CN117093477A - Software quality assessment method and device, computer equipment and storage medium - Google Patents
Software quality assessment method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117093477A CN117093477A CN202311014997.1A CN202311014997A CN117093477A CN 117093477 A CN117093477 A CN 117093477A CN 202311014997 A CN202311014997 A CN 202311014997A CN 117093477 A CN117093477 A CN 117093477A
- Authority
- CN
- China
- Prior art keywords
- software
- evaluation model
- training
- ant colony
- initial evaluation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012549 training Methods 0.000 claims abstract description 102
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 94
- 238000013210 evaluation model Methods 0.000 claims abstract description 93
- 238000000034 method Methods 0.000 claims abstract description 57
- 238000012706 support-vector machine Methods 0.000 claims abstract description 44
- 238000013522 software testing Methods 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims abstract description 23
- 230000006870 function Effects 0.000 claims description 54
- 239000013598 vector Substances 0.000 claims description 24
- 238000012795 verification Methods 0.000 claims description 21
- 239000003016 pheromone Substances 0.000 claims description 14
- 238000013507 mapping Methods 0.000 claims description 9
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000002372 labelling Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 abstract description 17
- 238000013473 artificial intelligence Methods 0.000 abstract description 14
- 230000000694 effects Effects 0.000 abstract description 7
- 238000012360 testing method Methods 0.000 description 15
- 238000005457 optimization Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 7
- 230000007547 defect Effects 0.000 description 7
- 239000002699 waste material Substances 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000003068 static effect Effects 0.000 description 4
- 241000257303 Hymenoptera Species 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000012384 transportation and delivery Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 238000012407 engineering method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000019637 foraging behavior Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 238000013442 quality metrics Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/36—Preventing errors by testing or debugging software
- G06F11/3668—Software testing
- G06F11/3672—Test management
- G06F11/3692—Test management for test results analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biomedical Technology (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Stored Programmes (AREA)
Abstract
The application discloses a software quality assessment method, a software quality assessment device, computer equipment and a storage medium, and belongs to the technical field of artificial intelligence and the technical field of finance and technology. According to the method, a training data set is constructed based on historical software test data, a preset initial evaluation model is trained by the training data set, parameter tuning is conducted on the initial evaluation model based on a preset ant colony algorithm, and an optimal parameter combination is obtained, wherein the initial evaluation model is a support vector machine, an initial evaluation model corresponding to the optimal parameter combination is obtained, a software quality evaluation model is obtained, software data to be tested is input into the software quality evaluation model, and a corresponding software test result is obtained. The application also relates to the technical field of blockchain, and software data to be tested can be stored on a blockchain node. According to the method, the software quality evaluation model is built by combining with parameter tuning of the ant colony algorithm, guidance and decision basis are provided for a software testing process, and accuracy and effect of software quality evaluation are improved.
Description
Technical Field
The application belongs to the technical field of artificial intelligence and the field of financial science and technology, and particularly relates to a software quality assessment method, a device, computer equipment and a storage medium.
Background
Along with the development of computer technology, software plays an irreplaceable role in different industries, and meanwhile, daily life of people is more and more free from convenience brought by the software, and meanwhile, the reliability and the safety of a software system are also particularly important, so that the software system is widely focused by social groups. The problem of unreliability of software is mainly caused by defects of the software, and the defects are unavoidable in the development process, but often cause immeasurable loss due to system breakdown caused by the defects, so that the defects of the software are predicted, and the improvement of the quality and the safety of the software is an important problem to be solved in the current society.
At present, a main way of guaranteeing the quality of software is manual software testing, but as the scale of a software system is larger and the complexity of software functional modules is higher and higher, for example, an insurance management system, which is a software system for supporting daily operation and management of an insurance company, a plurality of functional modules and business processes are covered. The manual software test requires a great deal of labor cost, is influenced by subjective factors of testers, cannot consider all modules in the software engineering, and has no way to comprehensively test the software scale.
Disclosure of Invention
The embodiment of the application aims to provide a software quality assessment method, a device, computer equipment and a storage medium, which are used for solving the technical problems of incomplete test and manpower waste existing in the existing manual software test mode.
In order to solve the above technical problems, the embodiment of the present application provides a software quality evaluation method, which adopts the following technical scheme:
a software quality assessment method, comprising:
acquiring historical software test data, and marking the historical software test data;
constructing a training data set based on the marked historical software test data;
training a preset initial evaluation model by using the training data set, and performing parameter tuning on the initial evaluation model based on a preset ant colony algorithm to obtain an optimal parameter combination, wherein the initial evaluation model is a support vector machine;
acquiring an initial evaluation model corresponding to the optimal parameter combination to obtain a software quality evaluation model;
receiving a software testing instruction, obtaining software data to be tested, and inputting the software data to be tested into the software quality evaluation model to obtain a software testing result corresponding to the software to be tested.
Further, before training the preset initial evaluation model by using the training data set and performing parameter tuning on the initial evaluation model based on a preset ant colony algorithm to obtain an optimal parameter combination, the method further comprises:
initializing parameters of the ant colony algorithm, wherein the parameters of the ant colony algorithm comprise an initial value of pheromone, an ant colony scale and a maximum iteration number;
and carrying out iterative updating on the information volatilization factors of the ant colony algorithm until the iterative times reach the maximum iterative times.
Further, the information volatilization factor of the ant colony algorithm is iteratively updated by the following formula:
ρ(i)＝0.98ρ(i-1)
wherein ρ is an information volatilization factor, and i is the current iteration number.
Further, training a preset initial evaluation model by using the training data set, and performing parameter tuning on the initial evaluation model based on a preset ant colony algorithm to obtain an optimal parameter combination, which specifically includes:
initializing parameters of the initial evaluation model, wherein the parameters of the initial evaluation model comprise penalty parameters and kernel function parameters of a support vector machine;
performing feature vector conversion on sample data in the training data set to obtain sample feature vectors;
Mapping the sample feature vector to a high-dimensional space, and searching the optimal parameter combination in the high-dimensional space by using the ant colony algorithm after iterative updating.
