Model training method, screening standard output method, screening method and device

Abstract

This disclosure provides a model training method, a standard output selection method, a selection method, and an apparatus. It relates to the fields of Internet of Things (IoT) and artificial intelligence (AI). The model training method includes: acquiring target hard drive attribute information, wherein the target hard drive satisfies a target selection threshold, the target selection threshold including a threshold defined for at least one hard drive attribute information of the target hard drive; acquiring a first hard drive attribute expectation value defined for the target hard drive by a first service, wherein the first service has first service type information; inputting the target hard drive attribute information, the first service type information, and the first hard drive attribute expectation value into a prediction model to be trained to obtain a prediction selection threshold, wherein the prediction selection threshold is used when the target hard drive is applied to the first service; and training the prediction model using the target selection threshold and the prediction selection threshold.

Description

Technical Field

[0001] This disclosure relates to the fields of Internet of Things, artificial intelligence and other technologies, and more specifically, to a model training method, a method for selecting standard outputs, a selection method and apparatus. Background Technology

[0002] Internet and IT companies often need to purchase numerous storage devices to store massive amounts of information. Hard drives, as a good data storage medium, are among the most common storage devices. Due to different business characteristics and performance requirements, different types of hard drives can be selected for different business scenarios.

[0003] In the process of realizing the present invention, the inventors discovered that the related technology has at least the following problems: it is difficult to select hard drives for different business scenarios, and the selection efficiency is low. Summary of the Invention

[0004] In view of this, this disclosure provides a model training method, a standard output selection method, a selection method, and an apparatus.

[0005] One aspect of this disclosure provides a method for training a prediction model, comprising: acquiring target hard disk attribute information of a target hard disk, wherein the target hard disk satisfies a target filtering threshold, the target filtering threshold including a threshold defined for at least one hard disk attribute information of the target hard disk; acquiring a first hard disk attribute expected value defined for the target hard disk by a first service, wherein the first service has first service type information; inputting the target hard disk attribute information, the first service type information, and the first hard disk attribute expected value into a prediction model to be trained to obtain a prediction filtering threshold, wherein the prediction filtering threshold is used to be invoked when the target hard disk is applied to the first service; and training the prediction model using the target filtering threshold and the prediction filtering threshold.

[0006] Another aspect of this disclosure provides a method for outputting hard disk screening criteria, comprising: obtaining second hard disk attribute information of a second hard disk to be screened; obtaining expected values ​​of second hard disk attributes defined by a second service for the second hard disk to be screened, wherein the second service has second service type information; inputting the second hard disk attribute information, the second service type information and the expected values ​​of the second hard disk attributes into a prediction model to obtain a standard screening threshold, wherein the prediction model is trained based on the training method of the prediction model described in this disclosure; and determining hard disk screening criteria according to the standard screening threshold.

[0007] Another aspect of this disclosure provides a hard disk screening method, comprising: obtaining fourth hard disk attribute information of a fourth hard disk to be screened, wherein the fourth hard disk to be screened includes hard disks that meet a third predefined usage condition; and screening the fourth hard disk to be screened according to hard disk screening criteria and the fourth hard disk attribute information, wherein the hard disk screening criteria include criteria output according to the hard disk screening criteria output method described in this disclosure.

[0008] Another aspect of this disclosure provides a training apparatus for a prediction model, comprising: a first acquisition module for acquiring target hard disk attribute information of a target hard disk, wherein the target hard disk satisfies a target filtering threshold, the target filtering threshold including a threshold defined for at least one hard disk attribute information of the target hard disk; a second acquisition module for acquiring a first hard disk attribute expected value defined for the target hard disk by a first service, wherein the first service has first service type information; a first obtaining module for inputting the target hard disk attribute information, the first service type information, and the first hard disk attribute expected value into a prediction model to be trained to obtain a prediction filtering threshold, wherein the prediction filtering threshold is used to be invoked when the target hard disk is applied to the first service; and a training module for training the prediction model using the target filtering threshold and the prediction filtering threshold.

[0009] Another aspect of this disclosure provides a hard disk screening standard output device, comprising: a third acquisition module for acquiring second hard disk attribute information of a second hard disk to be screened; a fourth acquisition module for acquiring expected values ​​of second hard disk attributes defined by a second service for the second hard disk to be screened, wherein the second service has second service type information; a second obtaining module for inputting the second hard disk attribute information, the second service type information and the expected values ​​of the second hard disk attributes into a prediction model to obtain a standard screening threshold, wherein the prediction model is trained by a prediction model training device; and a first determining module for determining a hard disk screening standard based on the standard screening threshold.

[0010] Another aspect of this disclosure provides a hard disk screening device, comprising: a sixth acquisition module for acquiring fourth hard disk attribute information of a fourth hard disk to be screened, wherein the fourth hard disk to be screened includes hard disks that meet a third predefined usage condition; and a screening module for screening the fourth hard disk to be screened according to hard disk screening criteria and the fourth hard disk attribute information, wherein the hard disk screening criteria include criteria output by a hard disk screening criteria output device.

[0011] Another aspect of this disclosure provides a computer-readable storage medium storing computer-executable instructions that, when executed, are used to implement the method described above.

[0012] Another aspect of this disclosure provides a computer program product including computer-executable instructions that, when executed, are used to implement the method described above.

