Fault detection method and device, computer storable medium

Abstract

The present disclosure relates to a fault detection method and device, and a computer storage medium, and relates to the technical field of big data or artificial intelligence. The fault detection method comprises: acquiring a plurality of log data, wherein each piece of log data has a position identifier and a data category, and the position identifiers of the plurality of log data reflect the time sequence relationship of the plurality of log data; performing a cyclic code encoding operation according to the position identifier and the data category of each piece of log data to obtain a cyclic code of each piece of log data, wherein the cyclic code comprises a position code corresponding to the position identifier and a category code corresponding to the data category; and determining fault positioning information by using a sequence model according to the cyclic codes of the plurality of log data. According to the present disclosure, rapid and accurate fault detection can be achieved.

Description

Technical Field

[0001] This disclosure relates to the fields of big data or artificial intelligence technology, and in particular to fault detection methods and devices, and computer-storable media. Background Technology

[0002] The development of new technologies such as cloud computing, blockchain, and 6G mobile communication has driven massive new demands for servers, which are evolving towards centralized and integrated management. Virtualized server resources bring more efficient resource utilization, but also present significant challenges for fault detection. Overly complex internal structures make it difficult for developers to quickly debug and test. Therefore, how to quickly determine the time and type of faults through intelligent technologies is a highly significant research direction for the future. Summary of the Invention

[0003] This disclosure presents a solution that enables rapid and accurate fault detection.

[0004] According to a first aspect of this disclosure, a fault detection method is provided, comprising: acquiring multiple log data entries, wherein each log data entry has a location identifier and a data category, the location identifier of the multiple log data entries reflecting the temporal relationship of the multiple log data entries; performing a cyclic code encoding operation based on the location identifier and data category of each log data entry to obtain a cyclic code for each log data entry, wherein the cyclic code includes a location code corresponding to the location identifier and a category code corresponding to the data category; and determining fault location information using a sequence model based on the cyclic codes of the multiple log data entries.

[0005] In some embodiments, performing a cyclic code encoding operation based on the location identifier and data category of each log data entry includes: encoding the location identifier of each log data entry to obtain the location code; constructing a corresponding generator polynomial based on the data category of each log data entry; determining a corresponding generator matrix based on the generator polynomial of each log data entry; generating the category code based on the location code and the corresponding generator matrix of each log data entry; and determining a corresponding cyclic code based on the location code and category code of each log data entry.

[0006] In some embodiments, determining fault location information based on the cycle codes of multiple log data using a sequence model includes: grouping the multiple log data to obtain multiple sets of log data; merging the cycle codes corresponding to each set of log data to obtain a word embedding matrix corresponding to each set of log data; and determining fault location information based on the word embedding matrices corresponding to the multiple sets of log data using the sequence model.

[0007] In some embodiments, the sequence model includes an encoder, a decoder, and a softmax layer. Determining fault location information using the sequence model based on word embedding matrices corresponding to multiple sets of log data includes: determining the hidden layer semantic vector of each word embedding matrix using the encoder; determining the weight of the hidden layer semantic vector of each word embedding matrix using an attention mechanism, wherein the weight represents the importance of the data category to fault detection; and determining the fault location information using the decoder and the softmax layer based on the hidden layer semantic vectors of the multiple word embedding matrices and their corresponding weights.

[0008] In some embodiments, using an attention mechanism to determine the weights of the hidden layer semantic vectors of each word embedding matrix includes: determining the chi-square test value corresponding to the data category of each group of log data, wherein the chi-square test value characterizes the importance of the data category of the corresponding group of log data to fault detection; and determining the weights of the hidden layer semantic vectors of each word embedding matrix based on the chi-square test value corresponding to each word embedding matrix.

[0009] In some embodiments, determining fault location information based on the hidden layer semantic vectors of the plurality of word embedding matrices and their corresponding weights, using the decoder and the softmax layer, includes: multiplying the hidden layer semantic vector corresponding to each word embedding matrix by the weights; and inputting the product obtained by multiplication sequentially into the decoder and the softmax layer to obtain fault location information.

[0010] In some embodiments, the fault detection method further includes: determining the location identifier of each log data based on the timestamp information of multiple log data.

