A method and device for automatically checking the repair status of program bug problems in a cycle

Abstract

The present invention discloses a method and device for automatically checking the repair status of program bug problems in a loop. The method includes: collecting a bug report data set in ZenTao; wherein the bug report data set includes: bug description, reproduction steps and repair content; cleaning and standardizing the bug report data set to obtain a valid bug report data set; performing text vectorization on the data in the valid bug report data set to obtain a bug text vector data set; training a pre-built recurrent neural network model architecture according to the bug text vector data set to generate a deep network model; inputting the bug report into an automated test script to obtain a test result, and inputting the text vector of the bug report into the deep network model for prediction, and outputting the prediction result; judging the repair result of the bug report according to the test result and the prediction result.

Description

Technical Field

[0001] The present invention relates to the technical field of program testing, and more specifically, to a method and device for automatically and cyclically checking the repair status of program bug problems. Background Art

[0002] When testers raise many questions on ZenTao and all of them are solved by developers, they need to retest them one by one. This retesting process is very tedious, requiring both simulation of bug scenarios and imitation of the data at the time. Moreover, the results after retesting may not be completely accurate. How to check batches of problems has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] In view of the deficiencies in the prior art, the present invention provides a method and device for automatically and cyclically checking the repair status of program bug problems.

[0004] According to one aspect of the present invention, a method for automatically and cyclically checking the repair status of a program bug problem is provided, comprising:

[0005] Collect the bug report dataset in ZenTao; the bug report dataset includes: bug description, reproduction steps and repair content;

[0006] Clean and standardize the bug report dataset to obtain a valid bug report dataset;

[0007] Perform text vectorization on the data in the valid bug report dataset to obtain the bug text vector dataset;

[0008] Train the pre-built recurrent neural network model architecture based on the bug text vector dataset to generate a deep network model;

[0009] Input the bug report into the automated test script to obtain the test results, and input the textual vector of the bug report into the deep network model for prediction, and output the prediction results;

[0010] Determine the repair result of the bug report based on the test results and prediction results.

[0011] Optionally, data in a valid bug report dataset is represented by text vectorization to obtain a bug text vector dataset, including:

[0012] Extract words from the valid bug report dataset and build a vocabulary;

[0013] According to the pre-trained word embedding model, the words in the vocabulary are mapped into vector representations in a low-dimensional continuous space to obtain the Bug text vector dataset.

[0014] Optionally, the training process of the word embedding model is as follows:

[0015] Extract the vocabulary from the preprocessed historical bug report dataset and build a historical vocabulary table;

[0016] Based on the historical vocabulary, the Skip-gram model is used to train the Word2Vec model to generate a word embedding model. The goal of the Skip-gram model is to maximize the conditional probability P(c1,c2,...,cN|w), where N is the window size of the given bug report text; w is the current word, and c1,c2,...,cN are the context words of w;

[0017] The loss function of the Skip-gram model is: L = -log P(c1,c2,...,cN|w).

[0018] Optionally, the recurrent neural network model architecture includes an Embedding layer and one or more RNN layers, wherein a fully connected layer and an activation function are provided on the output of the RNN layer.

[0019] Optionally, based on the test results and the prediction results, determine the repair result of the bug report, including:

[0020] If the test result and the prediction result are the same, the bug report is considered to be fixed;

[0021] When the test result is different from the predicted result, it is determined that the bug report has not been fixed and the bug report is retested.

[0022] According to another aspect of the present invention, there is provided a device for automatically checking the repair status of a program bug problem in a cycle, comprising:

[0023] The collection module is used to collect the bug report dataset in ZenTao. The bug report dataset includes: bug description, reproduction steps and repair content;

[0024] The processing module is used to clean and standardize the bug report data set to obtain a valid bug report data set;

[0025] A vectorization module is used to perform text vectorization on the data in the valid bug report dataset to obtain the bug text vector dataset;

[0026] The training module is used to train the pre-built recurrent neural network model architecture based on the bug text vector dataset to generate a deep network model;

[0027] The prediction module is used to input the bug report into the automated test script to obtain the test results, and input the textual vector of the bug report into the deep network model for prediction, and output the prediction results;

[0028] The judgment module is used to judge the repair result of the bug report based on the test results and prediction results.

