In recent years, with the development of cloud computing technology, the application field of cloud computing has become more and more extensive, and the problem of cloud platform failure has become more and more serious. In order to ensure the reliability and service quality of the cloud platform, a long short-term memory network (LSTM) based on long short-term memory network (LSTM) in the cloud environment is proposed.
LI Mingrui said that for the field of software development, LSTM is a new technology model. As an improved recurrent neural network, LSTM can not only solve the problem that RNNs cannot handle long-distance dependence, but also solve the common problems of gradient explosion or gradient disappearance in neural networks, which is very effective in processing sequence data.
According to LI Mingrui, the LSTM network is a special RNN model, and its special structural design makes it possible to avoid long-term dependency problems, remembering that information at a very early time is the default behavior of LSTM, without paying a large price for this. In the ordinary RNN model, the chain model of the repeating neural network module repeats only a very simple structure, a single neural network layer (such as tanh layer), which will lead to low information processing power.
LI Mingrui has been deeply engaged in the field of software development for many years and has always been at the forefront of software technology development. He keeps up with the development of the world computer industry and conducts in-depth research on the application of new technologies. The application of the LSTM model to software development is one of LI Mingrui’s important research directions, and his previous project “Application and Research of Building and Developing Cloud Platform Based on Cloud Native Technology: Resource Utilization and Security Development For Software Development” research actively explores cloud native technologies, which has a huge role in promoting the further development of China’s cloud environment. Since then, he has still set his sights on the cloud environment, combined with the subject research and self-developed technical achievements, conducted in-depth research on the application of LSTM network in the cloud environment, and actively explored the construction of LSTM models.
In order to ensure the reliability and service quality of the cloud platform, LI Mingrui proposed a virtual machine failure prediction model based on the combination of Long Short-Term Memory (LSTM) and Support Vector Machines (SVM) in the cloud environment. First, LSTM predicts the future cycle operation data of the virtual machine based on the historical data of the virtual machine, and then classifies the fault of the predicted data through the trained SVM fault determination model, and finally obtains the fault prediction result. LI Mingrui carried out relevant experiments by constructing a real environment, and the experimental results show that the prediction model can effectively predict virtual machine failures.
In addition, LI Mingrui also applied LSTM to code completion. Code completion is one of the important functions of automated software development by providing predictions such as class names and method names to assist developers in writing code. In recent years, intelligent code completion has become one of the hot research directions in the field of software engineering, and the existing work shows that learning code through natural language technology or neural network can improve the accuracy of code completion, but these completion models still have shortcomings, such as weak information representation in code context, incomplete program information extraction and unbalanced code completion tasks.
Therefore, LI Mingrui proposes a new intelligent code completion method, in which the deformed long and short memory network (Mogrifier-LSTM) and attention mechanism are introduced to enhance the information representation of the code context, and at the same time, the hierarchical information of the bidirectional LSTM is used to learn the hierarchical information of the program, and a multi-tasking framework is designed to automatically achieve the balance between code completion tasks. Through experiments on real datasets, the results show that the proposed method outperforms the mainstream code completion method.
LI Mingrui has conducted a number of studies on the LSTM model, and his research results have attracted widespread attention from the computer industry, and highly appreciated and recognized his research. A series of LSTM application methods proposed by LI Mingrui have an important role in promoting the new development of software development, and are important theoretical achievements in the field of software development in China, which have a great influence on the development of the industry.
LI Mingrui said that in the future, he will continue to conduct in-depth research on software development technology, explore at the forefront of software development, and create more advanced achievements in the field of software development, thereby contributing to the innovation of software development technology and the comprehensive development of the computer industry. (Author: PYGMALION)