[0011] According to a second aspect of this disclosure, a fault detection device is provided, comprising: an acquisition module configured to acquire multiple log data entries, wherein each log data entry has a location identifier and a data category, the location identifier of the multiple log data entries reflecting the temporal relationship of the multiple log data entries; an execution module configured to perform a cyclic code encoding operation based on the location identifier and data category of each log data entry to obtain a cyclic code for each log data entry, wherein the cyclic code includes a location code corresponding to the location identifier and a category code corresponding to the data category; and a determination module configured to determine fault location information based on the cyclic code of the multiple log data entries using a sequence model.

[0012] According to a third aspect of this disclosure, a fault detection apparatus is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute the fault detection method described in any of the above embodiments based on instructions stored in the memory.

[0013] According to a fourth aspect of this disclosure, a computer-storeable medium is provided having computer program instructions stored thereon, which, when executed by a processor, implement the fault detection method described in any of the above embodiments.

[0014] In the above embodiments, rapid and accurate fault detection can be achieved. Attached Figure Description

[0015] The accompanying drawings, which form part of this specification, illustrate embodiments of this disclosure and, together with the specification, serve to explain the principles of this disclosure.

[0016] This disclosure will become clearer with reference to the accompanying drawings and the following detailed description, wherein:

[0017] Figure 1 This is a flowchart illustrating a fault detection method according to some embodiments of the present disclosure;

[0018] Figure 2 This is a schematic diagram illustrating the process of obtaining a word embedding matrix according to some embodiments of the present disclosure;

[0019] Figure 3 This is a schematic diagram illustrating the determination of fault location information according to some embodiments of the present disclosure;

[0020] Figure 4 This is a block diagram illustrating a fault detection apparatus according to some embodiments of the present disclosure;

[0021] Figure 5 This is a block diagram illustrating a fault detection apparatus according to other embodiments of the present disclosure;

[0022] Figure 6 This is a block diagram illustrating a computer system for implementing some embodiments of the present disclosure. Detailed Implementation

[0023] Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that, unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present disclosure.

[0024] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0025] The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use.

[0026] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0027] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0028] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0029] Figure 1 This is a flowchart illustrating a fault detection method according to some embodiments of the present disclosure.

[0030] like Figure 1 As shown, the fault detection method includes steps S110-S130.

[0031] In step S110, multiple log data entries are acquired. Each log data entry has a location identifier and a data category. The location identifiers of the multiple log data entries reflect their temporal sequence. In some embodiments, the location identifier of each log data entry can be determined based on the timestamp information of the multiple log data entries.

[0032] In some embodiments, multiple log entries are generated by the same type of calling program. For example, multiple log entries may be port call data, and the data categories or log types of port call data include system information acquisition, network communication, file operations, service behavior, registry behavior, and operation process behavior. Log data is text data generated by print output code embedded in a program; it records key information such as variables and execution status during program runtime. Log data is a series of time-based server information.

[0033] In step S120, a cycle code encoding operation is performed based on the location identifier and data category of each log data entry to obtain a cycle code for each log data entry. The cycle code includes the location code corresponding to the location identifier and the category code corresponding to the data category.

[0034] Typically, vectorized text information can be obtained directly from existing corpora or trained on a network as unknown parameters. This disclosure is applied to server log data scenarios where the associated corpora are relatively small, requiring custom model training. Without prior information, one-hot encoding is often used. While simple to implement, this encoding is prone to the curse of dimensionality and fails to capture the correlation and sequence information between different types of text information.

[0035] Based on this, the inventors innovatively use a combination of linear block codes and word embedding: the information bits of the cyclic code record the position information of the text, while the redundant bits generated by the generator polynomial of the cyclic code record the category information of the text. Different Hamming distances of the cyclic code represent the differences between different codes. The original intention of the Hamming distance design is to prevent errors in channel transmission and provide redundancy for error correction. In this disclosure, however, this distance is innovatively used to distinguish the differences between texts. If the log data belongs to the same category, the Hamming distance is small; if the log data belongs to different categories, the Hamming distance is large. This is the basic innovative idea of ​​this disclosure for word embedding encoding using cyclic codes.

[0036] In the above embodiments, based on the channel coding in communication, the cycle code of each log data is determined, so that text data such as log data is quantified or vectorized, which makes it easier for neural networks such as sequence models to understand, process and learn features. This allows the neural network to capture sequence information more quickly and reduces the difficulty of network training convergence.