[0013] According to the embodiments of this disclosure, by employing the technical means of inputting target hard disk attribute information, first service type information, and expected value of first hard disk attributes into the prediction model to be trained to obtain a prediction screening threshold, wherein the prediction screening threshold is used to be invoked when the target hard disk is applied to the first service; and by using the target screening threshold and the prediction screening threshold to train the prediction model, the technical problems of difficulty and low screening efficiency in screening hard disks for different service scenarios are at least partially overcome, thereby achieving the technical effect of different screening of hard disks according to the form and requirements of different services and improving screening efficiency. Attached Figure Description

[0014] The above and other objects, features and advantages of this disclosure will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0015] Figure 1 An exemplary system architecture is illustrated, according to embodiments of the present disclosure, in which at least one of a predictive model training method, a disk screening standard output method, and a disk screening method can be applied;

[0016] Figure 2 A flowchart illustrating a method for training a prediction model according to an embodiment of the present disclosure is shown schematically.

[0017] Figure 3 A flowchart illustrating a method for outputting hard disk screening criteria according to an embodiment of the present disclosure is shown schematically.

[0018] Figure 4 A schematic diagram illustrating the principle of a model training process according to an embodiment of the present disclosure is provided.

[0019] Figure 5 A flowchart illustrating a hard disk screening method according to an embodiment of the present disclosure is shown schematically;

[0020] Figure 6 This illustration schematically shows a process for selecting usable hard drives from returned hard drives and alarm hard drives according to an embodiment of the present disclosure;

[0021] Figure 7 A block diagram of a training apparatus for a predictive model according to an embodiment of the present disclosure is shown schematically.

[0022] Figure 8 A block diagram of a hard disk screening standard output device according to an embodiment of the present disclosure is shown schematically;

[0023] Figure 9 A block diagram schematically illustrates a hard disk screening device according to an embodiment of the present disclosure; and

[0024] Figure 10 A block diagram of an electronic device suitable for implementing at least one of the following methods according to embodiments of the present disclosure: a training method for an application prediction model, a standard output method for disk screening, and a disk screening method. Detailed Implementation

[0025] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0026] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0027] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0028] When using expressions such as "at least one of A, B, and C", they should generally be interpreted in accordance with the meaning that is commonly understood by a person skilled in the art (e.g., "a system having at least one of A, B, and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B, and C, etc.).

[0029] The following two situations exist during the use of hard drives: (1) Due to various reasons such as business shutdown or department reduction, used hard drives are taken offline and returned to the warehouse. Later, due to business needs, the returned hard drives are put back online as spare parts. (2) Based on the alarm information in the system, the hard drive is considered to be faulty, and the hard drive with alarm information is replaced and destroyed as a bad part.

[0030] In case (1), in order to maximize the value of the hard drive, the hard drive was reused after being returned to the warehouse. The usage time may have exceeded the warranty period. The quality of this part of the hard drive cannot be guaranteed in subsequent use. Although it will undergo some tests before being put into use, the test results are not related to the subsequent usage and there is a lack of tracking of the usage after the second online use.

[0031] In scenario (2), the determination of a faulty hard drive is often ambiguous. In reality, not all alarm messages are caused by hard drive failure, such as file system failures or transport layer failures. According to statistics from hard drive manufacturers, among the replaced hard drives with alarms, up to 50% showed no obvious faults. Therefore, in this situation, a large number of hard drives fail to realize their full potential, resulting in a serious waste of resources.

[0032] In realizing this disclosed concept, the inventors discovered that, regardless of whether it's reusing returned hard drives or reusing alarm hard drives, different business operations have different usage patterns and, similarly, different requirements for reusing hard drives. Currently, there is no method or mechanism to selectively select reusable hard drives based on the different business models and requirements. Selection criteria are often one-size-fits-all and cannot adapt to the needs of all business scenarios.

[0033] Embodiments of this disclosure provide a model training method, a standard output filtering method, a filtering method, and an apparatus. The method includes: acquiring target hard drive attribute information, wherein the target hard drive satisfies a target filtering threshold, the target filtering threshold including a threshold defined for at least one hard drive attribute information of the target hard drive; acquiring a first hard drive attribute expectation value defined for the target hard drive by a first service, wherein the first service has first service type information; inputting the target hard drive attribute information, the first service type information, and the first hard drive attribute expectation value into a prediction model to be trained to obtain a prediction filtering threshold, wherein the prediction filtering threshold is used when the target hard drive is applied to the first service; and training the prediction model using the target filtering threshold and the prediction filtering threshold.

[0034] Figure 1 An exemplary system architecture 100 is illustrated, according to embodiments of the present disclosure, in which at least one of a predictive model training method, a disk screening standard output method, and a disk screening method can be applied. It should be noted that... Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, in order to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments or scenarios.

[0035] like Figure 1As shown, the system architecture 100 according to this embodiment may include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104, and a server 105. The network 104 serves as a medium for providing communication links between the first terminal device 101, the second terminal device 102, the third terminal device 103, and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0036] Users can use the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 via the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102, and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, and / or social media platform software (for example only).

[0037] The first terminal device 101, the second terminal device 102, and the third terminal device 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0038] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0039] It should be noted that at least one of the prediction model training method, hard disk screening standard output method, and hard disk screening method provided in this disclosure embodiment can generally be executed by server 105. Correspondingly, at least one of the prediction model training device, hard disk screening standard output device, and hard disk screening device provided in this disclosure embodiment can generally be located in server 105. At least one of the prediction model training method, hard disk screening standard output method, and hard disk screening method provided in this disclosure embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, at least one of the prediction model training device, hard disk screening standard output device, and hard disk screening device provided in this disclosure embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Alternatively, at least one of the methods provided in this disclosure—the prediction model training method, the hard disk screening standard output method, and the hard disk screening method—can be executed by the first terminal device 101, the second terminal device 102, or the third terminal device 103, or by other terminal devices different from the first terminal device 101, the second terminal device 102, or the third terminal device 103. Correspondingly, at least one of the devices provided in this disclosure—the prediction model training device, the hard disk screening standard output device, and the hard disk screening device—can be disposed in the first terminal device 101, the second terminal device 102, or the third terminal device 103, or in other terminal devices different from the first terminal device 101, the second terminal device 102, or the third terminal device 103.

