result matches the second fault prediction result, a preset reward value is determined as a reward or penalty value;

[0171] Step 2: If the disk replacement record corresponding to the comparison result does not match the second fault prediction result, the preset penalty value is determined as the reward or penalty value.

[0172] Wherein, step 1, when the comparison result corresponds to the disk replacement record and the second fault prediction result, determining the preset reward value as the reward or penalty value, includes:

[0173] In the case that the comparison result corresponds to a disk replacement record that matches the second fault prediction result, if the disk replacement record is a disk replacement, the preset first reward value is determined as the reward or penalty value;

[0174] In the case that the comparison result corresponds to a disk replacement record that matches the second fault prediction result, if the disk replacement record indicates that the disk has not been replaced, the preset second reward value is determined as the reward or penalty value;

[0175] The first reward value is greater than the second reward value.

[0176] For ease of description, the above steps are combined and explained below.

[0177] To better guide the agent in making decisions based on SMART information, this embodiment proposes a reward function that rewards or penalizes the agent for each decision based on the function flow. The target model can be trained offline using SMART information data from a certain period of time. Starting from a certain period of time, the model is trained to make decisions based on the SMART information.

[0178] It should be noted that because SMART information varies between different machine models, each agent can only be trained on the SMART information for one machine model. Each time, the agent predicts the disk's health status for a certain period of time based on the server's continuous SMART information over a period of time and then takes an action. The current agent's decision and corresponding reward: whether to replace the current disk within the predicted time period. If the disk predicts a failure within the predicted time period and takes the action of replacing it, the agent is given a large reward R1 (first reward value). If the failure is not predicted within the expected time period and the action is not to replace the disk, or if there is no failure within the predicted time period but the action is to replace the disk, the agent is given a large penalty P1 (penalty value). In a continuously collected dataset, the majority of SMART information should indicate a healthy state, meaning that the disk is generally normal. In this case, if the agent takes the action of not replacing the disk, it is given a small reward R2 (second reward value). This guides the agent to learn all health states and solves the sparse reward problem.

[0179] The value network in the target model uses a four-layer MLP. The value network trains itself by collecting rewards from the policy network to predict the expected reward for a given sequence.

[0180] In a specific embodiment of the present application, during the process of optimizing the target model using training data, reward and penalty values ​​are used to indicate the optimization direction of the target model, including:

[0181] Step 1: When optimizing the target model using training data, substitute the reward and penalty values ​​into the advantage function to calculate the difference between the expected reward and the predicted reward.

[0182] Step 2: Update the target model based on the difference.

[0183] For ease of description, the above steps are combined and explained below.

[0184] In the value network, the calculation formula of the advantage function is as follows:

[0185]

[0186] Among them, i means the currently executed action is the i-th one, i' means the currently executed action is the i'th one, i'>i, a i represents the i-th action, x i Indicates the state corresponding to the execution of the i-th action, A t (x i ,a i ) is to execute action a in state xi iThe difference between the predicted reward value and the expected reward value corresponding to the time, r i is the single reward for the ith action, Indicates that action a is executed in the current state i The predicted reward value obtained after φ (x i ) is the state value function of the value network, representing the value of the current state x i and the expected reward value for the current network parameters.

[0187] The advantage function can guide the agent to avoid favoring frequent small reward events and increase the probability of less frequent large reward events. Furthermore, during the update process, the network is not directly updated using the estimated long-term reward. Instead, the network is updated using the difference between the accumulated reward from environmental feedback and the estimated reward. This approach effectively improves training efficiency and prevents updates from being too small or too large.

[0188] In a specific embodiment of the present application, it also includes:

[0189] Alarm processing is performed according to the first fault prediction result and / or the second fault prediction result.

[0190] Specifically, an alarm module can be set up. Function of the alarm module: After the prediction result of the above health level or decision action is generated, it is processed by the alarm module. If the output result of the fault prediction module is to replace the disk, an alarm will be generated immediately, prompting the administrator to replace the corresponding disk immediately and add the disk to the high-risk disk sequence; if the disk is not replaced, no alarm will be generated. When issuing an alarm, the first fault prediction result and the second fault prediction result can be processed indiscriminately. Of course, different differentiated alarms can also be issued. That is, when there is a prediction result of disk failure in the first fault prediction result and the second fault prediction result, an alarm can be issued.