[0037] In some embodiments, step S120 can be implemented in the following manner.

[0038] First, the location identifier of each log data entry is encoded to obtain a location code. A timestamp is generated the instant the log data is created. The timestamp information not only records the time but also the order in which the log information was generated. Based on this, this disclosure innovatively references the information bits in linear block codes for encoding.

[0039] For example, taking 1024 log data entries as an example, the log entry with sequence 1 is encoded as 0000000001 (nine zeros and one one), the log entry with sequence 2 is encoded as 0000000010, and the log entry with sequence 512 is encoded as 0100000000. And so on, the location encoding information can be obtained. Compared to one-hot encoding, which is 1024-dimensional, the information bit portion of the encoding disclosed herein is only 10-dimensional, significantly reducing data dimensionality and improving the data processing efficiency for fault detection or location.

[0040] Secondly, a corresponding generator polynomial is constructed based on the data category of each log data entry. The essence of cyclic code encoding lies in the fact that all codewords, after shifting, remain code groups, and the maximum term of the parity check bit is always one less than the generator polynomial. Therefore, setting the power of the generator polynomial, from a certain perspective, fixes the vector space of the cyclic code. If the vector space is very large, the encoded information will be more precise, but it will also be more complex. If the text information itself is not extensive, an excessively large vector space will only increase complexity and make model convergence more difficult. Therefore, this disclosure innovatively sets the maximum term of the generator polynomial based on the type of log data. If there are n types of log data, then the maximum term of the generator polynomial is n+1, thus providing a vector space that matches the data and constructs a vector space adapted to the data complexity.

[0041] Next, the corresponding generator matrix is ​​determined based on the generator polynomial of each log data.

[0042] Then, a category code is generated based on the location code of each log data and the corresponding generation matrix.

[0043] Linear block codes increase the Hamming distance between different coded sequences by adding a check bit to the information bits, thus mitigating bit errors that occur during channel transmission. If the erroneous symbol is smaller than the Hamming distance, it can be determined whether a transmission error has occurred. In the above embodiments, this disclosure innovatively combines log data types with the check bits of cyclic codes, transforming the log data type into a check bit (redundancy bit) in the cyclic code. By setting different Hamming distances to express the differences between log information, it assists the sequence model in learning corresponding features, enabling more accurate fault detection or location.

[0044] Finally, the corresponding cycle code is determined based on the position code and category code of each log data.

[0045] Figure 2 This is a schematic diagram illustrating the process of obtaining a word embedding matrix according to some embodiments of the present disclosure.

[0046] like Figure 2 As shown, each log entry has location information and a data category. The location information of each log entry is encoded to obtain a location code. A generator polynomial is constructed based on the data category of each log entry, and then a generator matrix is ​​determined based on the generator polynomial. The location code is multiplied by the generator matrix to generate the category code. The location code and category code serve as the information bits and redundant bits of the cyclic code, respectively, together forming the cyclic code.

[0047] return Figure 1In step S130, fault location information is determined using a sequence model based on the cycle codes of multiple log data. In some embodiments, server log activity information from the Tianchi platform (open source) can be used as training data to train the sequence model. For example, the sequence model is a Transformer model.

[0048] In some embodiments, fault location information can be determined by using a sequence model based on the cyclic codes of multiple log data in the following manner.

[0049] First, the multiple log data entries are grouped to obtain multiple groups of log data.

[0050] Then, the cycle codes corresponding to each group of log data are merged to obtain the word embedding matrix corresponding to each group of log data. For example... Figure 2 As shown, positional encoding and category encoding are combined (e.g., sequential concatenation) to obtain a cyclic code. Multiple log data from a set of log data are merged to obtain a word embedding matrix.

[0051] Finally, based on the word embedding matrix corresponding to multiple sets of log data, the fault location information is determined using the sequence model.

[0052] In some embodiments, the sequence model includes an encoder, a decoder, and a softmax layer (normalization layer). In this case, fault location information can be determined using the sequence model based on word embedding matrices corresponding to multiple sets of log data in the following manner.

[0053] First, based on multiple word embedding matrices, the encoder is used to determine the hidden layer semantic vector of each word embedding matrix.