[0029] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the storage medium stores a computer program, and the computer program is used to execute the method described in any one of the above aspects of the present invention.

[0030] According to another aspect of the present invention, an electronic device is provided, comprising: a processor; a memory for storing instructions executable by the processor; the processor is configured to read the executable instructions from the memory and execute the instructions to implement the method described in any one of the above aspects of the present invention.

[0031] Therefore, the technical solution of this application using NLP and RNN technology to realize automatic retesting of ZenTao bugs can convert bug reports into vector representations and use RNN models for prediction, thereby improving the efficiency and accuracy of bug retesting and realizing an automated bug retesting process; the above technical solution can help testers to automatically retest bugs, saving time costs and greatly ensuring the accuracy of retesting. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] A more complete understanding of exemplary embodiments of the present invention may be obtained by referring to the following drawings:

[0033] Figure 1 It is a flowchart of a method for automatically checking program bug problems in a cycle provided by an exemplary embodiment of the present invention;

[0034] Figure 2 It is a structural schematic diagram of a device for automatically checking program bugs in a cycle provided by an exemplary embodiment of the present invention;

[0035] Figure 3 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0036] Below, the exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments of the present invention, and it should be understood that the present invention is not limited to the exemplary embodiments described here.

[0037] It should be noted that the relative arrangement of components and steps, the numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.

[0038] Those skilled in the art can understand that the terms "first" and "second" in the embodiments of the present invention are only used to distinguish different steps, devices or modules, etc., and neither represent any specific technical meaning nor indicate the necessary logical order between them.

[0039] It should also be understood that, in the embodiments of the present invention, “plurality” may refer to two or more than two, and “at least one” may refer to one, two or more than two.

[0040] It should also be understood that any component, data or structure mentioned in the embodiments of the present invention can generally be understood as one or more, unless explicitly limited or otherwise indicated in the context.

[0041] In addition, the term "and / or" in the present invention is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in the present invention generally indicates that the associated objects before and after are in an "or" relationship.

[0042] It should also be understood that the description of the various embodiments of the present invention focuses on the differences between the various embodiments, and the same or similar aspects thereof can be referenced to each other, and for the sake of brevity, they will not be described one by one.

[0043] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0044] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.

[0045] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered part of the specification.

[0046] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0047] Embodiments of the present invention can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate with many other general or special computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, small computer systems, large computer systems, and distributed cloud computing technology environments including any of the above systems, etc.

[0048] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system executable instructions (such as program modules) executed by computer systems. Generally, program modules can include routines, programs, object programs, components, logic, data structures, etc., which perform specific tasks or implement specific abstract data types. Computer systems / servers can be implemented in a distributed cloud computing environment, where tasks are performed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0049] Exemplary Methods

[0050] Figure 1 FIG. 1 is a flow chart of a method for automatically checking the status of a program bug problem in a cycle according to an exemplary embodiment of the present invention. This embodiment can be applied to electronic devices, such as Figure 1 As shown, the method 100 for automatically checking the repair status of program bug problems in a cycle includes the following steps:

[0051] Step 101, collect the bug report dataset in ZenTao; wherein the bug report dataset includes: bug description, reproduction steps and repair content;

[0052] Step 102, cleaning and standardizing the bug report data set to obtain a valid bug report data set;

[0053] Step 103, performing text vectorization on the data in the valid bug report dataset to obtain a bug text vector dataset;

[0054] Step 104, training the pre-built recurrent neural network model architecture according to the bug text vector dataset to generate a deep network model;

[0055] Step 105, input the bug report into the automated test script to obtain the test result, and input the textual vector of the bug report into the deep network model for prediction, and output the prediction result;

[0056] Step 106: Determine the repair result of the bug report according to the test result and the prediction result.

[0057] Specifically, this application addresses the technical problems existing in the prior art, uses natural language processing and deep learning technology to convert bug reports into vector representations, designs and trains deep learning models, and realizes automatic retesting of ZenTao bugs.