[0191] Applying the method provided in the embodiments of this application,

[0192] Obtain multiple pieces of detection data information and the disk health score corresponding to each piece of detection data information; use the disk health score to determine the attribution of each piece of detection data information, and obtain predicted data and direct estimation data; among which, the prediction difficulty of predicted data is higher than that of direct estimation data; use the disk health score corresponding to the detection data information in the direct estimation data to determine the first fault prediction result; input the predicted data into the target model for fault prediction to obtain the second fault prediction result.

[0193] In the present application, when multiple pieces of detection data information and the disk health score corresponding to each piece of detection data information are obtained. For the disk health score, the score size is related to the prediction difficulty. For example, the more extreme the score, the more accurate the fault prediction result. Therefore, the attribution of each piece of detection data information can be determined based on the disk health score, thereby obtaining prediction data and direct estimation data. After the attribution division is completed, the prediction difficulty of the obtained prediction data is higher than that of the direct estimation data. Therefore, the detection data information in the direct estimation data can be directly based on the corresponding disk health score to obtain a first fault prediction result. For prediction data with high prediction difficulty, the target model is used to perform fault prediction, thereby obtaining a second fault prediction result. That is to say, for multiple pieces of detection data information to be predicted, the prediction difficulty can be screened and classified by the disk health score. For the part belonging to the direct estimation data, the disk fault prediction is directly performed based on the disk health score, and the first fault prediction result can be quickly obtained. For the part belonging to the prediction data, the fault prediction is performed with the help of the target model, thereby obtaining a second fault prediction result. Because the target model prediction is not simply based on the disk health score, but is directly based on the specific content of the detection data information, and the target model has been trained in advance, its accuracy can be higher than fault prediction based directly on the disk health score.

[0194] The technical effect of the present application is as follows: In general, relatively accurate data can be obtained based on the disk health score. Therefore, by dividing the detection data information into different categories based on the disk health score, a large amount of direct estimation data and a small amount of prediction data can be obtained. For a large amount of direct estimation data, an accurate first fault prediction result can be quickly determined based on the disk health score. For a small amount of prediction data that is difficult to obtain an accurate result based on the disk health score, a fault prediction is performed based on the target model to obtain an accurate second fault prediction result. It can be seen that the present application can not only improve the efficiency of disk fault prediction, but also improve the accuracy of fault prediction.

[0195] Corresponding to the above method embodiment, the embodiment of the present application further provides a disk failure prediction device. The disk failure prediction device described below and the disk failure prediction method described above can refer to each other.

[0196] See also Figure 3 As shown, the device includes the following units:

[0197] The data acquisition unit 101 is used to acquire multiple pieces of detection data information and the disk health score corresponding to each piece of detection data information;

[0198] The data screening unit 102 is used to determine the ownership of each piece of detection data information using the disk health score to obtain predicted data and direct estimated data;

[0199] The first fault prediction unit 103 is configured to determine a first fault prediction result by using a disk health score corresponding to the detection data information in the direct estimation data;

[0200] The second fault prediction unit 104 is configured to input the prediction data into the target model for fault prediction to obtain a second fault prediction result.

[0201] Using the device provided in the embodiment of the present application, multiple detection data information and the disk health score corresponding to each detection data information are obtained; the disk health score is used to determine the attribution of each detection data information, and predicted data and direct estimation data are obtained; wherein, the prediction difficulty of the predicted data is higher than that of the direct estimation data; the disk health score corresponding to the detection data information in the direct estimation data is used to determine the first fault prediction result; the predicted data is input into the target model for fault prediction to obtain the second fault prediction result.

[0202] In the present application, when multiple pieces of detection data information and the disk health score corresponding to each piece of detection data information are obtained. For the disk health score, the score size is related to the prediction difficulty. For example, the more extreme the score, the more accurate the fault prediction result. Therefore, the attribution of each piece of detection data information can be determined based on the disk health score, thereby obtaining prediction data and direct estimation data. After the attribution division is completed, the prediction difficulty of the obtained prediction data is higher than that of the direct estimation data. Therefore, the detection data information in the direct estimation data can be directly based on the corresponding disk health score to obtain a first fault prediction result. For prediction data with high prediction difficulty, the target model is used to perform fault prediction, thereby obtaining a second fault prediction result. That is to say, for multiple pieces of detection data information to be predicted, the prediction difficulty can be screened and classified by the disk health score. For the part belonging to the direct estimation data, the disk fault prediction is directly performed based on the disk health score, and the first fault prediction result can be quickly obtained. For the part belonging to the prediction data, the fault prediction is performed with the help of the target model, thereby obtaining a second fault prediction result. Because the target model prediction is not simply based on the disk health score, but is directly based on the specific content of the detection data information, and the target model has been trained in advance, its accuracy can be higher than fault prediction based directly on the disk health score.