[0054] Then, using an attention mechanism, the weights of the hidden layer semantic vectors of each word embedding matrix are determined, where the weights characterize the importance of data categories to fault detection. In some embodiments, the chi-square test value corresponding to the data category of each group of log data is first determined; then, for each word embedding matrix, the weights of the hidden layer semantic vectors of each word embedding matrix are determined based on the chi-square test value corresponding to each word embedding matrix. The chi-square test value characterizes the importance of the data category of the corresponding group of log data to fault detection. If the chi-square test value of a log data category in fault detection is large, then this type of data is given a larger weight, and vice versa, helping the neural network to better understand the semantic features or meaning of the log data.

[0055] In the above embodiments, an attention mechanism layer is added to neural networks such as sequence models based on the variance of log data and fault detection. The chi-square test value reflects the magnitude of the difference between the theoretical frequency and the actual frequency; the greater the difference (the larger the numerator), the larger the chi-square test value; conversely, the smaller the chi-square test value. Therefore, this disclosure uses the chi-square test value to determine the importance of the type / category of log data for fault detection. For example, the registry behavior of an abnormal program will be significantly greater than that of a normal program. Therefore, when determining whether a new program is abnormal, more attention will be paid to registry behavior because the frequency of normal and abnormal programs accessing such ports is very different.

[0056] Attention mechanisms assign different weights to sequences at different positions, offering significant advantages when sequences are long. Networks and servers generate massive amounts of log data synchronously during operation, and this data varies greatly in type. Some data is crucial and directly impacts fault detection results (e.g., service mode), while others are simply timestamps (e.g., time). Since different behavioral data within the logs have varying impacts on whether a fault has occurred, this disclosure proposes the aforementioned attention mechanism based on the characteristics of log data. This mechanism assigns different weights to the impact of data type on fault detection, thereby improving the accuracy of fault detection or fault localization.

[0057] Finally, based on the hidden layer semantic vectors of the multiple word embedding matrices and their corresponding weights, the fault location information is determined using the decoder and the softmax layer. In some embodiments, the hidden layer semantic vector corresponding to each word embedding matrix is ​​multiplied by its weight; the product is then sequentially input into the decoder and the softmax layer to obtain the fault location information.

[0058] Figure 3 This is a schematic diagram illustrating the determination of fault location information according to some embodiments of the present disclosure.

[0059] like Figure 3As shown, each word embedding matrix is ​​input as a sentence vector into the encoder, resulting in the hidden layer semantic vector output by the encoder. Taking the encoder input sentence vectors 1, 2, 3, and 4 as an example, the encoder outputs hidden layer semantic vectors C1, C2, C3, and C4. The sequence model, as a neural network model, provides an attention mechanism. This attention mechanism performs a chi-square test on each group of log data 1, 2, 3, and 4, obtaining the corresponding chi-square test values. The data categories of each group of log data are the same. The chi-square test value characterizes the importance of the data category of the corresponding group of log data to fault detection. The chi-square test value of each group of log data is used as the weight of the hidden layer semantic vector corresponding to each group of log data. The product of this weight and the hidden layer semantic vector is then passed through the data decoder and the softmax layer to obtain the outputs of sentence vectors 1, 2, 3, and 4, respectively, which serve as fault location information.

[0060] Figure 3 The neural network model shown employs a seq2seq architecture, which is common to sequence models. Compared to RNNs, it can freely control the lengths of the input and output sequences. This disclosure processes log data generated by a network or server, using log information to determine the type of fault. Since the amount of log data generated within a single time period is variable, a seq2seq architecture is used, ensuring that the output at each time step is constrained by the entire input sequence. The essence of the seq2seq architecture can be viewed as a conditional language model (i.e., a conditional probability model): P(Y│X)=P(y_1│x)P(y_2│y_1,x)…

[0061] In some embodiments, the encoder can be implemented using a recurrent neural network, where the hidden layer semantic vector is the last hidden state of the recurrent neural network. This hidden state is passed to the decoder after passing through a fully connected layer. The input to the encoder is a vector obtained by convolution and pooling the word vector matrix, which is fed into the encoder in fixed-length groups of 30 log data entries.