[0040] For example, the target hard drive attribute information, the first service type information of the first service, and the expected value of the first hard drive attribute defined by the first service for the target hard drive can originally be stored in any one of the first terminal device 101, the second terminal device 102, or the third terminal device 103 (e.g., terminal device 101, but not limited thereto), or stored on an external storage device and can be imported into terminal device 101. Then, terminal device 101 can locally execute the training method of the prediction model provided in the embodiments of this disclosure, or send the target hard drive attribute information, the first service type information, and the expected value of the first hard drive attribute to other terminal devices, servers, or server clusters, and have the other terminal devices, servers, or server clusters that receive the target hard drive attribute information, the first service type information, and the expected value of the first hard drive attribute execute the training method of the prediction model provided in the embodiments of this disclosure.

[0041] For example, the second hard drive attribute information of the second hard drive to be screened, the second service type information corresponding to the current business scenario, and the expected value of the second hard drive attribute defined by the second service for the second hard drive to be screened can originally be stored in any one of the first terminal device 101, the second terminal device 102, or the third terminal device 103 (e.g., terminal device 101, but not limited thereto), or stored on an external storage device and can be imported into terminal device 101. Then, terminal device 101 can execute the hard drive screening standard output method provided in the embodiments of this disclosure locally, or send the second hard drive attribute information, the second service type information, and the expected value of the second hard drive attribute to other terminal devices, servers, or server clusters, and have other terminal devices, servers, or server clusters that receive the second hard drive attribute information, the second service type information, and the expected value of the second hard drive attribute to execute the hard drive screening standard output method provided in the embodiments of this disclosure.

[0042] For example, the fourth hard drive attribute information of the fourth hard drive to be screened may originally be stored in any one of the first terminal device 101, the second terminal device 102, or the third terminal device 103 (e.g., terminal device 101, but not limited thereto), or it may be stored on an external storage device and imported into terminal device 101. Then, terminal device 101 may execute the hard drive screening method provided in the embodiments of this disclosure locally, or send the fourth hard drive attribute information to other terminal devices, servers, or server clusters, and have the other terminal devices, servers, or server clusters that receive the fourth hard drive attribute information execute the hard drive screening method provided in the embodiments of this disclosure.

[0043] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0044] Figure 2 A flowchart illustrating a method for training a prediction model according to an embodiment of the present disclosure is shown.

[0045] like Figure 2 As shown, the method includes operations S201 to S204.

[0046] In operation S201, target hard disk attribute information of the target hard disk is obtained, wherein the target hard disk meets the target filtering threshold, and the target filtering threshold includes a threshold defined for at least one hard disk attribute information of the target hard disk.

[0047] According to embodiments of this disclosure, hard disk attribute information can characterize observable indicators that reflect the current usage status of the hard disk or may subsequently affect its performance. This may include, but is not limited to, the current performance status of the hard disk and test parameters for hard disk screening tests. At least one hard disk attribute information may include at least one of the following: hard disk usage time, hard disk test duration, throughput information, stability information, hard disk capacity information, hard disk rotation speed information, hard disk cache information, average seek time information, burst data transfer rate, sustained transfer rate, hard disk brand information, hard disk model information, etc., and is not limited to these. The target screening threshold can characterize a lower limit value defined for the aforementioned hard disk attribute information or type information such as brand and model. The target hard disk attribute information may include at least one of the following: hard disk usage time, hard disk test duration, throughput information, stability information, and is not limited to these. It should be noted that the above-mentioned at least one hard disk attribute information and the above-mentioned target hard disk attribute information may be the same or different.

[0048] According to embodiments of this disclosure, filtering items can first be set based on hard drive attribute information, and a target filtering threshold corresponding to each filtering item can be determined. Then, the hard drive attribute information corresponding to the target filtering threshold that satisfies the threshold defined by the target filtering threshold is obtained. Afterwards, the attribute information of the target hard drive is collected to obtain the target hard drive attribute information.

[0049] In operation S202, the expected value of the first hard disk attribute defined by the first service for the target hard disk is obtained, wherein the first service has first service type information.

[0050] According to embodiments of this disclosure, the first service may include at least one of the following: services characterized by a read / write frequency greater than a first preset threshold, such as big data services; services characterized by a read / write frequency less than a second preset threshold, such as cloud computing services; services characterized by a read frequency greater than a third preset threshold and a write frequency less than a fourth preset threshold, such as query services; and services characterized by a read frequency less than a fifth preset threshold and a write frequency greater than a sixth preset threshold, such as add, delete, and modify services, etc., and are not limited to these. It should be noted that the first preset threshold is greater than the second preset threshold, and the threshold information of the first, second, third, fourth, and fifth preset thresholds can be set according to the actual scenario, and is not limited here.

[0051] According to embodiments of this disclosure, the first service type information may include type information categorized by different levels based on read / write frequencies. For example, it may include first-level type information, which can characterize the service type information corresponding to services with read / write frequencies greater than a first preset threshold; Nth-level type information, which can characterize the service type information corresponding to services with read / write frequencies less than a second preset threshold; and so on. The first service type information may also include type information categorized by service type, such as big data, cloud computing, etc., and is not limited to these.

[0052] According to embodiments of this disclosure, the first hard disk attribute expectation value can characterize the expected value that the service hopes the hard disk will achieve during the reuse of the hard disk. The first hard disk attribute expectation value may include at least one of the following: expected usage duration, expected throughput information, expected stability information, etc., and is not limited to these.

