Software defects reflect software quality, and software failures can be predicted through software reliability models. Aiming at the problem that the parameters of software reliability model are difficult to estimate, this paper used the hybrid algorithm for model parameter estimation to software defect prediction. As a typical swarm intelligence algorithm, PSO (Particle Swarm Optimization) has fast convergence but low solution accuracy. SSA (Sparrow Search Algorithm) not only has high search accuracy and fast convergence speed, but also has the advantages of good stability and strong robustness. Based on the characteristic that the fitness function proposed in this paper, this paper hybrid PSO and SSA to accelerate the convergence before the individual update of the SSA. At the same time, this paper also constructed a new fitness function based on the maximum likelihood estimation of the parameters, and used it for parameter initialization. Through the analysis of the experimental results of five sets of actual data sets, the optimization performance of the hybrid algorithm (SSA-PSO) was better than that of a single algorithm with higher convergence speed and more stable, accurate results. Moreover, with the support of the new fitness function, it effectively solved the problems of slow convergence speed and low accuracy of solution. The experimental results showed that the hybrid SSA-PSO could obtain the better solution, convergence speed and stability than single SSA and PSO in software defections estimation and prediction.

Software reliability is estimated and predicted based on software reliability model and software failure data. As a new optimization method, swarm intelligence algorithm has been widely used in solving the parameter optimization of the model. WPA (Wolf Pack Algorithm) and PSO (Particle Swarm Optimization) are two typical swarm intelligence algorithms. WPA has a strong global optimization ability, fast convergence speed and various optimization strategies, but the algorithm is relatively complex. PSO algorithm has a simple structure and fast convergence speed, but it is easy to fall into premature, which leads to low accuracy of solution. Considering the advantages and disadvantages of the two algorithms, a hybrid method of WPA and PSO is proposed, and a fitness function is constructed on maximum likelihood estimation, then the parameters of software reliability model are estimated and predicted based on the hybrid algorithm (WPA-PSO). Five sets of data from industry are used to estimate the parameters of GO model and make predictions. The simulation results show that the hybrid algorithm has higher accuracy of parameter estimation, better optimization performance, better accuracy of prediction and algorithm stability than single algorithm, and show obvious advantages than the single algorithm in the case of limited data.

The rapid growth in the development of Internet-based information systems increases the demand for natural language interfaces that are easy to set up and maintain. Unfortunately, the problem of deep understanding natural language queries is far from being solved. In this paper, an automated question answering system based on domain ontology and question template is proposed, which does not need deep understanding of user's questions. Ontology was employed to model the interesting domain, and properties of concepts are described by a collection of question templates. The system captures a user's intention by matching his questions to predefined templates, and return answers corresponding to template's query focus. The system has been applied to mobile service consulting area, and experimental results show that the system has high practicability as well as maintainability.

Multimodal knowledge graph completion necessitates the integration of information from multiple modalities (such as images and text) into the structural representation of entities to improve link prediction. However, most existing studies have overlooked the interaction between different modalities and the symmetry in the modal fusion process. To address this issue, this paper proposed a Transformer-based knowledge graph link prediction model (MM-Transformer) that fuses multimodal features. Different modal encoders are employed to extract structural, visual, and textual features, and symmetrical hybrid key-value calculations are performed on features from different modalities based on the Transformer architecture. The similarities of textual tags to structural tags and visual tags are calculated and aggregated, respectively, and multimodal entity representations are modeled and optimized to reduce the heterogeneity of the representations. The experimental results show that compared with the current multimodal SOTA method, MKGformer, MM-Transformer improves the Hits@1 and Hits@10 evaluation indicators by 1.17% and 1.39%, respectively, proving that the proposed method can effectively solve the problem of multimodal feature fusion in the knowledge graph link prediction task.

In order to improve software quality and testing efficiency, this paper implements the prediction of software defects based on deep learning. According to the respective advantages and disadvantages of the particle swarm algorithm and the wolf swarm algorithm, the two algorithms are mixed to realize the complementary advantages of the algorithms. At the same time, the hybrid algorithm is used in the search of model hyperparameter optimization, the loss function of the model is used as the fitness function, and the collaborative search ability of the swarm intelligence population is used to find the global optimal solution in multiple local solution spaces. Through the analysis of the experimental results of six data sets, compared with the traditional hyperparameter optimization method and a single swarm intelligence algorithm, the model using the hybrid algorithm has higher and better indicators. And, under the processing of the autoencoder, the performance of the model has been further improved.

With the increasing scale and complexity of system, it is very necessary to analyze the safety of complex system. Fault tree is an effective method to safety analysis. However, traditional fault tree relies on manual construction and analysis. When fault nodes and systems are complex, the efficiency and correctness of manual analysis can hardly be guaranteed. To the varied understanding of analysts, it is difficult to ensure the consistency of failure mode and system architecture due to the different understanding from safety analysts and system designers. The same node needs fault analysis again in different systems, which has poor reusability and low efficiency. AltaRica is a fault-oriented Safety Modeling Language. It takes the guard transformation system(GTS) as its core, describes nodes and faults with a style of reusable object-oriented language, and describes information of interaction between nodes and systems through interface connections between nodes and nested systems. Therefore, this paper proposed an automatic system modeling and fault analysis method and its detailed computer algorithm on single class node, multiple nodes and nodes with subsystems based on AltaRica. Finally we developed a software prototype and carry out the automatic modeling and fault analysis in a detailed example. The results showed that the proposed method, algorithm and software prototype can realize automatic graphical modeling of the system on AltaRica, the automatic fault analysis is correct and efficient, has reusability of modeling and fault analysis, and greatly improve the accuracy, objectivity and efficiency of fault modeling and analysis.