Further, the optimal parameter combination includes the penalty parameter and the kernel parameter, the mapping the sample feature vector to a high-dimensional space, and searching the optimal parameter combination in the high-dimensional space by using the ant colony algorithm after iterative updating, specifically including:
constructing an objective function based on the penalty parameter and the kernel function parameter;
searching the high-dimensional space by using the ant colony algorithm after iterative updating to obtain a target parameter combination;
calculating the fitness value of the objective function based on the objective parameter combination;
judging whether the fitness value meets an iteration termination condition, and determining a target parameter combination corresponding to the fitness value meeting the iteration termination condition as the optimal parameter combination when the fitness value meets the iteration termination condition.
Further, the objective function expression is as follows:
F＝C*Loss[y,f(x)]+α*R(γ)+β*Kernel
wherein F is an objective function, C is a penalty parameter, loss [ y, F (x) ] is a training error, loss is a Loss function between a label y and a model prediction output F (x), alpha is a regularization parameter, R (gamma) is a regularization term, beta is a Kernel function parameter, and Kernel is a Kernel function.
Further, constructing a training data set based on the noted historical software test data, specifically including:
carrying out data set division on the marked historical software test data to obtain a training data set, wherein the training data set comprises a training sample set and a verification sample set;
training a preset initial evaluation model by using the training data set, and performing parameter tuning on the initial evaluation model based on a preset ant colony algorithm to obtain an optimal parameter combination, wherein the method specifically comprises the following steps:
training a preset initial evaluation model by using the training data set;
in the initial evaluation model training process, parameter tuning is carried out on the initial evaluation model based on the ant colony algorithm to obtain an optimal parameter combination;
after the initial evaluation model corresponding to the optimal parameter combination is obtained, the method further comprises the following steps:
and verifying the trained software quality assessment model by using the verification sample set, and outputting the software quality assessment model passing the verification.
In order to solve the technical problems, the embodiment of the application also provides a software quality evaluation device, which adopts the following technical scheme:
A software quality assessment device, comprising:
the data labeling module is used for acquiring historical software test data and labeling the historical software test data;
the data set construction module is used for constructing a training data set based on the marked historical software test data;
the parameter tuning module is used for training a preset initial evaluation model by utilizing the training data set, and performing parameter tuning on the initial evaluation model based on a preset ant colony algorithm to obtain an optimal parameter combination, wherein the initial evaluation model is a support vector machine;
the model acquisition module is used for acquiring an initial evaluation model corresponding to the optimal parameter combination to obtain a software quality evaluation model;
the software testing module is used for receiving a software testing instruction, obtaining software data to be tested, inputting the software data to be tested into the software quality evaluation model, and obtaining a software testing result corresponding to the software to be tested.
In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical schemes:
a computer device comprising a memory having stored therein computer readable instructions which when executed by a processor implement the steps of the software quality assessment method of any of the preceding claims.
In order to solve the above technical problems, an embodiment of the present application further provides a computer readable storage medium, which adopts the following technical schemes:
a computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the software quality assessment method as claimed in any one of the preceding claims.
Compared with the prior art, the embodiment of the application has the following main beneficial effects:
the application discloses a software quality assessment method, a software quality assessment device, computer equipment and a storage medium, and belongs to the technical field of artificial intelligence and the technical field of finance and technology. According to the method, historical software test data are obtained, the historical software test data are marked, a training data set is constructed based on the marked historical software test data, a preset initial evaluation model is trained by the training data set, parameter tuning is conducted on the initial evaluation model based on a preset ant colony algorithm, and an optimal parameter combination is obtained, wherein the initial evaluation model is a support vector machine, an initial evaluation model corresponding to the optimal parameter combination is obtained, a software quality evaluation model is obtained, a software test instruction is received, software data to be tested is obtained, the software data to be tested is input into the software quality evaluation model, and a software test result corresponding to the software to be tested is obtained. According to the application, the parameter tuning of the support vector machine is carried out by combining with the ant colony algorithm, so that a software quality assessment model is constructed, the model can be used for predicting the quality level of the software to be tested, providing guidance and decision basis for the software testing process, improving the accuracy and effect of software quality assessment by utilizing the historical data and the characteristics of the ant colony algorithm, and solving the problems of incomplete test and manpower waste existing in the existing manual software testing mode.
Drawings
In order to more clearly illustrate the solution of the present application, a brief description will be given below of the drawings required for the description of the embodiments of the present application, it being apparent that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without the exercise of inventive effort for a person of ordinary skill in the art.
FIG. 1 illustrates an exemplary system architecture diagram in which the present application may be applied;
FIG. 2 illustrates a flow chart of one embodiment of a software quality assessment method in accordance with the present application;
FIG. 3 shows a flow chart of another embodiment of a software quality assessment method according to the present application;
FIG. 4 shows a schematic structural diagram of one embodiment of a software quality assessment device according to the present application;
fig. 5 shows a schematic structural diagram of an embodiment of a computer device according to the application.
Detailed Description
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the description of the drawings above are intended to cover a non-exclusive inclusion. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
In order to make the person skilled in the art better understand the solution of the present application, the technical solution of the embodiment of the present application will be clearly and completely described below with reference to the accompanying drawings.
As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (MovingPicture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.
The server 105 may be a server that provides various services, such as a background server that provides support for pages displayed on the terminal devices 101, 102, 103, and may be a stand-alone server, or may be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.