[0053] According to embodiments of this disclosure, based on the different performance requirements of different types of services, the usage requirements of the first service on the target hard drive can be determined firstly for each type of first service. Then, based on these usage requirements, the expected values ​​of the first hard drive attributes defined for the target hard drive by the first service can be determined.

[0054] In operation S203, the target hard disk attribute information, the first service type information, and the expected value of the first hard disk attribute are input into the prediction model to be trained to obtain the prediction screening threshold. The prediction screening threshold is used to be invoked when the target hard disk is applied to the first service.

[0055] According to embodiments of this disclosure, the prediction model to be trained can be implemented by constructing an algorithm library. The process of constructing the algorithm library may include, for example, selecting multiple regression algorithms and adding them to the algorithm library. The prediction screening threshold may include a threshold corresponding to the prediction of one or more hardware attribute information. In practical applications, the prediction screening threshold output by the model can be used as a hard drive screening criterion when applying the target hard drive to the first service.

[0056] In operation S204, a prediction model is trained using the target selection threshold and the prediction selection threshold.

[0057] According to embodiments of this disclosure, the target hard disk attribute information may also include basic information about the hard disk, such as, but not limited to, the brand, model, and capacity of the hard disk.

[0058] According to embodiments of this disclosure, the sampled target hard disk attribute information, first service type information, expected values ​​of the first hard disk attributes, and target screening threshold can be used as training data first. The training data is then initialized, including removing null values, duplicate data, and other abnormal data, and standardizing the data. Then, the collected training data can be divided into input data and output data. For example, the target hard disk attribute information, first service type information, and expected values ​​of the first hard disk attributes during the hard disk reuse process can be used as input data, and the target screening threshold corresponding to the screening item can be used as output data. A dataset is then constructed based on the input and output data.

[0059] According to embodiments of this disclosure, when a prediction model needs to be trained, the algorithms in the algorithm library can be trained based on the input and output data in the dataset. During the training process, model validation metrics can be set, such as the algorithm's accuracy, recall, and F-score (fundamental factor), and cross-validation can be used to select the model with higher validation metric scores as the output model for model training.

[0060] Through the above embodiments of this disclosure, by training a prediction model using target hard disk attribute information, first service type information, first hard disk attribute expected value and target screening threshold, the hard disk usage and usage requirements of different services can be used as input to derive the threshold required for screening and reusing hard disks corresponding to that service. This enables different hard disk screening based on the form and requirements of different services, and is applicable to different service scenarios.

[0061] The following describes specific embodiments. Figure 2 The method shown will be further explained.

[0062] According to embodiments of this disclosure, the process of obtaining the target hard disk corresponding to the above operation S201 may include: obtaining first hard disk attribute information of the first hard disk to be screened. In response to determining that the first hard disk attribute information meets a first predefined usage condition, the first hard disk to be screened corresponding to the first hard disk attribute information is determined as the target hard disk.

[0063] According to embodiments of this disclosure, the first hard drive to be screened may include at least one of the following: a returned hard drive and an alarm hard drive. A returned hard drive may represent a hard drive that has been used. An alarm hard drive may represent a hard drive that has generated alarm information during use. It should be noted that the first hard drive to be screened is not limited to the types of hard drives described above; for example, the first hard drive to be screened may also include a brand new, unused hard drive.

[0064] According to embodiments of this disclosure, the first hard disk attribute information may include, but is not limited to, various attribute information included in the aforementioned hard disk attribute information. The first predefined usage conditions may include at least one of the following: the hard disk SMART (Self-Monitoring Analysis and Reporting Technology) data does not exceed a specified threshold, the hard disk SMART health check or long / short test is successful, other professional hard disk testing tools show that the hard disk is not faulty, the hard disk amplitude is within a predetermined range, the hard disk temperature, etc., are within a predetermined range, etc., and are not limited to these.

[0065] According to embodiments of this disclosure, after obtaining at least one type of hard drive to be screened, such as returned hard drives, alarm hard drives, and other hard drives, a hard drive detection stage can be performed to conduct necessary fault detection on these hard drives, initially filtering out hard drives with obvious faults, and using the screened hard drives without obvious faults as target hard drives. Fault detection may include at least one of the following detection methods: using detection tools to detect the screening items, analyzing error logs provided by the manufacturer to detect the screening items, etc., and is not limited to these.

[0066] According to embodiments of this disclosure, the target hard disk attribute information and the target hard disk attribute expectation value can have the same attribute type. After obtaining the target hard disk, the above operation S201 may further include: determining a sampling period. In the process of applying the target hard disk to the first service, in response to determining that the target hard disk attribute information meets the first hard disk attribute expectation value, the target hard disk attribute information is periodically acquired based on the sampling period.

[0067] According to embodiments of this disclosure, during the application of the target hard disk to the first service, sampling can be performed every preset time period. This preset time period can be used as the sampling cycle.

[0068] According to embodiments of this disclosure, during the aforementioned fault detection process, an initial test threshold can be set for each hard drive as a target screening threshold. Hard drives that meet the threshold conditions of the target screening threshold can be reused online. During hard drive usage, a sampling period can be set to continuously collect various indicators of the hard drive based on the business requirements for hard drive usage. Sampling can be stopped when the hard drive performance no longer meets the business requirements. This sampling method can obtain the aforementioned target hard drive attribute information.

[0069] Through the above embodiments of this disclosure, by initially screening hard drives and periodically sampling hard drive attribute information during the experiment, training data adapted to business needs can be obtained. Based on this training data, a prediction model can be trained, which can improve the model's prediction efficiency and accuracy.

[0070] Figure 3 A flowchart illustrating a hard disk screening criterion output method according to an embodiment of the present disclosure is shown schematically.

