Automatic Film Label Acquisition Method Based on Improved Neural Networks Optimized by Mutation Ant Colony Algorithm.

Junjie Liu

doi:10.1155/2021/7158051

Abstract

Nowadays, with the constant change of public aesthetic standards, a large number of new types and themes of film programs have emerged. For this reason, this paper proposes an improved neural network optimized by mutation ant colony algorithm for automatic acquisition of film labels, which not only overcomes the disadvantages of traditional neural network, such as difficulty in determining weights, slow convergence speed, and easiness to fall into local minimum, but also makes up for the shortcomings faced by using ant colony algorithm alone through the gradient information of quantum genetic algorithm neural network. The results show that the user similarity judgment is added in the process of calculating the user rating deviation between movies, and the neighbor chooses to add the movie tag weight and rating similarity as the basis for the neighbor selection of the target movie in the process of predicting the target movie rating. Experiments show the effectiveness of the algorithm.

Highlights

Nowadays, the research field of knowledge acquisition covers the fields of medicine, product information, and expert system construction
Common methods of constructing personalized interest patterns of users often focus on using historical access information of users and combine knowledge base and semantic analysis technology to realize personalized information push [8]
Short-term interest change may be related to the temporary needs of users, while long-term interest change is related to the natural evolution of interest

Summary

Introduction

The research field of knowledge acquisition covers the fields of medicine, product information, and expert system construction. Common methods of constructing personalized interest patterns of users often focus on using historical access information of users and combine knowledge base and semantic analysis technology to realize personalized information push [8]. In [9], the user’s historical access information is processed by matrix decomposition method, and the usefulness calculation method of the recommendation object to the user is used to realize the complete personalized recommendation service. Among the existing time analysis methods, literature [10] points out that distinguishing short-term interest from long-term interest is a common research idea. After analyzing the user’s Weibo data in [11], it is found that the user’s personalized interest features change very frequently, and the latest interest features are most in line with the current information needs of users. According to the sequence of paths, additional pheromones are added. rough the training model, the user tags are trained, and the user tag word vectors are obtained to verify the effectiveness of film tag weight extraction

Related Work

Research Method

Analysis and Discussion