Evaluation of multimedia learning resource classification retrieval based on decision tree hashing algorithm

Current classification and retrieval methods are affected by the amount of data in the classification of multimedia learning resources, and there are problems such as low classification accuracy, low retrieval rate, and long retrieval time. To solve this problem, a new multimedia learning method is proposed. Combine decision tree and hash algorithm to design resource classification and retrieval method. The decision tree algorithm is used for the collection and classification of multimedia learning resources, the hash algorithm is introduced to solve and preprocess the resources, and the Lyapunov theorem is used to obtain features. By using two different deep convolutional networks as non-linear hash functions, joint training enables the corresponding hash codes of the network to interpret the similar relations contained in the semantic information. Use annotated propagation algorithm to realize multimedia classification and retrieval of learning resources. The experimental results show that the improved method can effectively improve the retrieval accuracy and efficiency of multimedia learning resources, and has certain practicability. Copyright © 2021 The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.