[0203] The technical effect of the present application is as follows: In general, relatively accurate data can be obtained based on the disk health score. Therefore, by dividing the detection data information into different categories based on the disk health score, a large amount of direct estimation data and a small amount of prediction data can be obtained. For a large amount of direct estimation data, an accurate first fault prediction result can be quickly determined based on the disk health score. For a small amount of prediction data that is difficult to obtain an accurate result based on the disk health score, a fault prediction is performed based on the target model to obtain an accurate second fault prediction result. It can be seen that the present application can not only improve the efficiency of disk fault prediction, but also improve the accuracy of fault prediction.

[0204] In a specific embodiment of the present application, it also includes:

[0205] The optimization training unit is used to compare the disk replacement record with the second fault prediction result to obtain a comparison result; in the process of optimizing the target model using the training data, rewards and punishments are given based on the comparison result.

[0206] In a specific embodiment of the present application, the optimization training unit is specifically used to determine the reward and punishment values ​​using the comparison results;

[0207] In the process of optimizing the target model using training data, reward and penalty values ​​are used to indicate the optimization direction of the target model.

[0208] In a specific embodiment of the present application, the optimization training unit is specifically configured to determine a preset reward value as a reward or penalty value when the comparison result corresponds to a disk replacement record that matches the second fault prediction result;

[0209] In the case that the disk replacement record corresponding to the comparison result does not match the second fault prediction result, the preset penalty value is determined as the reward and penalty value.

[0210] In a specific embodiment of the present application, the optimization training unit is specifically configured to, when the comparison result corresponds to a disk replacement record that matches the second fault prediction result, determine a preset first reward value as a reward or penalty value if the disk replacement record is a disk replacement;

[0211] In the case that the comparison result corresponds to a disk replacement record that matches the second fault prediction result, if the disk replacement record indicates that the disk has not been replaced, the preset second reward value is determined as the reward or penalty value;

[0212] The first reward value is greater than the second reward value.

[0213] In a specific embodiment of the present application, the optimization training unit is specifically configured to substitute the reward and punishment values ​​into the advantage function to calculate the difference between the expected reward and the predicted reward during the optimization training of the target model using the training data;

[0214] Based on the difference, the target model is updated.

[0215] In a specific embodiment of the present application, the second fault prediction unit is specifically configured to add manufacturer information and disk attribute information to each piece of detection data information belonging to the prediction data;

[0216] After completing the data augmentation, each piece of detection data information is converted into a vector;

[0217] Group the obtained vectors to obtain a vector group;

[0218] The vector group is input into a target model for fault prediction to obtain a second fault prediction result; wherein the target model is a model that has learned the fault prediction capabilities of disks of different manufacturers and different attributes.

[0219] In a specific embodiment of the present application, the second fault prediction unit is specifically configured to input the vector group into the target model, and use the information cross-learning module in the target model to perform cross-learning between different feature dimensions in the vector group to obtain effective features;

[0220] Use the temporal information module in the strategy network to organize the effective features and obtain statistical characteristics;

[0221] The normalization layer in the strategy network is used to normalize the statistical characteristics to obtain the second fault prediction result.

[0222] In a specific embodiment of the present application, the second fault prediction unit is specifically configured to use an encoder in the time series information module to determine dependencies between different positions in the valid features to obtain a global feature representation;

[0223] The residual network in the temporal information module is used to perform residual processing on the global feature representation to obtain statistical characteristics.

[0224] In a specific embodiment of the present application, it also includes:

[0225] The data cleaning unit is configured to search for invalid indicators in each piece of detection data information before using the disk health score to determine the ownership of each piece of detection data information and obtaining predicted data and direct estimated data. If an invalid indicator is found, the invalidity index of the detection data information is increased by one; wherein each piece of detection data information includes multiple indicators;

[0226] If the invalidity index exceeds the preset threshold, the detection data information will be deleted.

[0227] In a specific embodiment of the present application, the data cleaning unit is specifically configured to delete the piece of detection data information after obtaining disk information corresponding to the piece of detection data information if the invalid indicator exceeds a preset threshold;

[0228] Use disk information to output prompt information of data collection abnormalities.

[0229] In a specific embodiment of the present application, the data acquisition unit is specifically used to use a disk self-test tool to test the disk and obtain multiple test data information; wherein, one test data information includes multiple indicator data;

[0230] Obtain the indicator threshold set corresponding to each piece of detection data information, and compare the current state value of each indicator in the detection data information with the corresponding threshold in the threshold set;

[0231] Based on the status comparison result, the disk health score corresponding to the detection data information is determined.

