Video intelligent recommendation method and device based on random matrix coding and simplified convolutional network, and storage medium

Abstract

The invention relates to a video recommendation method, in particular to an intelligent video recommendation method and device based on random matrix coding and a simplified convolutional network and a storage medium, and belongs to the technical field of network information processing. The method specifically comprises the following steps: firstly, preprocessing a data set; secondly, generating a random matrix code for the user characteristics through a random vector; transmitting the data coding matrix to a first full connection layer to obtain a user feature vector; transmitting the video features to a simplified convolutional network to generate a simplified text convolutional network code, and generating a video feature matrix; transmitting the video feature matrix to a second full connection layer to obtain a movie feature vector; calculating a prediction score through the user feature vector and the film feature vector, and carrying out fitting training on the prediction score and a real score; and finally, performing video recommendation on the user through the prediction score. The technical problems that in the prior art, a video recommendation method is large in calculation amount and tedious in information coding are solved.

Description

technical field [0001] The present application relates to a video recommendation method, in particular to a video intelligent recommendation method, device and storage medium based on random matrix coding and simplified convolutional network, and belongs to the technical field of network information processing. Background technique [0002] Facing the mass and structural complexity of the current Internet information, the value of recommendation algorithms is increasingly evident. At present, deep learning technology is developing rapidly and has achieved remarkable results in many fields, but there are few studies applying it to video recommendation algorithms. [0003] Deep learning is to learn the internal laws and representation levels of sample data. The information obtained during the learning process is of great help to the interpretation of data such as text, images and sounds. Its ultimate goal is to enable machines to have the ability to analyze and learn like hum...

AI Technical Summary

Problems solved by technology

However, doing so will bring a lot of additional calculation burden, making the system design more complex, and in practical application scenarios, in many cases, such as user id, which is of little significance to the calculation results but has a high dimension, it is not necessary to perform additional calculations. coding to increase the difficulty and complexity of system design

Images