It should be noted that, the software quality evaluation method provided by the embodiment of the present application is generally executed by a server, and accordingly, the software quality evaluation device is generally disposed in the server.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow chart of one embodiment of a software quality assessment method according to the present application is shown. The embodiment of the application can acquire and process the related data based on the artificial intelligence technology. Among these, artificial intelligence (Artificial Intelligence, AI) is the theory, method, technique and application system that uses a digital computer or a digital computer-controlled machine to simulate, extend and extend human intelligence, sense the environment, acquire knowledge and use knowledge to obtain optimal results.
Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a robot technology, a biological recognition technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
At present, a main way of guaranteeing the quality of software is manual software testing, but as the scale of a software system is larger and the complexity of software functional modules is higher and higher, for example, an insurance management system, which is a software system for supporting daily operation and management of an insurance company, a plurality of functional modules and business processes are covered. The manual software test requires a great deal of labor cost, is influenced by subjective factors of testers, cannot consider all modules in the software engineering, and has no way to comprehensively test the software scale.
In order to solve the technical problems, the application discloses a software quality assessment method, a device, computer equipment and a storage medium, belongs to the technical field of artificial intelligence and the field of financial science and technology, and constructs a software quality assessment model by combining with an ant colony algorithm to support parameter tuning of a vector machine, wherein the model can be used for predicting the quality level of software to be tested, providing guidance and decision basis for a software testing process, improving the accuracy and effect of software quality assessment by utilizing the historical data and the characteristics of the ant colony algorithm, and solving the problems of incomplete test and manpower waste in the existing insurance management system by using the artificial software testing mode.
The software quality evaluation method comprises the following steps:
s201, acquiring historical software test data and marking the historical software test data.
In this embodiment, historical software test data is obtained, where the historical software test data includes software samples that have been tested and corresponding test results. These historical software test data are then annotated, i.e., each sample is assigned the correct label or category to indicate its quality level, e.g., good or defective.
It should be noted that the software quality assessment model is obtained based on training of a support vector machine (SupportVector Machine, abbreviated as SVM), the SVM is a supervised learning algorithm commonly used for pattern recognition and machine learning, and the SVM can be used for classification and regression problems and is widely applied to the fields of text classification, image recognition, bioinformatics and the like. The core idea of the SVM is to find an optimal hyperplane, called the separation hyperplane (separating hyperplane), that separates the different classes of samples and maximizes the separation of the two classes.
Software quality assessment is a process of predicting or assessing the quality level of a software product by feature extraction and analysis, and SVM algorithms may be applied to classify problems in software quality assessment, for example, to determine whether the software has a high quality, a medium quality, or a low quality. When using the SVM algorithm for software quality assessment, special attention needs to be paid to feature selection, and selecting appropriate software features is important for accurate quality assessment, and the following common software features can be used for software quality assessment:
code complexity: such as the number of code lines, loop complexity, number of function call layers, etc., higher complexity codes are often prone to errors and difficult to maintain.
Code scale: such as the number of classes and methods, the annotation scale, etc., larger-scale code may require more testing and debugging effort.
Code repetition rate: repeated codes often imply inefficiency and maintenance difficulties.
Static analysis index: such as static analysis results of the code, including code quality metrics, code specification compliance, etc., which can be obtained by a static code analysis tool.
Defect rate: past defect rate data may be used to predict future quality levels.
Test coverage: such as test coverage of code lines, functions or classes, codes with higher coverage are generally of better quality.
Change history: such as the frequency of code changes, differences between versions, etc., frequently changing codes can present potential problems.
Programming specification compliance degree: such as whether the code specification, naming convention, etc., is met, codes with a high degree of compliance are generally easy to read and maintain.
Design mode use: for example, the application of design patterns, good design pattern usage typically reflects higher code quality.
Code dependency relationship: such as dependencies between codes, degree of coupling between modules, low degree of coupling and modular codes are generally of better quality.
In the above embodiments, it is necessary to select appropriate software features according to circumstances, and to collect and analyze data according to availability and feasibility. Meanwhile, the selection of the features can be optimized and improved by a feature engineering method, such as feature selection, dimension reduction and other operations, so as to improve the performance and generalization capability of the model.
Before training an SVM model, each sample in a training data set is ensured to have a correct label, a model which can accurately predict unknown sample labels can be trained through the training data set carrying the labels, and meanwhile, the labeling quality and the labeling accuracy of the training data set can also influence the performance and the generalization capability of the model.
S202, constructing a training data set based on the marked historical software test data.
In this embodiment, after the annotated historical software test data is obtained, it can be used to construct a training dataset. The training dataset is made up of input features, which may be various software quality-related features, such as code complexity, test coverage, defect rate, etc., and corresponding labels, which represent the quality levels of the samples.
Further, constructing a training data set based on the annotated historical software test data, specifically comprising:
and carrying out data set division on the marked historical software test data to obtain a training data set, wherein the training data set comprises a training sample set and a verification sample set.
In this embodiment, the labeled historical software test data is subjected to data set division, where the data division ratio is 7:3, wherein 70% is used as a training sample set, 30% is used as a verification sample set, the training sample set is used for model training, and the verification sample set is used for model verification.
Further, before training the preset initial evaluation model by using the training data set and performing parameter tuning on the initial evaluation model based on the preset ant colony algorithm to obtain an optimal parameter combination, the method further comprises:
initializing parameters of an ant colony algorithm, wherein the parameters of the ant colony algorithm comprise an initial value of a pheromone, an ant colony scale and a maximum iteration number;
and carrying out iterative updating on the information volatilization factors of the ant colony algorithm until the iterative times reach the maximum iterative times.
Further, the information volatilization factor of the ant colony algorithm is iteratively updated by the following formula:
ρ(i)＝0.98ρ(i-1)
Wherein ρ is an information volatilization factor, and i is the current iteration number.
The ant colony algorithm (Ant Colony Algorithm, abbreviated as ACO) is a heuristic optimization algorithm designed for simulating the foraging behavior of ants, the ACO algorithm simulates the behavior rule and information communication mode of ants in the process of searching food, and the optimization process is realized through accumulation and volatilization of pheromones. The ACO algorithm has wide application in the fields of combination optimization, path planning, graph theory and the like. The basic idea of the ACO algorithm is that ants find the optimal solution by releasing and sensing pheromones in the environment, communicating and cooperating with each other through the pheromones.