[0232] Please refer to Figure 4 In practical applications, a disk failure prediction system corresponding to the above disk failure prediction method can also be built, and the system includes:

[0233] The data collection and screening unit collects SMART information-related data and performs preliminary screening of the information on a disk-by-disk basis according to the heuristic rule method in Example 1, thereby reducing the decision-making difficulty of subsequent models and the amount of calculation.

[0234] The fault prediction unit uses the disk fault prediction algorithm based on the first embodiment as the core, sets a reward function, and predicts the fault of a certain disk based on the SMART information within a period of time according to the model, guiding the model to make better decisions.

[0235] The alarm monitoring unit generates corresponding alarms based on the current disk status information and the health level prediction generated by the model, and reminds the administrator to deal with the corresponding disk in a timely manner.

[0236] The disk status update unit responds to disk updates. If the administrator updates the disk, the alarm list is updated and the corresponding information of the new disk is added to the prediction module to predict the new health level.

[0237] In summary, this application proposes a prediction technology that combines expert knowledge strategy with reinforcement learning (RL) algorithm, combining the advantages of both heuristic rules and machine learning algorithms to improve the accuracy of decision-making, reduce the decision-making pressure of the algorithm model, and improve the decision-making efficiency of the fault prediction platform.

[0238] A more detailed classification of disk health is proposed, which divides the health level according to the scores of heuristic rules, thereby providing more accurate suggestions for fault prediction.

[0239] Introducing encoder processing into the training model improves the model's ability to predict sequential text information.

[0240] The technical solution provided in this application can be applied not only to disk failure prediction (DFP), but also to server component failure prediction. It is necessary to replace disk detection data with component detection data, collect the corresponding component information, and then train network parameters based on the above-mentioned incentive function and target model to achieve rapid and accurate prediction of server component failures.

[0241] Corresponding to the above method embodiment, an embodiment of the present application further provides an electronic device. The electronic device described below and the disk failure prediction method described above can refer to each other.

[0242] See also Figure 5 As shown, the electronic device includes:

[0243] Memory 332, for storing computer programs;

[0244] The processor 322 is configured to implement the steps of the disk failure prediction method of the above method embodiment when executing a computer program.

[0245] For details, please refer to Figure 6 , Figure 6 This is a schematic diagram of the specific structure of an electronic device provided in this embodiment. The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors (central processing units, CPU) (for example, one or more processors) and a memory 332, and the memory 332 stores one or more computer programs 342 or data 344. Among them, the memory 332 can be a temporary storage or a permanent storage. The program stored in the memory 332 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the data processing device. Furthermore, the processor 322 can be configured to communicate with the memory 332 to execute a series of instruction operations in the memory 332 on the electronic device 301.

[0246] The electronic device 301 may further include one or more power supplies 326 , one or more wired or wireless network interfaces 350 , one or more input / output interfaces 358 , and / or one or more operating systems 341 .

[0247] The steps in the disk failure prediction method described above can be implemented by the structure of an electronic device.

[0248] Corresponding to the above method embodiment, an embodiment of the present application further provides a readable storage medium. The readable storage medium described below and the disk failure prediction method described above can refer to each other.

[0249] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the disk failure prediction method of the above method embodiment.

[0250] The readable storage medium may specifically be any readable storage medium that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0251] Corresponding to the above method embodiment, an embodiment of the present application further provides a computer program product. The computer program product described below and the disk failure prediction method described above can refer to each other.

[0252] A computer program product includes a computer program / instruction. When the computer program / instruction is executed by a processor, the steps of the disk failure prediction method are implemented.

[0253] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from the other embodiments. Reference can be made to the descriptions of the identical or similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and the relevant parts can be referred to the descriptions of the methods.