[0071] like Figure 3 The method includes operations S301 to S304.

[0072] In operation S301, the attribute information of the second hard drive to be filtered is obtained.

[0073] In operation S302, the expected value of the second hard disk attribute defined by the second service for the second hard disk to be filtered is obtained, wherein the second service has second service type information.

[0074] In operation S303, the second hard disk attribute information, the second service type information, and the expected value of the second hard disk attribute are input into the prediction model to obtain the standard screening threshold. The prediction model is trained based on the prediction model training method described in this disclosure.

[0075] In operation S304, the hard drive screening criteria are determined based on the standard screening threshold.

[0076] According to embodiments of this disclosure, after training the prediction model, the second service type information, the usage requirements of the second service for the second hard drive to be screened, and the attribute information of the second hard drive can be used as inputs. The output of the prediction model can be used as a standard screening threshold to obtain the hard drive screening criteria when applying the second hard drive to be screened in the second service. The second hard drive to be screened that meets the hard drive screening criteria can be put into service as a spare part in the second service scenario.

[0077] It should be noted that the second hard drive to be screened can include various types of hard drives, and the second hard drive to be screened can be the same as or different from the first hard drive to be screened. The attribute information of the second hard drive can include, but is not limited to, the various attribute information included in the aforementioned hard drive attribute information. The attribute information of the first hard drive and the attribute information of the second hard drive can be the same as or different. The second service can include, but is not limited to, the various services included in the aforementioned first service. The first service and the second service can be the same as or different. The second service type information can include, but is not limited to, the service type information included in the aforementioned first service type information. The first service type information and the second service type information can be the same as or different. The expected value of the second hard drive attribute can include, but is not limited to, the various expected value information included in the aforementioned first hard drive attribute expected value. The expected value of the first hard drive attribute and the expected value of the second hard drive attribute can be the same as or different.

[0078] Through the above embodiments of this disclosure, an adaptive method for formulating hard drive screening criteria can be implemented. Using the values ​​obtained by this method as thresholds in conjunction with certain detection methods, hard drives are screened, and the screened hard drives are reused, thus maximizing their value. In particular, screening for hard drives such as those returned from inventory or those triggering alarms can reduce wasted hard drive value.

[0079] According to embodiments of this disclosure, in the above-described hard disk screening standard output method, the method for obtaining the second hard disk to be screened may include: obtaining third hard disk attribute information of the third hard disk to be screened, wherein the third hard disk to be screened includes the second hard disk to be screened. In response to determining that the third hard disk attribute information meets a second predefined usage condition, the third hard disk to be screened corresponding to the third hard disk attribute information is determined as the second hard disk to be screened.

[0080] It should be noted that the third hard drive to be screened can include various types of hard drives, and the third hard drive to be screened can be the same as or different from the second hard drive to be screened. The attribute information of the third hard drive can include, but is not limited to, the various attribute information included in the aforementioned hard drive attribute information. The attribute information of the third hard drive can be the same as or different from the attribute information of the second hard drive. The second predefined usage conditions can include, but are not limited to, the conditions included in the aforementioned first predefined usage conditions. The first predefined usage conditions and the second predefined usage conditions can be the same as or different.

[0081] Through the above embodiments of this disclosure, a third hard disk to be screened can be initially screened by combining a second predefined usage condition. The second hard disk to be screened and its related information obtained from the screening can be used as input data, and the hard disk screening criteria can be output by combining the prediction model, which can effectively improve the accuracy of the hard disk screening criteria.

[0082] Figure 4 A schematic diagram illustrating the principle of a model training process according to an embodiment of the present disclosure is shown.

[0083] like Figure 4 As shown, screening item 410 can be used to record the type information of hard drive attributes that need to be used in the hard drive screening process, i.e., observable indicator information. Screening criterion 420 can characterize the target screening threshold, which can be formulated by defining attribute thresholds for the hardware attributes corresponding to screening item 410. Business usage requirements 430 can be used to record the expected values ​​of hard drive attributes defined by the business for the hard drive. Reuse hard drive usage status 440 can be used to record real-time information of target hard drive attribute information collected periodically during hard drive usage.

[0084] According to embodiments of this disclosure, the hard drive attribute information, business type information, expected values ​​of hard drive attributes, and corresponding screening thresholds obtained periodically when the hard drive is used in business can be used as training data based on the usage of the hard drive after its secondary online use. The screening criteria can be continuously adjusted and the prediction model optimized in real time through corresponding algorithms.

[0085] Through the above embodiments of this disclosure, by tracking the online usage of hard drives and continuously adjusting the screening criteria based on feedback information, the hard drives selected based on the screening criteria can meet the real-time online usage requirements and expectations, thereby improving the screening accuracy.

[0086] Figure 5 A flowchart illustrating a hard disk screening method according to an embodiment of the present disclosure is shown schematically.

[0087] like Figure 5 As shown, the method includes operations S501 to S502.

[0088] In operation S501, the fourth hard disk attribute information of the fourth hard disk to be filtered is obtained, wherein the fourth hard disk to be filtered includes hard disks that meet the third predefined usage conditions.

[0089] In operation S502, the fourth hard disk to be screened is screened according to the hard disk screening criteria and the fourth hard disk attribute information. The hard disk screening criteria include the criteria output according to the hard disk screening criteria output method described in this disclosure.

[0090] It should be noted that the fourth hard drive to be filtered can include various types of hard drives, and the fourth hard drive to be filtered can be the same as or different from the second hard drive to be filtered. The attribute information of the fourth hard drive can include, but is not limited to, the various attribute information included in the aforementioned hard drive attribute information. The attribute information of the fourth hard drive can be the same as or different from the attribute information of the second hard drive. The third predefined usage conditions can include, but are not limited to, the conditions included in the aforementioned first predefined usage conditions. The third predefined usage conditions and the first predefined usage conditions can be the same as or different.

