Search

In order to predict the impact of commodity characteristics on click in commodity description copy, quantitatively analyze users’ consumption behavior characteristics and alleviate the cold start problem, this paper established a click prediction model based on LDA model and text emotion analysis. Based on the LDA topic model, the model classifies and screens the commodity description words, analyzes the emotion of the constituent words, constructs the feature vector to represent the user’s emotional tendency to the characteristics of the commodity, and predicts the click through the lightgbm algorithm. The model can transform unstructured text data into structured data, quantify users’ interest in different characteristics of goods, and use the similar characteristics of different goods to alleviate the cold start problem. The experimental results show that the model can effectively improve the click prediction effect and alleviate the cold start problem. [ABSTRACT FROM AUTHOR]

In order to exploit the performance advantages of many core processors and solve more large-scale problems, this paper studied the parallelization of large integer multiplication on many core processors. Based on the parallel analysis of Written multiplication and Comba multiplication, this paper proposed a variety of solutions to solve the problem of load balancing when Comba multiplication is parallelized. Then according to the structural characteristics of SW26010, this paper selected the improved Comba multiplication based on Written multiplication. And the implementation process used some optimization methods such as vectorization, register communication and so on. The test results show that the improved Comba algorithm has better parallelism and can make good use of the performance advantages of the SW26010 many core processors. [ABSTRACT FROM AUTHOR]