With the development of the media industry, maximizing concurrency while ensuring the user’s viewing experience has become an important research topic for each major video website. Currently, one solution is to slice the video, which conserves server bandwidth. Therefore, the design of segment durations has been widely discussed in academia. The research shows that the longer the segment duration is, the better the user experience; however, the increase in video segment duration has a negative impact on the concurrency of the video website. In this paper, a variable length segmentation strategy based on user behaviour is proposed for video segmentation. In the early stage of video browsing, the video loading is ensured, and a short video segmentation strategy is adopted. When the number of users becomes stable, the segment duration is slowly increased to a fixed value to ensure fluency for the users watching the videos. In this paper, the JMeter test tool is used to test the concurrency volume. Through experimental verification, the variable length video segmentation algorithm proposed in this paper is shown to effectively improve the concurrency of the video websites.

In the prediction of time series, the data scale often changes rapidly or a data series shows periodic mutation trend characteristic. A general prediction algorithm cannot obtain the periodic change information of time series in advance, resulting in a limited prediction effect. Considering this factor, the structural improvement of periodic features in a general prediction algorithm can be more suitable for some real scenarios. To solve this problem, this paper proposes a network traffic prediction model based on double-synchronized periodic LSTM (DSP-LSTM), which can comprehensively consider the good fitting ability of linear model to periodic feature data and the nonlinear prediction characteristic of neural network. The experimental results show that the improved DSP-LSTM model can show a better fitting effect when time series data have periodic trend characteristics. Compared with general prediction algorithm, the DSP-LSTM model can effectively reduce the prediction error of periodic time series, improve the prediction accuracy, and adapt well to the changes of different time series patterns.