[0091] According to embodiments of this disclosure, after obtaining a fourth hard drive that has passed the test based on a third predefined usage condition, the fourth hard drive can be further screened according to the hard drive screening criteria determined by the prediction model, and the hard drives that meet the hard drive screening criteria can be used as spare parts for subsequent online use.

[0092] Figure 6 The illustration shows a schematic diagram of the process of selecting usable hard drives from returned hard drives and alarm hard drives according to an embodiment of the present disclosure.

[0093] like Figure 6 The process includes operations S610 to S660.

[0094] When operating the S610, retrieve the returned hard drive and the alarm hard drive.

[0095] In operation S620, a hard disk test is performed. In this operation, the hard disk 610 can be tested based on predefined usage conditions. If the hard disk test passes, operation S630 can be executed. If the hard disk test fails, operation S660 can be executed.

[0096] In operation S630, hard drive screening is performed. In this operation, hard drives that have passed the initial screening are screened based on the screening criteria output by the predictive model. For hard drives that pass the screening, operations S640 to S650 can be executed. For hard drives that pass the screening, operation S660 can be executed.

[0097] In the S640 operation, hard drive spare parts are selected. This operation indicates that the selected hard drives can be used as spare hard drives for subsequent deployment.

[0098] The S650 is being operated and brought online for use. This operation indicates that the spare hard drive is being brought online for use.

[0099] In operation S660, hard drive replacement. This operation may include at least one of the following: filtering out hard drives that fail the detection or screening, and replacing the hard drive that fails the detection or screening with another hard drive.

[0100] The embodiments described above provide a comprehensive detection and screening process for returned and alarm-triggered hard drives during the reuse process. Based on this screening process, and combined with the hard drive screening criteria output by the predictive model, hard drives that meet the needs of different business scenarios can be selected.

[0101] Figure 7 A block diagram of a training apparatus for a predictive model according to an embodiment of the present disclosure is shown schematically.

[0102] like Figure 7 As shown, the training device 700 for the prediction model includes a first acquisition module 710, a second acquisition module 720, a first acquisition module 730, and a training module 740.

[0103] The first acquisition module 710 is used to acquire target hard disk attribute information of the target hard disk, wherein the target hard disk meets the target filtering threshold, and the target filtering threshold includes a threshold defined for at least one hard disk attribute information of the target hard disk.

[0104] The second acquisition module 720 is used to acquire the expected value of the first hard disk attribute defined by the first service for the target hard disk, wherein the first service has first service type information.

[0105] The first acquisition module 730 is used to input the target hard disk attribute information, the first service type information and the expected value of the first hard disk attribute into the prediction model to be trained, and obtain the prediction screening threshold, wherein the prediction screening threshold is used to be invoked when the target hard disk is applied to the first service.

[0106] Training module 740 is used to train a prediction model using the target screening threshold and the prediction screening threshold.

[0107] According to embodiments of this disclosure, the target hard disk attribute information and the expected value of the target hard disk attributes have the same attribute type. The first acquisition module includes a first determining unit and a first acquisition unit.

[0108] The first determining unit is used to determine the sampling period.

[0109] The first acquisition unit is used to periodically acquire target hard disk attribute information based on a sampling period in response to determining that the target hard disk attribute information meets the expected value of the first hard disk attribute during the process of applying the target hard disk to the first service.

[0110] According to embodiments of this disclosure, the first acquisition module includes a second acquisition unit and a second determination unit.

[0111] The second acquisition unit is used to acquire the first hard drive attribute information of the first hard drive to be screened.

[0112] The second determining unit is used to determine the first hard disk to be screened as the target hard disk in response to determining that the first hard disk attribute information meets the first predefined usage conditions.

[0113] According to embodiments of this disclosure, the target hard disk attribute information includes at least one of the following: hard disk usage duration, hard disk testing duration, throughput information, and stability information. The first hard disk attribute expected value includes at least one of the following: expected usage duration, expected throughput information, and expected stability information.

[0114] According to embodiments of this disclosure, the first hard drive to be screened includes at least one of the following: a returned hard drive and an alarm hard drive, wherein the returned hard drive represents a hard drive that has been used, and the alarm hard drive represents a hard drive that has generated alarm information during use.

[0115] Figure 8 A block diagram of a hard disk screening standard output device according to an embodiment of the present disclosure is shown schematically.

[0116] like Figure 8 As shown, the hard disk screening standard output device 800 includes a third acquisition module 810, a fourth acquisition module 820, a second acquisition module 830, and a first determination module 840.

[0117] The third acquisition module 810 is used to acquire the second hard drive attribute information of the second hard drive to be screened.

[0118] The fourth acquisition module 820 is used to acquire the expected value of the second hard disk attribute defined by the second service for the second hard disk to be screened, wherein the second service has second service type information.

[0119] The second obtaining module 830 is used to input the second hard disk attribute information, the second service type information, and the expected value of the second hard disk attribute into the prediction model to obtain the standard screening threshold, wherein the prediction model is trained based on the training device of the prediction model described in this disclosure.

[0120] The first determining module 840 is used to determine the hard disk screening criteria based on the standard screening threshold.

[0121] According to embodiments of this disclosure, the hard disk screening standard output device further includes a fifth acquisition module and a second determination module.

[0122] The fifth acquisition module is used to acquire the third hard drive attribute information of the third hard drive to be screened, wherein the third hard drive to be screened includes the second hard drive to be screened.

[0123] The second determining module is used to determine the third hard disk to be screened as the second hard disk to be screened in response to determining that the third hard disk attribute information meets the second predefined usage conditions.