In the iterative optimization process of the ant colony algorithm, the ant colony algorithm is required to be preferentially selected by virtue of the pheromone, and in order to ensure the timeliness of the pheromone, a volatilization factor is required to be set. In the conventional standard ant colony algorithm, the information volatilization factor ρ is an initial set value, but this will make the optimization error larger and seriously affect the convergence speed, so in this embodiment, the information volatilization factor ρ is improved, and the dynamic adaptive pheromone volatilization factor ρ (i) is used to replace the conventional information volatilization factor ρ, and by the improvement, the volatilization factor is continuously reduced with the increase of the iteration number, and the importance of the pheromone is relatively increased.
In the above embodiment, the application provides a dynamic self-adaptive volatilization factor updating method, which reduces the volatilization factors and increases the importance of pheromones by carrying out iterative updating on the information volatilization factors of the ACO algorithm, thereby solving the iterative optimization problem of the ACO optimization algorithm caused by the limitation of the change of the pheromones.
S203, training a preset initial evaluation model by using a training data set, and performing parameter tuning on the initial evaluation model based on a preset ant colony algorithm to obtain an optimal parameter combination, wherein the initial evaluation model is a support vector machine.
In this embodiment, the initial evaluation model is implemented by using a Support Vector Machine (SVM), and a classification model is constructed by training a data set and learning a relationship between sample features and labels by using the SVM, and parameters of the initial evaluation model are optimized by using a preset ant colony algorithm to find an optimal parameter combination, so as to improve performance and generalization capability of the model.
The working principle of the SVM can be summarized simply as the following steps:
data preparation: the training data is represented in the form of feature vectors, each sample having a set of features as input.
Feature conversion: if the data is not linearly separable, the data may be mapped to the high-dimensional space using kernel functions that are linearly separable in the high-dimensional space, common kernel functions include a linear kernel, a polynomial kernel, and a Radial Basis Function (RBF) kernel.
Searching an optimal hyperplane: in the space after feature transformation, the goal of the SVM is to find an optimal hyperplane so that the distance of the samples of different classes from the hyperplane is maximized, and these closest sample points to the hyperplane are called support vectors.
Classification prediction: and for the new unknown sample, determining the category of the new unknown sample by calculating the position relation between the new unknown sample and the optimal hyperplane.
In the embodiment, the strategy of the ACO algorithm is improved, the dynamic self-adaptive volatile factor is updated, the improved ACO algorithm is used for carrying out SVM model parameter combination selection, the optimal model parameter pair is selected for training the SVM, and the classification accuracy is improved.
Training a preset initial evaluation model by using a training data set, and performing parameter tuning on the initial evaluation model based on a preset ant colony algorithm to obtain an optimal parameter combination, wherein the method specifically comprises the following steps of:
training a preset initial evaluation model by using a training data set;
in the initial evaluation model training process, parameter tuning is performed on the initial evaluation model based on an ant colony algorithm, and an optimal parameter combination is obtained.
In this embodiment, a training data set is used to train a preset initial evaluation model, and in the training process of the initial evaluation model, parameter tuning is performed on the initial evaluation model based on an ant colony algorithm to obtain an optimal parameter combination.
Further, training a preset initial evaluation model by using a training data set, and performing parameter tuning on the initial evaluation model based on a preset ant colony algorithm to obtain an optimal parameter combination, wherein the method specifically comprises the following steps:
initializing parameters of an initial evaluation model, wherein the parameters of the initial evaluation model comprise penalty parameters and kernel function parameters of a support vector machine;
performing feature vector conversion on sample data in the training data set to obtain sample feature vectors;
and mapping the sample feature vector to a high-dimensional space, and searching for an optimal parameter combination in the high-dimensional space by utilizing an ant colony algorithm after iterative updating.
In this embodiment, the parameters of the initial evaluation model are initialized, where the parameters of the initial evaluation model include a penalty parameter C and a kernel function parameter β of the support vector machine, and any one of a kernel function linear kernel, a polynomial kernel, or a radial basis function kernel. After the model parameters are initialized, carrying out feature vector conversion on sample data in the training data set to obtain sample feature vectors, mapping the sample feature vectors to a high-dimensional space, and continuously searching parameter combinations in the high-dimensional space by utilizing an ant colony algorithm until the optimal parameter combinations are obtained.
Further, the optimal parameter combination comprises a penalty parameter and a kernel function parameter, the sample feature vector is mapped to a high-dimensional space, and the optimal parameter combination is searched in the high-dimensional space by utilizing an ant colony algorithm after iteration updating, and the method specifically comprises the following steps:
constructing an objective function based on the penalty parameter and the kernel function parameter;
searching a high-dimensional space by using the ant colony algorithm after iterative updating to obtain a target parameter combination;
calculating the fitness value of the objective function based on the objective parameter combination;
judging whether the fitness value meets the iteration termination condition, and determining a target parameter combination corresponding to the fitness value meeting the iteration termination condition as an optimal parameter combination when the fitness value meets the iteration termination condition.
In this embodiment, an objective function F is constructed based on a penalty parameter C and a kernel function parameter β, an ant colony algorithm after iteration update is used to search a high-dimensional space to obtain a plurality of objective parameter combinations, then an fitness value of the objective function is calculated based on the objective parameter combinations, whether the fitness value meets an iteration termination condition is judged, and when the fitness value meets the iteration termination condition, an objective parameter combination corresponding to the fitness value meeting the iteration termination condition is determined to be an optimal parameter combination. The iteration termination condition is a preset fitness value threshold, and when the fitness value is greater than or equal to the fitness value threshold, it can be determined that the parameter combination corresponding to the fitness value meets the iteration termination condition, that is, the target parameter combination corresponding to the fitness value is the optimal parameter combination.