[0062] In some embodiments, the decoder may also employ a recurrent neural network. During training, the decoder accepts the hidden state provided by the encoder and the output vector of the convolutional layer as input. During prediction, since there is no target sequence, it accepts the output of the decoder from the previous time step and the hidden state provided by the encoder as input, and outputs the probability distribution predicted at the next time step.

[0063] In the above embodiments, log data enables the location of abnormal requests, the tracing of program execution logic, and the execution of more granular fault diagnosis. Location identifiers reflect the temporal information of the log data, allowing sequence models to capture this information. Combined with data categories, this enables rapid and accurate fault detection or location, improving fault detection performance and facilitating cloud-network convergence.

[0064] Figure 4 This is a block diagram illustrating a fault detection apparatus according to some embodiments of the present disclosure.

[0065] like Figure 4 As shown, the fault detection device 4 includes an acquisition module 41, an execution module 42, and a determination module 43.

[0066] The acquisition module 41 is configured to acquire multiple log data entries, each of which has a location identifier and a data category. The location identifiers of the multiple log data entries reflect their temporal relationship. For example, when performing an operation... Figure 1 The step S110 is shown.

[0067] Execution module 42 is configured to perform a cycle code encoding operation based on the location identifier and data category of each log data entry to obtain a cycle code for each log data entry. The cycle code includes a location code corresponding to the location identifier and a category code corresponding to the data category. For example, executing... Figure 1 The step S120 shown.

[0068] Module 43 is configured to determine fault location information based on the cycle codes of multiple log data entries using a sequence model, for example, by executing... Figure 1 The step S130 shown.

[0069] Figure 5 This is a block diagram illustrating a fault detection apparatus according to other embodiments of the present disclosure.

[0070] like Figure 5 As shown, the fault detection device 5 includes a memory 51 and a processor 52 coupled to the memory 51. The memory 51 is used to store instructions for executing embodiments of the fault detection method. The processor 52 is configured to execute fault detection methods in any of the embodiments of this disclosure based on the instructions stored in the memory 51.

[0071] Figure 6 This is a block diagram illustrating a computer system for implementing some embodiments of the present disclosure.

[0072] like Figure 6 As shown, the computer system 60 can be represented in the form of a general computing device. The computer system 60 includes a memory 610, a processor 620, and a bus 600 connecting different system components.

[0073] The memory 610 may include, for example, system memory, non-volatile storage media, etc. The system memory may store, for example, an operating system, application programs, a boot loader, and other programs. The system memory may include volatile storage media, such as random access memory (RAM) and / or cache memory. The non-volatile storage media may store, for example, instructions for performing at least one embodiment of a fault detection method. Non-volatile storage media include, but are not limited to, disk storage, optical storage, flash memory, etc.

[0074] The processor 620 can be implemented using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete hardware components such as discrete gates or transistors. Accordingly, each module, such as the decision module and the determination module, can be implemented by executing instructions in the central processing unit (CPU) memory to perform the corresponding steps, or by implementing dedicated circuitry to perform the corresponding steps.

[0075] Bus 600 can use any of the various bus architectures. For example, bus architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, and Peripheral Component Interconnect (PCI) bus.

[0076] The computer system 60 may also include an input / output interface 630, a network interface 640, and a storage interface 650. These interfaces 630, 640, and 650, as well as the memory 610 and processor 620, can be connected via a bus 600. The input / output interface 630 provides a connection interface for input / output devices such as a monitor, mouse, and keyboard. The network interface 640 provides a connection interface for various networked devices. The storage interface 650 provides a connection interface for external storage devices such as floppy disks, USB flash drives, and SD cards.

[0077] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations thereof, can be implemented by computer-readable program instructions.

[0078] These computer-readable program instructions are provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable device to produce a machine, such that execution of the instructions by the processor produces means for implementing the functions specified in one or more boxes of the flowchart and / or block diagram.

[0079] These computer-readable program instructions may also be stored in a computer-readable storage medium. These instructions cause a computer to work in a particular manner to produce an article of manufacture, including instructions that implement the functions specified in one or more boxes in a flowchart and / or block diagram.

[0080] This disclosure may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects.

[0081] The fault detection method and apparatus, and the computer storage medium described in the above embodiments can achieve rapid and accurate fault detection.

[0082] The fault detection method and apparatus, and the computer-storable medium according to this disclosure have been described in detail above. To avoid obscuring the concept of this disclosure, some details known in the art have not been described. Those skilled in the art can fully understand how to implement the technical solutions disclosed herein based on the above description.

Claims

1. A fault detection method, comprising: obtaining a plurality of log data, wherein each log data has a position identifier and a data category, and the position identifiers of the plurality of log data reflect a time sequence relationship of the plurality of log data; performing a cyclic code encoding operation according to the position identifier and the data category of each log data to obtain a cyclic code of each log data, comprising: encoding the position identifier of each log data to obtain a position code, constructing a corresponding generator polynomial according to the data category of each log data, determining a corresponding generator matrix according to the generator polynomial of each log data, generating a category code according to the position code and the corresponding generator matrix of each log data, and determining a corresponding cyclic code according to the position code and the category code of each log data, wherein the cyclic code comprises the position code corresponding to the position identifier and the category code corresponding to the data category; determining fault positioning information by using a sequence model according to the cyclic codes of the plurality of log data, comprising: grouping the plurality of log data to obtain a plurality of groups of log data, merging the cyclic codes corresponding to each group of log data to obtain a word embedding matrix corresponding to each group of log data, and determining the fault positioning information by using the sequence model according to the word embedding matrices corresponding to the plurality of groups of log data.

2. The fault detection method of claim 1, wherein, The sequence model comprises an encoder, a decoder and a softmax layer, and determining the fault positioning information by using the sequence model according to the word embedding matrices corresponding to the plurality of groups of log data comprises: determining a hidden layer semantic vector of each word embedding matrix by using the encoder according to the plurality of word embedding matrices; determining a weight of the hidden layer semantic vector of each word embedding matrix by using an attention mechanism, wherein the weight represents the importance of the data category to fault detection; determining the fault positioning information by using the decoder and the softmax layer according to the hidden layer semantic vectors of the plurality of word embedding matrices and the corresponding weights.

3. The fault detection method of claim 2, wherein, Determining the weight of the hidden layer semantic vector of each word embedding matrix by using the attention mechanism comprises: determining a chi-square test value corresponding to the data category of each group of log data, wherein the chi-square test value represents the importance of the data category of the corresponding group of log data to fault detection; and determining the weight of the hidden layer semantic vector of each word embedding matrix according to the chi-square test value corresponding to each word embedding matrix.

4. The fault detection method of claim 3, wherein, Determining the fault positioning information by using the decoder and the softmax layer according to the hidden layer semantic vectors of the plurality of word embedding matrices and the corresponding weights comprises: multiplying the hidden layer semantic vector corresponding to each word embedding matrix by the weight; inputting the product obtained by multiplication into the decoder and the softmax layer in sequence to obtain the fault positioning information.

5. The fault detection method of claim 1, further comprising: determining the position identifier of each log data according to timestamp information of the plurality of log data.

6. A fault detection apparatus, comprising: an obtaining module configured to obtain a plurality of log data, wherein each log data has a position identifier and a data category, and the position identifiers of the plurality of log data reflect a time sequence relationship of the plurality of log data; The execution module is configured to perform a cyclic code encoding operation according to the position identifier and the data category of each piece of log data to obtain a cyclic code of each piece of log data, including: encoding the position identifier of each piece of log data to obtain a position code, constructing a corresponding generating polynomial according to the data category of each piece of log data, determining a corresponding generating matrix according to the generating polynomial of each piece of log data, generating a category code according to the position code and the corresponding generating matrix of each piece of log data, and determining a corresponding cyclic code according to the position code and the category code of each piece of log data, wherein the cyclic code includes the position code corresponding to the position identifier and the category code corresponding to the data category. The determination module is configured to determine fault positioning information by using a sequence model according to the cyclic codes of the plurality of pieces of log data, including: grouping the plurality of pieces of log data to obtain a plurality of groups of log data, merging the cyclic codes corresponding to each group of log data to obtain a word embedding matrix corresponding to each group of log data, and determining the fault positioning information by using the sequence model according to the word embedding matrices corresponding to the plurality of groups of log data.

7. A fault detection apparatus, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute a fault detection method according to any one of claims 1 to 5 based on instructions stored in the memory.

8. A computer storage medium having computer program instructions stored thereon, the instructions being executed by a processor to implement a fault detection method according to any one of claims 1 to 5.

Images