[0124] Figure 9 A block diagram of a hard disk screening apparatus according to an embodiment of the present disclosure is shown schematically.

[0125] like Figure 9 As shown, the hard disk screening device 900 includes a sixth acquisition module 910 and a screening module 920.

[0126] The sixth acquisition module 910 is used to acquire the fourth hard disk attribute information of the fourth hard disk to be screened, wherein the fourth hard disk to be screened includes hard disks that meet the third predefined usage conditions.

[0127] The filtering module 920 is used to filter the fourth hard disk to be filtered according to the hard disk filtering criteria and the fourth hard disk attribute information, wherein the hard disk filtering criteria include the criteria output by the hard disk filtering criteria output device according to the present disclosure.

[0128] Any one or more of the modules or units according to embodiments of this disclosure, or at least a portion thereof, may be implemented in a single module. Any one or more of the modules or units according to embodiments of this disclosure may be implemented by dividing them into multiple modules. Any one or more of the modules or units according to embodiments of this disclosure may be at least partially implemented as hardware circuitry, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a System-on-Chip, a System-on-Substrate, a System-on-Package, an Application-Specific Integrated Circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging the circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three methods. Alternatively, one or more of the modules or units according to embodiments of this disclosure may be at least partially implemented as computer program modules, which, when run, can perform corresponding functions.

[0129] For example, any and more of the following modules can be implemented in one module / unit: the first acquisition module 710, the second acquisition module 720, the first acquisition module 730, and the training module 740; or the third acquisition module 810, the fourth acquisition module 820, the second acquisition module 830, and the first determination module 840; or the sixth acquisition module 910 and the filtering module 920. Alternatively, any one of these modules / units can be split into multiple modules / units. Or, at least some of the functionality of one or more of these modules / units can be combined with at least some of the functionality of other modules / units and implemented in one module / unit. According to embodiments of this disclosure, at least one of the following can be implemented at least partially as hardware circuitry: a first acquisition module 710, a second acquisition module 720, a first acquisition module 730 and a training module 740; a third acquisition module 810, a fourth acquisition module 820, a second acquisition module 830 and a first determination module 840; or a sixth acquisition module 910 and a screening module 920. This can be implemented as hardware or firmware, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or any other reasonable method of integrating or packaging the circuitry. Alternatively, it can be implemented in any one of the three methods—software, hardware, and firmware—or in a suitable combination of any of these methods. Alternatively, at least one of the following modules can be implemented, at least partially, as a computer program module, which can perform corresponding functions when the computer program module is run.

[0130] It should be noted that the training device portion of the prediction model in the embodiments of this disclosure corresponds to the training method portion of the prediction model in the embodiments of this disclosure. For a detailed description of the training device portion of the prediction model, please refer to the training method portion of the prediction model, and it will not be repeated here. Similarly, the hard disk screening standard output device portion in the embodiments of this disclosure corresponds to the hard disk screening standard output method portion of the embodiments of this disclosure. For a detailed description of the hard disk screening standard output device portion, please refer to the hard disk screening standard output method portion, and it will not be repeated here. Likewise, the hard disk screening device portion in the embodiments of this disclosure corresponds to the hard disk screening method portion of the embodiments of this disclosure. For a detailed description of the hard disk screening device portion, please refer to the hard disk screening method portion, and it will not be repeated here.

[0131] Figure 10 A block diagram of an electronic device suitable for implementing at least one of the following methods according to embodiments of the present disclosure: a training method for an application prediction model, a standard output method for disk screening, and a disk screening method. Figure 10 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.

[0132] like Figure 10 As shown, an electronic device 1000 according to an embodiment of the present disclosure includes a processor 1001, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage portion 1008 into a random access memory (RAM) 1003. The processor 1001 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 1001 may also include onboard memory for caching purposes. The processor 1001 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0133] RAM 1003 stores various programs and data required for the operation of electronic device 1000. Processor 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. Processor 1001 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 1002 and / or RAM 1003. It should be noted that the programs may also be stored in one or more memories other than ROM 1002 and RAM 1003. Processor 1001 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0134] According to embodiments of this disclosure, the electronic device 1000 may further include an input / output (I / O) interface 1005, which is also connected to a bus 1004. The system 1000 may also include one or more of the following components connected to the I / O interface 1005: an input section 1006 including a keyboard, mouse, etc.; an output section 1007 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 1008 including a hard disk, etc.; and a communication section 1009 including a network interface card such as a LAN card, modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. A drive 1010 is also connected to the I / O interface 1005 as needed. A removable medium 1011, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 1010 as needed so that computer programs read from it can be installed into the storage section 1008 as needed.

[0135] According to embodiments of this disclosure, the method flow according to embodiments of this disclosure can be implemented as a computer software program. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 1009, and / or installed from removable medium 1011. When the computer program is executed by processor 1001, it performs the functions defined in the system of embodiments of this disclosure. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0136] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0137] According to embodiments of this disclosure, the computer-readable storage medium can be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0138] For example, according to embodiments of this disclosure, a computer-readable storage medium may include the ROM 1002 and / or RAM 1003 described above and / or one or more memories other than ROM 1002 and RAM 1003.

[0139] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of this disclosure. When the computer program product is run on an electronic device, the program code enables the electronic device to implement at least one of the application prediction model training method, hard disk screening standard output method, and hard disk screening method provided in the embodiments of this disclosure.