In the above embodiment, the present application considers that the ACO algorithm and the SVM parameter tuning are combined, so as to search the parameter space by utilizing the advantage of the ACO algorithm that the ACO algorithm explores in the search space, and update the pheromone according to the performance index of each parameter combination, such as the accuracy or the error of cross-validation, and gradually converge to the optimal parameter combination through the iterative process of the ant colony algorithm.
Referring to fig. 3, the present application proposes a model based on an improved ACO-SVM, firstly initializing SVM parameters and ACO parameters, then iteratively updating information volatilization factors of an ant colony algorithm, searching a parameter space by using the improved ACO algorithm, judging whether an iteration exit condition is satisfied or not based on a fitness value of an objective function, acquiring an optimal parameter combination when iteration is stopped, and training a software quality evaluation model.
In the above embodiment, the prediction accuracy of the SVM for the classification data is used as the objective function, the parameters to be optimized are the penalty factor C and the core parameter β of the SVM, the objective function is marked as F, and after the optimal SVM parameter is obtained through ACO optimization, the model training is performed by using the historical software test data, so as to obtain the software quality evaluation model.
Further, the objective function expression is as follows:
F＝C*Loss[y,f(x)]+α*R(γ)+β*Kernel
wherein F is an objective function, C is a penalty parameter, loss [ y, F (x) ] is a training error, loss is a Loss function between a label y and a model prediction output F (x), alpha is a regularization parameter, R (gamma) is a regularization term, beta is a Kernel function parameter, and Kernel is a Kernel function.
S204, obtaining an initial evaluation model corresponding to the optimal parameter combination, and obtaining a software quality evaluation model.
In this embodiment, after parameter tuning, an optimal parameter combination is obtained, and the optimal parameter combination is combined with an initial evaluation model to form an optimized software quality evaluation model, where the model can be used to predict the quality level of an unknown software sample, and give a corresponding software test result or quality evaluation according to the input software characteristics.
After obtaining the initial evaluation model corresponding to the optimal parameter combination and obtaining the software quality evaluation model, the method further comprises the following steps:
and verifying the trained software quality assessment model by using the verification sample set, and outputting the software quality assessment model passing the verification.
In this embodiment, after the training of the software quality assessment model is completed, it is also necessary to verify the trained software quality assessment model using a verification sample set, and output the software quality assessment model that passes the verification. The performance of the software quality evaluation model is evaluated through model verification, the indexes of model evaluation comprise evaluation indexes such as prediction accuracy, recall rate and F1 value, the prediction capability of the software quality evaluation model constructed through model verification evaluation on unknown data is ensured, the generalization capability and practicability of the model are ensured, and the model with the best performance can be selected through full verification and optimization so as to perform actual software quality evaluation and test work.
S205, receiving a software testing instruction, obtaining software data to be tested, inputting the software data to be tested into a software quality evaluation model, and obtaining a software testing result corresponding to the software to be tested.
In this embodiment, in practical application, when there is a software test requirement, a software test instruction is received, and software data to be tested is obtained, and the software data to be tested is input into a software quality evaluation model, and a quality evaluation result of the software to be tested or a software test result can be obtained through the prediction of the software quality evaluation model.
In the embodiment, the application discloses a software quality assessment method, and belongs to the technical field of artificial intelligence and the field of financial science and technology. According to the method, historical software test data are obtained, the historical software test data are marked, a training data set is constructed based on the marked historical software test data, a preset initial evaluation model is trained by the training data set, parameter tuning is conducted on the initial evaluation model based on a preset ant colony algorithm, and an optimal parameter combination is obtained, wherein the initial evaluation model is a support vector machine, an initial evaluation model corresponding to the optimal parameter combination is obtained, a software quality evaluation model is obtained, a software test instruction is received, software data to be tested is obtained, the software data to be tested is input into the software quality evaluation model, and a software test result corresponding to the software to be tested is obtained. According to the application, the parameter tuning of the support vector machine is carried out by combining with the ant colony algorithm, so that a software quality assessment model is constructed, the model can be used for predicting the quality level of the software to be tested, providing guidance and decision basis for the software testing process, improving the accuracy and effect of software quality assessment by utilizing the historical data and the characteristics of the ant colony algorithm, and solving the problems of incomplete test and manpower waste existing in the existing manual software testing mode.
In this embodiment, the electronic device (e.g., the server shown in fig. 1) on which the software quality evaluation method operates may acquire data or receive instructions through a wired connection or a wireless connection. It should be noted that the wireless connection may include, but is not limited to, 3G/4G connections, wiFi connections, bluetooth connections, wiMAX connections, zigbee connections, UWB (ultra wideband) connections, and other now known or later developed wireless connection means.
It should be emphasized that, to further ensure the privacy and security of the software data to be tested, the software data to be tested may also be stored in a node of a blockchain.
The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.
Those skilled in the art will appreciate that implementing all or part of the processes of the methods of the embodiments described above may be accomplished by way of computer readable instructions, stored on a computer readable storage medium, which when executed may comprise processes of embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
With further reference to fig. 4, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a software quality assessment apparatus, which corresponds to the method embodiment shown in fig. 2, and which is particularly applicable to various electronic devices.
As shown in fig. 4, the software quality evaluation device 400 according to the present embodiment includes:
the data labeling module 401 is configured to obtain historical software test data, and label the historical software test data;
a data set construction module 402, configured to construct a training data set based on the annotated historical software test data;
the parameter tuning module 403 is configured to train a preset initial evaluation model by using a training data set, and perform parameter tuning on the initial evaluation model based on a preset ant colony algorithm to obtain an optimal parameter combination, where the initial evaluation model is a support vector machine;
the model obtaining module 404 is configured to obtain an initial evaluation model corresponding to the optimal parameter combination, so as to obtain a software quality evaluation model;
the software testing module 405 is configured to receive a software testing instruction, obtain software data to be tested, input the software data to be tested into the software quality evaluation model, and obtain a software testing result corresponding to the software to be tested.