[0058] Specific implementation steps:

[0059] 1. First, we conduct data preparation and preprocessing. We collect the bug report data set in ZenTao, including bug description, reproduction steps, repair content, etc., and clean and standardize the data to remove noise and redundant information.

[0060] 2. Next, perform text vectorization. Use the word embedding technology Word2Vec to convert the bug report text into a vector representation, mapping the words into a low-dimensional continuous space so that the machine learning model can process it. (Specific algorithm innovation: The innovative algorithm converts the bug report into a vector representation, using natural language processing and deep learning technology. Through the vectorization method of the word embedding model (such as Word2Vec), the words in the bug report are mapped to a vector representation in a low-dimensional continuous space. This vectorization method can effectively capture the semantic and contextual information of the bug report, providing a richer feature representation for subsequent model training and prediction.)

[0061] The specific steps are as follows:

[0062] 1) Based on the preprocessed bug report dataset, build a vocabulary containing all the words that appear in the dataset.

[0063] 2) Using the constructed vocabulary, the Word2Vec model is trained using the Skip-gram model. Given a bug report text with a window size of N, assuming that the current word is w and the context words are c1, c2, ..., cN, the goal of the Skip-gram model is to maximize the conditional probability P(c1, c2, ..., cN|w), that is, the probability of predicting the context word given the current word. The loss function of the Skip-gram model can be expressed as: L = -log P(c1, c2, ..., cN|w)

[0064] 3) On the trained Word2Vec model, you can query the words in the vocabulary to get the corresponding word vector. Each word will be mapped to a vector representation in a low-dimensional continuous space.

[0065] 4) To vectorize the bug report text, a simple method can be used, such as averaging or weighted averaging all word vectors. In this way, each bug report will be represented as a text vector composed of word vectors.

[0066] 3. Then, design a deep learning model. Select a recurrent neural network (RNN) model architecture for automatic bug retesting. The model accepts vectorized bug report text as input and outputs a prediction result, such as whether the bug is reproduced or whether the repair is successful. (Innovative algorithms design and train deep learning models, such as recurrent neural networks (RNN), for automatic ZenTao bug retesting. This model can automatically learn the complex relationship between the bug report vector representation and the retest results, so as to make accurate predictions and judgments.)

[0067] 1) Add an Embedding layer to the RNN model to map the input word index to a low-dimensional continuous vector representation. The parameters of the Embedding layer can be learned and optimized during the model training process.

[0068] 2) Add one or more RNN layers after the Embedding layer so that the model can capture the contextual relationship and semantic information in the sequence data. The RNN layer can be LSTM or GRU. The specific choice can be made according to the characteristics of the dataset and task.

[0069] 3) Add an appropriate fully connected layer and activation function to the output of the RNN layer to generate the final prediction result. The activation function of the output layer can be sigmoid or softmax, which is selected according to the requirements of the specific task.

[0070] 4. Then, perform model training and optimization. Use the labeled bug report dataset to train the model. By minimizing the loss function and using optimization algorithms such as gradient descent, adjust the model's weights and parameters to improve the model's accuracy and generalization ability. (The innovative algorithm uses the labeled bug report dataset to train the deep learning model. By minimizing the loss function and using optimization algorithms such as gradient descent, adjust the model's parameters and weights to improve the model's accuracy and generalization ability. This training and optimization process enables the model to better adapt to the characteristics of the bug report and to accurately retest and predict new bug reports)

[0071] 5. Perform model testing and evaluation. Use an independent test data set to evaluate the trained model and calculate the performance indicators of the model on the test set, such as accuracy, recall, F1 value, etc. Tune and improve the model based on the evaluation results.

[0072] 6. Finally, realize automatic retesting. Combine the automated test script with the trained deep learning model to realize the function of automated retesting. The automated script receives the bug report as input, uses the deep learning model to make predictions, and performs the corresponding retesting operations based on the prediction results. (The algorithm innovation of automatic retesting lies in combining natural language processing and deep learning technology, converting the bug report into a vector representation and using the model prediction to achieve efficient and accurate automated retesting).