[0140] When the computer program is executed by the processor 1001, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0141] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 1009, and / or installed from a removable medium 1011. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0142] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0143] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features recited in the various embodiments and / or claims of this disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not expressly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure may be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0144] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A method for training a prediction model, comprising: obtaining target hard disk attribute information of a target hard disk, wherein the target hard disk satisfies a target screening threshold, and the target screening threshold comprises a threshold defined for at least one hard disk attribute information of the target hard disk; obtaining a first hard disk attribute expected value defined by a first service for the target hard disk, wherein the first service has first service type information; inputting the target hard disk attribute information, the first service type information and the first hard disk attribute expected value into a prediction model to be trained to obtain a prediction screening threshold, wherein the prediction screening threshold is used in a case where the target hard disk is applied to the first service, and comprises a threshold predicted for the at least one hard disk attribute information, and wherein the prediction model to be trained is implemented by constructing an algorithm library; and training the prediction model by using the target screening threshold and the prediction screening threshold, wherein training the prediction model comprises: taking the target hard disk attribute information, the first service type information and the first hard disk attribute expected value as input data, taking the target screening threshold as output data, constructing a data set according to the input data and the output data, and training algorithms of the algorithm library based on input and output data in the data set.

2. The method of claim 1, wherein, The target hard disk attribute information and the target hard disk attribute expected value have the same attribute type. The obtaining of the target hard disk attribute information of the target hard disk comprises: determining a sampling period; and in a process of applying the target hard disk to the first service, periodically obtaining the target hard disk attribute information based on the sampling period in response to determining that the target hard disk attribute information satisfies the first hard disk attribute expected value. The obtaining of the target hard disk attribute information of the target hard disk comprises:

3. The method of claim 1, wherein, obtaining first hard disk attribute information of a first hard disk to be screened; and in response to determining that the first hard disk attribute information satisfies a first predefined use condition, determining a first hard disk to be screened corresponding to the first hard disk attribute information as the target hard disk. The target hard disk attribute information comprises at least one of the following: hard disk used time length, hard disk test time length, throughput information and stability information; and the first hard disk attribute expected value comprises at least one of the following: expected use time length, expected throughput information and expected stability information.

4. The method of claim 1, wherein, The first hard disk to be screened comprises at least one of the following: a returned hard disk and an alarm hard disk, wherein the returned hard disk represents a used hard disk, and the alarm hard disk represents a hard disk that has appeared alarm information in a use process.

5. The method of claim 3, wherein, 6.A method for outputting a hard disk screening standard, comprising: obtaining second hard disk attribute information of a second hard disk to be screened; obtaining a second hard disk attribute expected value defined by a second service for the second hard disk to be screened, wherein the second service has second service type information; inputting the second hard disk attribute information, the second service type information and the second hard disk attribute expected value into a prediction model to obtain a standard screening threshold, wherein the prediction model is trained based on the method of any one of claims 1-5; and ​ determine a hard disk screening criterion according to the standard screening threshold.

7. The method of claim 6, further comprising: obtaining third hard disk attribute information of a third hard disk to be screened, wherein the third hard disk to be screened comprises the second hard disk to be screened; in response to determining that the third hard disk attribute information satisfies a second predefined use condition, determining the third hard disk to be screened corresponding to the third hard disk attribute information as the second hard disk to be screened.

8. A hard disk screening method, comprising: obtaining fourth hard disk attribute information of a fourth hard disk to be screened, wherein the fourth hard disk to be screened comprises a hard disk satisfying a third predefined use condition; and screening the fourth hard disk to be screened according to a hard disk screening criterion and the fourth hard disk attribute information, wherein the hard disk screening criterion comprises a standard output by the method of claim 6 or 7.

9. A training device of a prediction model, comprising: a first obtaining module configured to obtain target hard disk attribute information of a target hard disk, wherein the target hard disk satisfies a target screening threshold, and the target screening threshold comprises a threshold defined for at least one hard disk attribute information of the target hard disk; a second obtaining module configured to obtain a first hard disk attribute expected value defined by a first service for the target hard disk, wherein the first service has first service type information; a first obtaining module configured to input the target hard disk attribute information, the first service type information, and the first hard disk attribute expected value into a prediction model to be trained to obtain a prediction screening threshold, wherein the prediction screening threshold is used in a case where the target hard disk is applied to the first service, and comprises a threshold predicted for the at least one hard disk attribute information, and wherein the prediction model to be trained is implemented by constructing an algorithm library; and a training module configured to train the prediction model by using the target screening threshold and the prediction screening threshold, wherein training the prediction model comprises: taking the target hard disk attribute information, the first service type information, and the first hard disk attribute expected value as input data, taking the target screening threshold as output data, constructing a data set according to the input data and the output data, and training an algorithm of the algorithm library based on input-output data in the data set.

10. A hard disk screening criterion output device, comprising: a third obtaining module configured to obtain second hard disk attribute information of a second hard disk to be screened; a fourth obtaining module configured to obtain a second hard disk attribute expected value defined by a second service for the second hard disk to be screened, wherein the second service has second service type information; a second obtaining module configured to input the second hard disk attribute information, the second service type information, and the second hard disk attribute expected value into a prediction model to obtain a standard screening threshold, wherein the prediction model is trained based on the device of claim 9; and a first determining module configured to determine a hard disk screening criterion according to the standard screening threshold.

11. A hard disk screening device, comprising: A sixth obtaining module, configured to obtain fourth hard disk attribute information of a fourth hard disk to be screened, wherein the fourth hard disk to be screened comprises a hard disk satisfying a third predefined use condition; and A screening module, configured to screen the fourth hard disk to be screened according to a hard disk screening standard and the fourth hard disk attribute information, wherein the hard disk screening standard comprises a standard output by the device according to claim 10. 12.An electronic device, comprising: one or more processors; memory storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-8. 13.A computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the method of any of claims 1-8. 14.A computer program product comprising a computer program that, when executed by a processor, implements the method of any of claims 1-8.

Images