Further, the software quality evaluation apparatus 400 further includes:
the ant colony algorithm parameter initializing module is used for initializing parameters of an ant colony algorithm, wherein the parameters of the ant colony algorithm comprise an initial value of pheromone, an ant colony scale and a maximum iteration number;
and the ant colony algorithm iteration module is used for carrying out iteration update on the information volatilization factors of the ant colony algorithm until the iteration times reach the maximum iteration times.
Further, the information volatilization factor of the ant colony algorithm is iteratively updated by the following formula:
ρ(i)＝0.98ρ(i-1)
wherein ρ is an information volatilization factor, and i is the current iteration number.
Further, the parameter tuning module 403 specifically includes:
the support vector machine parameter initializing unit is used for initializing parameters of an initial evaluation model, wherein the parameters of the initial evaluation model comprise penalty parameters and kernel function parameters of the support vector machine;
the feature vector conversion unit is used for carrying out feature vector conversion on sample data in the training data set to obtain sample feature vectors;
and the feature vector mapping unit is used for mapping the sample feature vector to a high-dimensional space and searching the optimal parameter combination in the high-dimensional space by utilizing the ant colony algorithm after iterative updating.
Further, the optimal parameter combination includes a penalty parameter and a kernel function parameter, and the feature vector mapping unit specifically includes:
an objective function construction subunit, configured to construct an objective function based on the penalty parameter and the kernel function parameter;
the parameter combination searching subunit is used for searching a high-dimensional space by using the ant colony algorithm after iterative updating to obtain a target parameter combination;
an fitness value calculation subunit, configured to calculate a fitness value of the objective function based on the objective parameter combination;
and the iteration termination judging subunit is used for judging whether the fitness value meets the iteration termination condition, and determining the target parameter combination corresponding to the fitness value meeting the iteration termination condition as the optimal parameter combination when the fitness value meets the iteration termination condition.
Further, the objective function expression is as follows:
F＝C*Loss[y,f(x)]+α*R(γ)+β*Kernel
wherein F is an objective function, C is a penalty parameter, loss [ y, F (x) ] is a training error, loss is a Loss function between a label y and a model prediction output F (x), alpha is a regularization parameter, R (gamma) is a regularization term, beta is a Kernel function parameter, and Kernel is a Kernel function.
Further, the data set construction module 402 specifically includes:
the data set dividing unit is used for dividing the marked historical software test data into data sets to obtain training data sets, wherein the training data sets comprise training sample sets and verification sample sets;
The parameter tuning module 403 further includes:
the model training unit is used for training a preset initial evaluation model by utilizing the training data set;
the parameter tuning unit is used for performing parameter tuning on the initial evaluation model based on the ant colony algorithm in the initial evaluation model training process to obtain an optimal parameter combination;
the software quality assessment device 400 further includes:
and the model verification module is used for verifying the trained software quality assessment model by using the verification sample set and outputting the software quality assessment model passing the verification.
In the embodiment, the application discloses a software quality assessment device, and belongs to the technical field of artificial intelligence and the field of financial science and technology. According to the method, historical software test data are obtained, the historical software test data are marked, a training data set is constructed based on the marked historical software test data, a preset initial evaluation model is trained by the training data set, parameter tuning is conducted on the initial evaluation model based on a preset ant colony algorithm, and an optimal parameter combination is obtained, wherein the initial evaluation model is a support vector machine, an initial evaluation model corresponding to the optimal parameter combination is obtained, a software quality evaluation model is obtained, a software test instruction is received, software data to be tested is obtained, the software data to be tested is input into the software quality evaluation model, and a software test result corresponding to the software to be tested is obtained. According to the application, the parameter tuning of the support vector machine is carried out by combining with the ant colony algorithm, so that a software quality assessment model is constructed, the model can be used for predicting the quality level of the software to be tested, providing guidance and decision basis for the software testing process, improving the accuracy and effect of software quality assessment by utilizing the historical data and the characteristics of the ant colony algorithm, and solving the problems of incomplete test and manpower waste existing in the existing manual software testing mode.
In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 5, fig. 5 is a basic structural block diagram of a computer device according to the present embodiment.
The computer device 5 comprises a memory 51, a processor 52, a network interface 53 which are communicatively connected to each other via a system bus. It should be noted that only the computer device 5 with components 51-53 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculations and/or information processing in accordance with predetermined or stored instructions, the hardware of which includes, but is not limited to, microprocessors, application specific integrated circuits (Application SpecificIntegrated Circuit, ASICs), programmable gate arrays (fields-Programmable Gate Array, FPGAs), digital processors (Digital Signal Processor, DSPs), embedded devices, etc.
The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.
The memory 51 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card memory (e.g., SD or DX memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 51 may be an internal storage unit of the computer device 5, such as a hard disk or a memory of the computer device 5. In other embodiments, the memory 51 may also be an external storage device of the computer device 5, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 5. Of course, the memory 51 may also comprise both an internal memory unit of the computer device 5 and an external memory device. In this embodiment, the memory 51 is typically used to store an operating system and various application software installed on the computer device 5, such as computer readable instructions of a software quality evaluation method, and the like. Further, the memory 51 may be used to temporarily store various types of data that have been output or are to be output.
The processor 52 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 52 is typically used to control the overall operation of the computer device 5. In this embodiment, the processor 52 is configured to execute computer readable instructions stored in the memory 51 or process data, such as computer readable instructions for executing the software quality assessment method.
The network interface 53 may comprise a wireless network interface or a wired network interface, which network interface 53 is typically used to establish communication connections between the computer device 5 and other electronic devices.