[0073] Therefore, the technical solution of this application using NLP and RNN technology to realize automatic retesting of ZenTao bugs can convert bug reports into vector representations and use RNN models for prediction, thereby improving the efficiency and accuracy of bug retesting and realizing an automated bug retesting process; the above technical solution can help testers to automatically retest bugs, saving time costs and greatly ensuring the accuracy of retesting.

[0074] Exemplary Devices

[0075] Figure 2 FIG. 1 is a schematic diagram of a structure of a device for automatically checking program bugs in a cycle according to an exemplary embodiment of the present invention. Figure 2 As shown, the device 200 includes:

[0076] The collection module 210 is used to collect the bug report data set in ZenTao; wherein the bug report data set includes: bug description, reproduction steps and repair content;

[0077] The processing module 220 is used to clean and standardize the bug report data set to obtain a valid bug report data set;

[0078] A vectorization module 230 is used to perform text vectorization on the data in the valid bug report data set to obtain a bug text vector data set;

[0079] A training module 240 is used to train a pre-built recurrent neural network model architecture according to the bug text vector dataset to generate a deep network model;

[0080] The prediction module 250 is used to input the bug report into the automated test script to obtain the test result, and input the textual vector of the bug report into the deep network model for prediction, and output the prediction result;

[0081] The judgment module 260 is used to judge the repair result of the bug report according to the test result and the prediction result.

[0082] Optionally, the vectorization module 230 includes:

[0083] The extraction submodule is used to extract words from the valid bug report dataset and build a vocabulary;

[0084] The vectorization submodule is used to map the words in the vocabulary into vector representations in a low-dimensional continuous space according to the pre-trained word embedding model to obtain the bug text vector dataset.

[0085] Optionally, the training process of the word embedding model is as follows:

[0086] Extract the vocabulary from the preprocessed historical bug report dataset and build a historical vocabulary table;

[0087] Based on the historical vocabulary, the Skip-gram model is used to train the Word2Vec model to generate a word embedding model. The goal of the Skip-gram model is to maximize the conditional probability P(c1,c2,...,cN|w), where N is the window size of the given bug report text; w is the current word, and c1,c2,...,cN are the context words of w;

[0088] The loss function of the Skip-gram model is: L = -log P(c1,c2,...,cN|w).

[0089] Optionally, the recurrent neural network model architecture includes an Embedding layer and one or more RNN layers, wherein a fully connected layer and an activation function are provided on the output of the RNN layer.

[0090] Optionally, the judging module 260 includes:

[0091] The first determination submodule is used to determine that the bug report is fixed when the test result and the prediction result are the same;

[0092] The second determination submodule is used to determine that the bug report has not been repaired and retest the bug report when the test result and the prediction result are different.

[0093] Exemplary Electronic Devices

[0094] Figure 3 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. Figure 3 As shown, the electronic device 30 includes one or more processors 31 and a memory 32 .

[0095] The processor 31 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0096] The memory 32 may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 31 may run the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above and / or other desired functions. In one example, the electronic device may also include: an input device 33 and an output device 34, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0097] In addition, the input device 33 may also include, for example, a keyboard, a mouse, and the like.

[0098] The output device 34 can output various information to the outside. The output device 34 can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto.

[0099] Of course, to simplify, Figure 3 Only some of the components related to the present invention in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application conditions, the electronic device may also include any other appropriate components.

[0100] Exemplary computer program products and computer-readable storage media

[0101] In addition to the above-mentioned methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above-mentioned "Exemplary Method" section of this specification.

[0102] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present invention, 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.

[0103] In addition, an embodiment of the present invention may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enables the processor to execute the steps of the method for information mining of historical change records according to various embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0104] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, system or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an 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 above.

[0105] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details disclosed above are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0106] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0107] The block diagrams of the devices, systems, equipment, and systems involved in the present invention are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, systems, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The word "such as" used here refers to the phrase "such as but not limited to", and can be used interchangeably with it.

[0108] The method and system of the present invention may be implemented in many ways. For example, the method and system of the present invention may be implemented by software, hardware, firmware or any combination of software, hardware, firmware. The above order of steps for the method is only for illustration, and the steps of the method of the present invention are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present invention may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0109] It should also be noted that in the system, device and method of the present invention, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. The above description of the disclosed aspects is provided to enable any technician in the field to make or use the present invention. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined here can be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown here, but in accordance with the widest range consistent with the principles and novel features disclosed here.

