Research on Digital Live Broadcast Recommendation System Based on Artificial Intelligence

In view of the limitations of the traditional Depth-first search algorithm in research on digital live broadcast recommendation system, a research scheme of research on the live broadcast recommendation system based on Artificial intelligence was proposed. Firstly, the influencing factors is accurately located through computer science dispensing theories, and the indicators is reasonably divided to reduce interference, and the Artificial intelligence is used to construct a research scheme for research on the live broadcast recommendation system. Experimental results show that under certain evaluation criteria, the proposed scheme is superior to the traditional Depth-first search algorithm in terms of research accuracy and processing time of influencing factors of research on the live broadcast recommendation system, and has obvious advantages. The research of research on the live broadcast recommendation system plays an extremely important role in digital live, which can accurately predict and optimize the growth characteristics and product generation of digital live. However, the traditional Depth-first search algorithm has some limitations in solving the problem of recommended system simulation, especially when dealing with complex problems. In this paper, this paper proposes a research scheme of research on the live broadcast recommendation system based on Artificial intelligence to better solve this problem. The scheme accurately locates the influencing factors through computer science dispensing theories, so as to determine the division of indicators, and uses the Artificial intelligence to construct the scheme. Experimental results show that under certain evaluation criteria, the accuracy and speed of the scheme is significantly improved for different problems, and it has better performance. Therefore, the simulation scheme based on Artificial intelligence in research on digital live broadcast recommendation system can better solve the limitations of traditional Depth-first search algorithm and improve the simulation accuracy and efficiency.