In the embodiment, the application discloses computer equipment, and belongs to the technical field of artificial intelligence and the technical field of finance. According to the method, historical software test data are obtained, the historical software test data are marked, a training data set is constructed based on the marked historical software test data, a preset initial evaluation model is trained by the training data set, parameter tuning is conducted on the initial evaluation model based on a preset ant colony algorithm, and an optimal parameter combination is obtained, wherein the initial evaluation model is a support vector machine, an initial evaluation model corresponding to the optimal parameter combination is obtained, a software quality evaluation model is obtained, a software test instruction is received, software data to be tested is obtained, the software data to be tested is input into the software quality evaluation model, and a software test result corresponding to the software to be tested is obtained. According to the application, the parameter tuning of the support vector machine is carried out by combining with the ant colony algorithm, so that a software quality assessment model is constructed, the model can be used for predicting the quality level of the software to be tested, providing guidance and decision basis for the software testing process, improving the accuracy and effect of software quality assessment by utilizing the historical data and the characteristics of the ant colony algorithm, and solving the problems of incomplete test and manpower waste existing in the existing manual software testing mode.
The present application also provides another embodiment, namely, a computer-readable storage medium storing computer-readable instructions executable by at least one processor to cause the at least one processor to perform the steps of the software quality assessment method as described above.
In this embodiment, the application discloses a computer readable storage medium, which belongs to the technical field of artificial intelligence and the technical field of finance. According to the method, historical software test data are obtained, the historical software test data are marked, a training data set is constructed based on the marked historical software test data, a preset initial evaluation model is trained by the training data set, parameter tuning is conducted on the initial evaluation model based on a preset ant colony algorithm, and an optimal parameter combination is obtained, wherein the initial evaluation model is a support vector machine, an initial evaluation model corresponding to the optimal parameter combination is obtained, a software quality evaluation model is obtained, a software test instruction is received, software data to be tested is obtained, the software data to be tested is input into the software quality evaluation model, and a software test result corresponding to the software to be tested is obtained. According to the application, the parameter tuning of the support vector machine is carried out by combining with the ant colony algorithm, so that a software quality assessment model is constructed, the model can be used for predicting the quality level of the software to be tested, providing guidance and decision basis for the software testing process, improving the accuracy and effect of software quality assessment by utilizing the historical data and the characteristics of the ant colony algorithm, and solving the problems of incomplete test and manpower waste existing in the existing manual software testing mode.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method according to the embodiments of the present application.
The application is operational with numerous general purpose or special purpose computer system environments or configurations. For example: personal computers, server computers, hand-held or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, distributed computing environments that include any of the above systems or devices, and the like. The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
It is apparent that the above-described embodiments are only some embodiments of the present application, but not all embodiments, and the preferred embodiments of the present application are shown in the drawings, which do not limit the scope of the patent claims. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a thorough and complete understanding of the present disclosure. Although the application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing description, or equivalents may be substituted for elements thereof. All equivalent structures made by the content of the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also within the scope of the application.
Claims (10)
1. A method for evaluating software quality, comprising:
acquiring historical software test data, and marking the historical software test data;
constructing a training data set based on the marked historical software test data;
training a preset initial evaluation model by using the training data set, and performing parameter tuning on the initial evaluation model based on a preset ant colony algorithm to obtain an optimal parameter combination, wherein the initial evaluation model is a support vector machine;
Acquiring an initial evaluation model corresponding to the optimal parameter combination to obtain a software quality evaluation model;
receiving a software testing instruction, obtaining software data to be tested, and inputting the software data to be tested into the software quality evaluation model to obtain a software testing result corresponding to the software to be tested.
2. The software quality assessment method according to claim 1, wherein before said training the preset initial assessment model using the training data set and performing parameter tuning on the initial assessment model based on a preset ant colony algorithm, obtaining an optimal parameter combination, further comprising:
initializing parameters of the ant colony algorithm, wherein the parameters of the ant colony algorithm comprise an initial value of pheromone, an ant colony scale and a maximum iteration number;
and carrying out iterative updating on the information volatilization factors of the ant colony algorithm until the iterative times reach the maximum iterative times.
3. The software quality evaluation method according to claim 2, wherein the information volatilization factor of the ant colony algorithm is iteratively updated by the following formula:
ρ(i)＝0.98ρ(i-1)
wherein ρ is an information volatilization factor, and i is the current iteration number.
4. The software quality assessment method according to claim 2, wherein the training of the preset initial assessment model by using the training data set, and the parameter tuning of the initial assessment model based on the preset ant colony algorithm, to obtain the optimal parameter combination, specifically comprises:
initializing parameters of the initial evaluation model, wherein the parameters of the initial evaluation model comprise penalty parameters and kernel function parameters of a support vector machine;
performing feature vector conversion on sample data in the training data set to obtain sample feature vectors;
mapping the sample feature vector to a high-dimensional space, and searching the optimal parameter combination in the high-dimensional space by using the ant colony algorithm after iterative updating.
5. The software quality assessment method according to claim 4, wherein said optimal parameter combination includes said penalty parameter and said kernel parameter, said mapping said sample feature vector to a high-dimensional space, and searching said optimal parameter combination in said high-dimensional space using said ant colony algorithm after iterative updating, specifically comprising:
constructing an objective function based on the penalty parameter and the kernel function parameter;
Searching the high-dimensional space by using the ant colony algorithm after iterative updating to obtain a target parameter combination;
calculating the fitness value of the objective function based on the objective parameter combination;
judging whether the fitness value meets an iteration termination condition, and determining a target parameter combination corresponding to the fitness value meeting the iteration termination condition as the optimal parameter combination when the fitness value meets the iteration termination condition.
6. The software quality assessment method according to claim 5, wherein said objective function expression is as follows:
F＝C*Loss[y,f(x)]+α*R(γ)+β*Kernel
wherein F is an objective function, C is a penalty parameter, loss [ y, F (x) ] is a training error, loss is a Loss function between a label y and a model prediction output F (x), alpha is a regularization parameter, R (gamma) is a regularization term, beta is a Kernel function parameter, and Kernel is a Kernel function.