[0254] Those skilled in the art may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0255] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0256] Finally, it should be noted that, in this document, relationships such as first and second, etc., are used solely to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms include, comprise, or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0257] This document uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A disk failure prediction method, characterized in that: include: Get multiple pieces of test data and the disk health score corresponding to each piece of test data; The disk health score is used to determine the attribution of each piece of detection data information, thereby obtaining predicted data and directly estimated data; wherein the prediction difficulty of the predicted data is higher than the prediction difficulty of the directly estimated data; Determine a first fault prediction result using a disk health score corresponding to the detection data information in the direct estimation data; Inputting the predicted data into a target model for fault prediction to obtain a second fault prediction result; The predicted data is input into the target model for fault prediction to obtain a second fault prediction result, including: Add manufacturer information and disk attribute information to each piece of detection data information belonging to the predicted data; After completing the data augmentation, each piece of detection data information is converted into a vector; Group the obtained vectors to obtain a vector group; Inputting the vector group into the target model for fault prediction to obtain the second fault prediction result; wherein the target model is a model that learns the fault prediction capabilities of disks of different manufacturers and different attributes; Inputting the vector group into the target model for fault prediction to obtain the second fault prediction result includes: Inputting the vector group into the target model, and using the information cross-learning module in the target model to perform cross-learning between different feature dimensions in the vector group to obtain effective features; Using the time series information module in the strategy network to sort out the effective features and obtain statistical characteristics; Normalizing the statistical characteristics using a normalization layer in the strategy network to obtain the second fault prediction result; The effective features are sorted using the time sequence information module in the strategy network to obtain statistical characteristics, including: Determine the dependency relationship between different positions in the effective features using the encoder in the temporal information module to obtain a global feature representation; The residual network in the temporal information module is used to perform residual processing on the global feature representation to obtain the statistical characteristics.

2. The method according to claim 1, characterized in that Also includes: Comparing the disk replacement record with the second fault prediction result to obtain a comparison result; In the process of optimizing and training the target model using the training data, rewards and punishments are given based on the comparison results.

3. The method according to claim 2, characterized in that In the process of optimizing and training the target model using the training data, rewards and penalties are given based on the comparison results, including: Determining reward and punishment values ​​using the comparison results; In the process of optimizing the target model using the training data, the reward and penalty values ​​are used to indicate the optimization direction of the target model.

4. The method according to claim 3, characterized in that Determining reward and punishment values ​​using the comparison results includes: If the comparison result corresponds to a match between the disk replacement record and the second fault prediction result, determining a preset reward value as the reward or penalty value; In a case where the comparison result corresponds to that the disk replacement record does not match the second fault prediction result, a preset penalty value is determined as the reward and penalty value.

5. The method according to claim 4, characterized in that When the comparison result corresponds to that the disk replacement record matches the second fault prediction result, determining a preset reward value as the reward or penalty value includes: In a case where the comparison result corresponds to that the disk replacement record matches the second fault prediction result, if the disk replacement record is a disk replacement, determining a preset first reward value as the reward or penalty value; In the case where the comparison result corresponds to that the disk replacement record matches the second fault prediction result, if the disk replacement record indicates that the disk has not been replaced, determining a preset second reward value as the reward or penalty value; Wherein, the first reward value is greater than the second reward value.

6. The method according to claim 3, characterized in that In the process of optimizing the target model using the training data, using the reward and penalty values ​​to indicate the optimization direction of the target model includes: In the process of optimizing the target model using the training data, substituting the reward and penalty values ​​into the advantage function to calculate the difference between the expected reward and the predicted reward; The target model is updated based on the difference.

7. The method according to claim 1, characterized in that Before using the disk health score to determine the ownership of each piece of detection data information and obtaining the predicted data and direct estimation data, the following steps are also included: Searching for invalid indicators in each piece of detection data information, and if an invalid indicator is found, increasing the invalidity index of the piece of detection data information by one; wherein each piece of detection data information includes multiple indicators; If the invalidity index exceeds a preset threshold, the detection data information is deleted.

8. The method according to claim 7, characterized in that If the invalidity index exceeds a preset threshold, the detection data information is deleted, including: If the invalidity indicator exceeds a preset threshold, after obtaining the disk information corresponding to the detection data information, the detection data information is deleted; The disk information is used to output a prompt message indicating abnormal data collection.

9. The method according to any one of claims 1 to 8, characterized in that Get multiple test data pieces and the disk health score corresponding to each test data piece, including: Using a disk self-test tool to test the disk, a plurality of test data information is obtained; wherein a piece of test data information includes a plurality of indicator data; Obtaining the indicator threshold set corresponding to each piece of detection data information, and comparing the current state value of each indicator in the detection data information with the corresponding threshold in the indicator threshold set; Based on the status comparison result, the disk health score corresponding to the detection data information is determined.

10. An electronic device, characterized in that: include: memory for storing computer programs; A processor, configured to implement the steps of the disk failure prediction method according to any one of claims 1 to 9 when executing the computer program.

11. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the disk failure prediction method according to any one of claims 1 to 9.

12. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the disk failure prediction method according to any one of claims 1 to 9 are implemented.

Images