[0110] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present invention to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A method for automatically checking the repair status of program bug problems in a cycle, characterized in that: include: Collect bug report datasets in ZenTao; The bug report dataset includes: bug description, reproduction steps and repair content; Cleaning and standardizing the bug report data set to obtain a valid bug report data set; Performing text vectorization on the data in the valid bug report dataset to obtain a bug text vector dataset; Training a pre-built recurrent neural network model architecture according to the Bug text vector dataset to generate a deep network model; Input the bug report into the automated test script to obtain the test result, and input the textual vector of the bug report into the deep network model for prediction, and output the prediction result; The repair result of the Bug report is determined according to the test result and the prediction result.

2. The method according to claim 1, characterized in that: Performing text vectorization on the data in the valid bug report dataset to obtain a bug text vector dataset, including: Extracting words from the valid bug report dataset and constructing a vocabulary; The words in the vocabulary are mapped into vector representations in a low-dimensional continuous space according to a pre-trained word embedding model to obtain the Bug text vector dataset.

3. The method according to claim 2, characterized in that The training process of the word embedding model is as follows: Extract the vocabulary from the preprocessed historical bug report dataset and build a historical vocabulary table; Based on the historical vocabulary, a Word2Vec model is trained using a Skip-gram model to generate the word embedding model, wherein the goal of the Skip-gram model is to maximize the conditional probability P(c1, c2, ..., cN|w), where N is the window size of a given bug report text; w is the current word, and c1, c2, ..., cN are context words of w; The loss function of the Skip-gram model is: L = -log P(c1, c2, ..., cN|w).

4. The method according to claim 1, characterized in that: The recurrent neural network model architecture includes an Embedding layer and one or more RNN layers, wherein a fully connected layer and an activation function are arranged on the output of the RNN layer.

5. The method according to claim 1, characterized in that Determining the repair result of the Bug report according to the test result and the prediction result includes: When the test result is the same as the prediction result, it is determined that the bug report is repaired; When the test result is different from the prediction result, it is determined that the bug report has not been repaired and the bug report is retested.

6. A device for automatically checking the repair status of program bugs in a cycle, characterized in that: include: The collection module is used to collect the bug report data set in ZenTao; The bug report dataset includes: bug description, reproduction steps and repair content; A processing module, used for cleaning and standardizing the bug report data set to obtain a valid bug report data set; A vectorization module, used to perform text vectorization representation on the data in the valid bug report dataset to obtain a bug text vector dataset; A training module, used to train a pre-built recurrent neural network model architecture according to the Bug text vector dataset to generate a deep network model; A prediction module, used to input the bug report into the automated test script to obtain the test result, and input the textual vector of the bug report into the deep network model for prediction, and output the prediction result; A judgment module is used to judge the repair result of the bug report according to the test result and the prediction result.

7. The device according to claim 6, characterized in that Vectorization modules, including: An extraction submodule, used to extract words from the valid bug report dataset and construct a vocabulary; The vectorization submodule is used to map the words in the vocabulary into vector representations in a low-dimensional continuous space according to a pre-trained word embedding model to obtain the Bug text vector dataset.

8. The device according to claim 7, characterized in that The training process of the word embedding model is as follows: Extract the vocabulary from the preprocessed historical bug report dataset and build a historical vocabulary table; Based on the historical vocabulary, a Word2Vec model is trained using a Skip-gram model to generate the word embedding model, wherein the goal of the Skip-gram model is to maximize the conditional probability P(c1, c2, ..., cN|w), where N is the window size of a given bug report text; w is the current word, and c1, c2, ..., cN are context words of w; The loss function of the Skip-gram model is: L = -log P(c1, c2, ..., cN|w).

9. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and the computer program is used to execute the method according to any one of claims 1 to 5.

10. An electronic device, characterized in that: The electronic device comprises: processor; a memory for storing instructions executable by the processor; The processor is used to read the executable instructions from the memory and execute the instructions to implement the method described in any one of claims 1 to 5.

Images