7. The software quality assessment method according to any one of claims 1 to 6, wherein constructing a training data set based on said annotated historical software test data, in particular comprises:
carrying out data set division on the marked historical software test data to obtain a training data set, wherein the training data set comprises a training sample set and a verification sample set;
Training a preset initial evaluation model by using the training data set, and performing parameter tuning on the initial evaluation model based on a preset ant colony algorithm to obtain an optimal parameter combination, wherein the method specifically comprises the following steps:
training a preset initial evaluation model by using the training data set;
in the initial evaluation model training process, parameter tuning is carried out on the initial evaluation model based on the ant colony algorithm to obtain an optimal parameter combination;
after the initial evaluation model corresponding to the optimal parameter combination is obtained, the method further comprises the following steps:
and verifying the trained software quality assessment model by using the verification sample set, and outputting the software quality assessment model passing the verification.
8. A software quality assessment apparatus, comprising:
the data labeling module is used for acquiring historical software test data and labeling the historical software test data;
the data set construction module is used for constructing a training data set based on the marked historical software test data;
the parameter tuning module is used for training a preset initial evaluation model by utilizing the training data set, and performing parameter tuning on the initial evaluation model based on a preset ant colony algorithm to obtain an optimal parameter combination, wherein the initial evaluation model is a support vector machine;
The model acquisition module is used for acquiring an initial evaluation model corresponding to the optimal parameter combination to obtain a software quality evaluation model;
the software testing module is used for receiving a software testing instruction, obtaining software data to be tested, inputting the software data to be tested into the software quality evaluation model, and obtaining a software testing result corresponding to the software to be tested.
9. A computer device comprising a memory and a processor, the memory having stored therein computer readable instructions which when executed by the processor implement the steps of the software quality assessment method of any of claims 1 to 7.
10. A computer readable storage medium having stored thereon computer readable instructions which when executed by a processor implement the steps of the software quality assessment method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311014997.1A CN117093477A (en) | 2023-08-11 | 2023-08-11 | Software quality assessment method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311014997.1A CN117093477A (en) | 2023-08-11 | 2023-08-11 | Software quality assessment method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117093477A true CN117093477A (en) | 2023-11-21 |
Family
ID=88782137
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311014997.1A Pending CN117093477A (en) | 2023-08-11 | 2023-08-11 | Software quality assessment method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117093477A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117827621A (en) * | 2024-03-06 | 2024-04-05 | 泰安北航科技园信息科技有限公司 | Automatic test platform system and method for embedded software |
| CN118014451A (en) * | 2024-04-10 | 2024-05-10 | 建信金融科技有限责任公司 | Data processing method, device, equipment and storage medium of software project |
-
2023
- 2023-08-11 CN CN202311014997.1A patent/CN117093477A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117827621A (en) * | 2024-03-06 | 2024-04-05 | 泰安北航科技园信息科技有限公司 | Automatic test platform system and method for embedded software |
| CN117827621B (en) * | 2024-03-06 | 2024-05-10 | 泰安北航科技园信息科技有限公司 | Automatic test platform system and method for embedded software |
| CN118014451A (en) * | 2024-04-10 | 2024-05-10 | 建信金融科技有限责任公司 | Data processing method, device, equipment and storage medium of software project |
| CN118014451B (en) * | 2024-04-10 | 2024-09-06 | 建信金融科技有限责任公司 | Data processing method, device, equipment and storage medium of software project |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106095942B (en) | Strong variable extracting method and device | |
| CN117093477A (en) | Software quality assessment method and device, computer equipment and storage medium | |
| CN112256886B (en) | Probability calculation method and device in atlas, computer equipment and storage medium | |
| CN112686301A (en) | Data annotation method based on cross validation and related equipment | |
| CN113986674B (en) | Time sequence data abnormality detection method and device and electronic equipment | |
| CN117217812A (en) | User behavior prediction method and device, computer equipment and storage medium | |
| CN111178687A (en) | Financial risk classification method and device and electronic equipment | |
| CN113807728A (en) | Performance assessment method, device, equipment and storage medium based on neural network | |
| CN111191677B (en) | User characteristic data generation method and device and electronic equipment | |
| CN116883181B (en) | Financial service pushing method based on user portrait, storage medium and server | |
| CN117234844A (en) | Cloud server abnormality management method and device, computer equipment and storage medium | |
| CN116703466A (en) | System access quantity prediction method based on improved wolf algorithm and related equipment thereof | |
| CN116843483A (en) | Vehicle insurance claim settlement method, device, computer equipment and storage medium | |
| CN114549053B (en) | Data analysis method, device, computer equipment and storage medium | |
| CN116796729A (en) | Text recommendation method, device, equipment and storage medium based on feature enhancement | |
| KR102284440B1 (en) | Method to broker deep learning model transactions perfomed by deep learning model transaction brokerage servers | |
| CN116662160B (en) | Software defect prediction method and processing device based on cost sensitive width learning | |
| CN117312991B (en) | Method for constructing classification recognition system and related equipment thereof | |
| US20240211750A1 (en) | Developer activity modeler engine for a platform signal modeler | |
| CN117407750A (en) | Metadata-based data quality monitoring method, device, equipment and storage medium | |
| CN118212072A (en) | Data evaluation method, device, equipment and storage medium based on artificial intelligence | |
| CN117056782A (en) | Data anomaly identification method, device, equipment and storage medium thereof | |
| CN117236707A (en) | Asset optimization configuration method and device, computer equipment and storage medium | |
| CN118041977A (en) | Method and device for processing micro-service component, computer equipment and storage medium | |
| CN117609013A (en) | Software defect prediction method and device based on fuzzy weighted width learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |