Fault prediction method of home subscriber server and related equipment

Abstract

The invention provides a fault prediction method of a home subscriber server and related equipment, and relates to the technical field of communication, and the method comprises the steps: obtaining business index data and resource index data of the home subscriber server, carrying out the preprocessing of the business index data and the resource index data, and obtaining model input features, the model input features are input into a trained prediction model, a fault prediction result is obtained, and the fault prediction result is used for representing whether a fault exists in the home subscriber server in a future preset time period or not. Through the above mode, whether the HSS network element has a fault in a period of time in the future can be accurately predicted in advance, the stability of the HSS network element is ensured, the fault is pre-judged in advance, the occurrence probability of an existing online accident is reduced, and volte and 5G user experience is improved.

Description

Background Art

[0002] With the development of communication technology, the stability of the core network is the key to the quality of user communication. The Home Subscriber Server (HSS) is an important component of the control layer in the IP Multimedia Subsystem (IMS). When the HSS fails, the failure may cause the user to fail to pass the authentication and thus be unable to use network services such as making calls, sending text messages and surfing the Internet. It may also cause user data loss, and the user cannot maintain a continuous network connection during the mobile process.

[0003] In the related art, a threshold is set to determine whether a fault occurs, which results in a delay. An alarm is generated only after the fault occurs. If the HSS fault is not handled in a timely manner, it may cause problems with network services, causing the entire mobile communication system to fail and then collapse.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The present disclosure provides a method for predicting a fault of a home subscriber server and related devices, which at least to a certain extent overcome the problem in the related art that HSS faults cannot be accurately predicted in advance.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0007] In a first aspect, an embodiment of the present disclosure provides a method for predicting a fault of a home subscriber server, the method comprising:

[0008] Obtaining service indicator data and resource indicator data of the home user server;

[0009] Preprocess the business indicator data and resource indicator data to obtain model input features;

[0010] The model input features are input into the trained prediction model to obtain a fault prediction result; wherein the fault prediction result is used to characterize whether the home user server has a fault in a preset time period in the future.

[0011] In a possible embodiment, the prediction model includes: a deep learning network based on a self-attention mechanism and a support vector machine; the deep learning network includes an encoder and a decoder; and the output of the decoder is connected to the input of the support vector machine.

[0012] In a possible embodiment, the model input features are input into a trained prediction model to obtain a fault prediction result, including:

[0013] Input the model input features into the encoder to extract the encoded features with time series;

[0014] Input the encoded features into the decoder to predict future time series values;

[0015] The future time series values ​​are input into the support vector machine to obtain the fault prediction results.

[0016] In a possible embodiment, the training process of the prediction model includes:

[0017] Obtain actual fault data of the home user server;

[0018] Obtain training data sets based on historical monitoring data;

[0019] Based on the training data set, the prediction model is iteratively trained, wherein one iterative training process includes:

[0020] Extract training samples from the training data set and input them into the encoder to extract encoding feature samples with time series;

[0021] Input the encoded feature samples into the decoder to predict future time series value samples;

[0022] Input the future time series value samples into the support vector machine to obtain the sample prediction results;

[0023] Determine the prediction loss function value based on actual fault data and sample prediction results;

[0024] According to the prediction loss function value, the network parameters of the prediction model are adjusted until the prediction loss function value meets the preset value to obtain the trained prediction model.

[0025] In a possible embodiment, obtaining a training data set according to historical monitoring data includes:

[0026] Obtaining historical monitoring data of the home user server; the historical monitoring data includes: historical business indicator data and historical resource indicator data;

[0027] Preprocess the historical monitoring data to obtain the data set to be processed;

[0028] The data set to be processed is divided according to a preset ratio to obtain a training data set.

[0029] In a possible embodiment, the business indicator data and the resource indicator data are preprocessed to obtain model input features, including:

[0030] Stack the business indicator data and resource indicator data in chronological order to obtain multivariate time series data;

[0031] Preprocessing operations are performed on multivariate time series data to obtain model input features; the preprocessing operations at least include: data standardization, missing value processing, and format conversion.

[0032] In a second aspect, an embodiment of the present disclosure provides a fault prediction device for a home user server, including:

[0033] An acquisition unit, used to acquire service indicator data and resource indicator data of a home user server;

[0034] A processing unit, used for preprocessing business indicator data and resource indicator data to obtain model input features;

[0035] The prediction unit is used to input the model input features into the trained prediction model to obtain a fault prediction result; wherein the fault prediction result is used to characterize whether the home user server has a fault in a preset time period in the future.

[0036] In a possible embodiment, the fault prediction device of the home subscriber server further includes:

[0037] Training unit: obtain actual fault data of the user server; obtain a training data set based on historical monitoring data; iteratively train the prediction model based on the training data set, wherein one iterative training process includes: extracting training samples from the training data set and inputting them into the encoder to extract coding feature samples with time series; inputting the coding feature samples into the decoder to predict future time series value samples; inputting the future time series value samples into the support vector machine to obtain sample prediction results; determining the prediction loss function value based on the actual fault data and the sample prediction results; adjusting the network parameters of the prediction model based on the prediction loss function value until the prediction loss function value meets the preset value to obtain a trained prediction model.

[0038] In a third aspect, an embodiment of the present disclosure provides an electronic device, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute the method in the first aspect above by executing the executable instructions.

[0039] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method in the first aspect described above is implemented.

[0040] In a fifth aspect, according to another aspect of the present disclosure, a computer program product or a computer program is also provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs any of the above methods.

[0041] The embodiments of the present disclosure provide a method for predicting a fault of a home user server and related equipment, the method comprising: obtaining the service indicator data and resource indicator data of the home user server, preprocessing the service indicator data and resource indicator data, obtaining model input features, inputting the model input features into a trained prediction model, and obtaining a fault prediction result, wherein the fault prediction result is used to characterize whether the home user server has a fault in a preset time period in the future. Through the above method, it is possible to accurately predict in advance whether the HSS network element will fail in a certain period of time in the future, ensure the stability of the HSS network element, predict faults in advance, reduce the probability of accidents on the current network, and improve the volte and 5G user experience.

[0042] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0044] Figure 1 A system architecture diagram is shown in an embodiment of the present disclosure;

[0045] Figure 2 Another system architecture diagram in an embodiment of the present disclosure is shown;

[0046] Figure 3 A flowchart showing a method for predicting a fault of a home user server in an embodiment of the present disclosure is shown;

[0047] Figure 4 A flowchart showing another method for predicting a fault of a home user server in an embodiment of the present disclosure is shown;

[0048] Figure 5 A flowchart of a preprocessing process in an embodiment of the present disclosure is shown;

[0049] Figure 6A flowchart of a prediction model training process in an embodiment of the present disclosure is shown;

[0050] Figure 7 A schematic diagram showing the structure of a fault prediction device for a home user server according to an embodiment of the present disclosure is shown;

[0051] Figure 8 A schematic structural diagram of an electronic device in an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0052] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that the disclosure will be more comprehensive and complete and to fully convey the concepts of the example embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0053] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0054] The following are explanations of the terms used in this disclosure:

[0055] The Transformer model (literally "transformer") is a deep learning model that uses an attention mechanism, which can assign different weights according to the importance of each part of the input data.

[0056] Support Vector Machine (SVM) is a generalized linear classifier that performs binary classification of data in a supervised learning manner. Its decision boundary is the maximum-margin hyperplane solved for the learning samples.

[0057] Figure 1 A schematic diagram of the system architecture of a method for predicting a fault of a home user server that can be applied in an embodiment of the present disclosure is shown.

[0058] like Figure 1As shown, the fault prediction system 100 of the home subscriber server may include a monitoring module 101 and a prediction module 102 .

[0059] The monitoring module 101 is used to obtain the service indicator data and resource indicator data of the home subscriber server, monitor the HSS network element, and collect the service indicator data of the HSS network element and the resource indicator data of the system.

[0060] The prediction module 102 is used to pre-process the business indicator data and resource indicator data to obtain model input features; input the model input features into the trained prediction model to obtain fault prediction results; wherein the fault prediction results are used to characterize whether the user server has a fault in a preset time period in the future.

[0061] The fault prediction system 100 of the home user server can be deployed in the existing network management system.

[0062] The service indicator data is the service-related data of HSS, which may at least include: the total number of long-term evolution voice bearer (Voiceover Long-Term Evolution, volte) users, authentication failure rate, location update failure rate, HSS response time to user, number of user authentication attempts, and authentication success rate.

[0063] Resource indicator data is system resource related data, and system resource related data may include: system computing power resources and network resources, etc. Resource indicator data may include at least: memory information, central processing unit (CPU) information, bandwidth information and input / output (IO) information.

[0064] Figure 2 A schematic diagram of the system architecture of another method for predicting a fault of a home user server that can be applied in an embodiment of the present disclosure is shown.

[0065] like Figure 2 As shown, the fault prediction system 100 of the home user server may further include: a model building module 201 .

[0066] The model building module 201 is used to build and deploy a prediction model so that the prediction model is used to predict the fault prediction results of the HSS network element.

[0067] The model building module 201 obtains a training data set through historical monitoring data, trains an untrained prediction model, determines a prediction loss function value, and adjusts the network parameters of the prediction model until the prediction loss function value meets a preset value, thereby obtaining a trained prediction model.

[0068] Through the above system, the present disclosure can predict in advance whether there is a fault in the HSS network element, reduce the probability of accidents in the existing network, and improve the volte and 5G user experience.

[0069] The present exemplary implementation is described in detail below with reference to the accompanying drawings and embodiments.

[0070] First, an embodiment of the present disclosure provides a method for predicting a fault of a home user server. The method can be executed by any electronic device with computing and processing capabilities. In the following process, a fault prediction system in which the electronic device is a home user server is taken as an example.

[0071] Figure 3 A flowchart of a method for predicting a fault of a home user server in an embodiment of the present disclosure is shown. Figure 3 As shown, the following steps are included:

[0072] S302: Acquire service indicator data and resource indicator data of the home user server.

[0073] S304: Preprocess the business indicator data and resource indicator data to obtain model input features.

[0074] S306: Inputting the model input features into the trained prediction model to obtain a fault prediction result, wherein the fault prediction result is used to characterize whether the home user server has a fault in a preset time period in the future.

[0075] The fault prediction result may be a probability value.

[0076] In a possible embodiment, a preset period can be set, for example, 30 minutes as a period. Each time preprocessing is performed, the business indicator data and resource indicator data of the belonging user server 30 minutes before the current moment are extracted, and the model input features are obtained after processing. After inputting into the prediction model, the fault prediction results of the preset time period are obtained. The preset time period can be set to 5 minutes.

[0077] In this way, by extracting 30 minutes of service indicator data and resource indicator data of the home user server each time, it can be determined whether the home user server has a fault within the next 5 minutes.

[0078] In a possible embodiment, based on the fault prediction result, if it is determined that the HSS has a fault, an alarm is issued; if it is determined that no fault has occurred, a record is made.

[0079] Through the above method, the probability of HSS failure within a preset time period in the future can be predicted in advance based on the data indicators of the HSS network element in different time periods, and the failure can be predicted in advance to ensure the stability of the HSS network element, thereby ensuring the stability of the entire communication system and improving user experience.

[0080] In a possible embodiment, the structure of the prediction model may include multiple ones, and a conventional prediction model may be used for prediction. An exemplary structure is given in the embodiment of the present disclosure, and the prediction model may include: a deep learning network and a support vector machine based on a self-attention mechanism; the deep learning network includes an encoder and a decoder; the output end of the decoder is connected to the input end of the support vector machine.

[0081] Figure 4 A flowchart of another method for predicting a fault of a home user server in an embodiment of the present disclosure is shown. Figure 4 As shown, the following steps are included:

[0082] S402: Input the model input features into the encoder to extract the encoding features with time series.

[0083] S404: Input the encoded features into the decoder to predict future time series values.

[0084] S406: Input the future time series value into the support vector machine to obtain a fault prediction result.

[0085] Through the prediction model of the Transformer+SVM joint structure, the self-attention mechanism is used for information interaction and transmission. This mechanism allows the model to pay attention to information at different positions when processing sequence data. The encoder in the Transformer is used to extract the features of the time series, and the decoder in the Transformer is used to predict the future time series values. Then it is input into the SVM. The SVM has the advantages of no local minimum and strong generalization ability. The SVM is used to obtain the final fault prediction result, improve the stability and accuracy of the multi-time series data processing of the business indicator data and resource indicator data of the user server, and then accurately predict the fault prediction results in advance, so as to avoid and handle faults in advance, enhance the stability of the entire communication network, and improve the user experience.

[0086] Among them, the above-mentioned prediction model needs to be trained, and its training process may include multiple methods. An example is given in the present disclosure to illustrate the training process. The training process of the prediction model can be offline training or real-time training. Real-time training, that is, the business indicator data and resource indicator data collected by the network management system are used to further train the prediction model and update the prediction model in real time.

[0087] Figure 5 A flowchart of a preprocessing process in an embodiment of the present disclosure is shown. Figure 5 As shown, the following steps are included:

[0088] S502: stacking the business indicator data and the resource indicator data in chronological order to obtain multivariate time series data.

[0089] S504: Preprocessing the multivariate time series data to obtain model input features, where the preprocessing operation at least includes: data standardization, missing value processing, and format conversion.

[0090] The data is preprocessed in the above manner to obtain model input features that meet format requirements and can be input into the model.

[0091] Figure 6 A flowchart of a prediction model training process in an embodiment of the present disclosure is shown. Figure 6 As shown, the following steps are included:

[0092] S602: Acquire actual fault data of the home user server.

[0093] In a possible embodiment, actual fault data is used as a label value to calculate a predicted loss function value for the constructed prediction loss function.

[0094] S604: Obtain a training data set based on historical monitoring data.

[0095] In a possible embodiment, the method of acquiring the training data set in the present disclosure is not limited to this, and the present disclosure exemplifies an acquisition method.

[0096] Exemplarily, historical monitoring data of a home user server is obtained; the historical monitoring data includes historical business indicator data and historical resource indicator data, the historical monitoring data is preprocessed to obtain a data set to be processed, and the data set to be processed is divided according to a preset ratio to obtain a training data set.

[0097] The acquired historical monitoring data can be stacked in a time series queue with a period of 30 minutes and processed to obtain a data set to be processed.

[0098] The preset ratio can be any ratio. After division, a training data set and a test data set can be obtained. The training data set is used for training the prediction model, and the test data set is used for testing after the training process of the prediction model is completed. If the test passes, a trained prediction model is obtained.

[0099] S606: Extract training samples from the training data set and input them into the encoder to extract coding feature samples with time series.

[0100] S608: Input the encoded feature samples into the decoder to predict future time series value samples.

[0101] S610: Input future time series value samples into the support vector machine to obtain sample prediction results.

[0102] S612: Determine the prediction loss function value based on the actual fault data and sample prediction results.

[0103] In a possible embodiment, the prediction loss function is used to obtain the prediction loss function, and when the prediction loss function satisfies a preset value, the training process is terminated.

[0104] Exemplarily, the present disclosure illustrates a constructed prediction loss function, as shown in formula (1).

[0105]

[0106] Where n represents the number of training samples; Y k represents the actual fault data of the kth training sample; represents the sample prediction result of the kth training sample, and MSE represents the overall error between the n sample prediction results and the actual fault data.

[0107] It should be noted that there are many ways to construct a prediction loss function. The mean square error (MSE) loss function constructed in this disclosure is only an example.

[0108] S614: Determine whether the predicted loss function value meets the preset value; if not, execute S616; if so, execute S618.

[0109] S616: Adjust the network parameters of the prediction model according to the prediction loss function value, and return to step S606.

[0110] S618: Obtain the trained prediction model.

[0111] The prediction model is trained in the above manner to obtain a trained prediction model. After testing, the best training model is saved and deployed to predict the failure of the HSS network element.

[0112] Based on the same inventive concept, the present disclosure also provides a fault prediction device for a home user server, such as the following embodiment. Since the principle of solving the problem in the device embodiment is similar to that in the above method embodiment, the implementation of the device embodiment can refer to the implementation of the above method embodiment, and the repeated parts will not be repeated.

[0113] Figure 7 A schematic diagram showing the structure of a fault prediction device for a home user server in an embodiment of the present disclosure is shown. Figure 7 As shown, the fault prediction device 70 of the belonging user server includes: an acquisition unit 701, used to obtain the business indicator data and resource indicator data of the belonging user server; a processing unit 702, used to pre-process the business indicator data and resource indicator data to obtain model input features; a prediction unit 703, used to input the model input features into a trained prediction model to obtain a fault prediction result; wherein the prediction model is composed of a deep learning network based on a self-attention mechanism and a support vector machine.

[0114] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0115] Refer to the following Figure 8 The electronic device 800 according to this embodiment of the present disclosure is described. Figure 8 The electronic device 800 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0116] like Figure 8 As shown, the electronic device 800 is in the form of a general computing device. The components of the electronic device 800 may include but are not limited to: at least one processing unit 810, at least one storage unit 820, and a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810).

[0117] The storage unit stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 performs the steps of various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification. For example, the processing unit 810 can perform any step of the above method embodiments.

[0118] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 8201 and / or a cache memory unit 8202 , and may further include a read-only memory unit (ROM) 8203 .

[0119] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0120] Bus 830 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0121] The electronic device 800 may also communicate with one or more external devices 840 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 800, and / or communicate with any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 850. Furthermore, the electronic device 800 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 860. As shown, the network adapter 860 communicates with other modules of the electronic device 800 via a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0122] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0123] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer program product or a computer program, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method in the above embodiment.

[0124] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. A program product capable of implementing the above method of the present disclosure is stored thereon. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above “Exemplary Method” section of this specification.

[0125] More specific examples of computer-readable storage media in the present disclosure may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0126] In the present disclosure, a computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein a readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A readable signal medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0127] Alternatively, the program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0128] In a specific implementation, the program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0129] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0130] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0131] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0132] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. The present disclosure is intended to cover any variations, uses or adaptations of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The description and examples are intended to be exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

Claims

1. A method for predicting a fault of a home user server, characterized in that: The method comprises: Obtaining service indicator data and resource indicator data of the home user server; Preprocessing the business indicator data and resource indicator data to obtain model input features; The model input feature is input into a trained prediction model to obtain a fault prediction result; wherein the fault prediction result is used to characterize whether the home user server has a fault in a preset time period in the future.

2. The method according to claim 1, characterized in that: The prediction model includes: a deep learning network and a support vector machine based on a self-attention mechanism; the deep learning network includes an encoder and a decoder; the output end of the decoder is connected to the input end of the support vector machine.

3. The method according to claim 2, characterized in that The step of inputting the model input features into the trained prediction model to obtain a fault prediction result includes: Inputting the model input features into the encoder to extract encoding features with time series; Inputting the encoded features into a decoder to predict future time series values; The future time series values ​​are input into the support vector machine to obtain a fault prediction result.

4. The method according to claim 2, characterized in that: The training process of the prediction model includes: Acquiring actual fault data of the home subscriber server; Obtain training data sets based on historical monitoring data; Based on the training data set, the prediction model is iteratively trained, wherein one iterative training process includes: Extracting training samples from the training data set and inputting them into the encoder to extract encoding feature samples with time series; Inputting the encoded feature samples into a decoder to predict future time series value samples; Inputting the future time series value samples into the support vector machine to obtain sample prediction results; Determining a prediction loss function value according to the actual fault data and the sample prediction result; According to the prediction loss function value, the network parameters of the prediction model are adjusted until the prediction loss function value meets the preset value, thereby obtaining a trained prediction model.

5. The method according to claim 4, characterized in that The step of obtaining a training data set based on historical monitoring data includes: Acquire historical monitoring data of the home user server; the historical monitoring data includes: historical service indicator data and historical resource indicator data; Preprocessing the historical monitoring data to obtain a data set to be processed; The data set to be processed is divided according to a preset ratio to obtain a training data set.

6. The method according to claim 1, characterized in that The preprocessing of the business indicator data and resource indicator data to obtain model input features includes: Stacking the business indicator data and the resource indicator data in chronological order to obtain multivariate time series data; The multivariate time series data is preprocessed to obtain the model input features; the preprocessing operation at least includes: data standardization, missing value processing, and format conversion.

7. A fault prediction device for a home user server, characterized in that: include: An acquisition unit, used to acquire service indicator data and resource indicator data of a home user server; A processing unit, used to pre-process the business indicator data and resource indicator data to obtain model input features; The prediction unit is used to input the model input features into the trained prediction model to obtain a fault prediction result; wherein the fault prediction result is used to characterize whether the home user server has a fault in a preset time period in the future.

8. An electronic device, characterized in that: include: processor; as well as A memory, configured to store executable instructions of the processor; The processor is configured to perform the method of any one of claims 1 to 6 by executing the executable instructions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product comprising: A computer program or instruction, characterized in that when the computer program or instruction is executed by a processor, the method described in any one of claims 1 to 6 is implemented.

Images