Unlock instant, AI-driven research and patent intelligence for your innovation.

Video sorting method, device, electronic device and storage medium

A sorting method, video technology, applied in the computer field

Active Publication Date: 2020-01-31
BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current method of estimating the click-through rate of users to videos by machine learning has efficiency problems

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Video sorting method, device, electronic device and storage medium
  • Video sorting method, device, electronic device and storage medium
  • Video sorting method, device, electronic device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present application as recited in the appended claims.

[0063] In the existing technology, in the process of recommending and sorting videos using a pre-trained neural network model, it is necessary to stitch together user features and video features, and estimate the click-through rate of each video through the calculation of the neural network model. Rank each video by a metric such as click-through rate. The inventors found that in the ex...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a video sorting method and device, electronic equipment and a storage medium, and the method comprises the steps: responding to a video obtaining request of a user, and obtaining the feature information of the user; Processing the feature information of the user by adopting a pre-trained user-side neural network of a video sorting model to obtain a first top vector; Calculating a first distance between the first top layer vector and each second top layer vector, the second top layer vector being obtained by processing feature information of each video to be recommendedby adopting a video side neural network of a video sequencing model; And sorting the to-be-recommended videos according to the first distances corresponding to the to-be-recommended videos. Accordingto the technical scheme, the second top layer vector can be regularly calculated by adopting the video side neural network in advance, and the first top layer vector and the second top layer vector donot need to be calculated simultaneously in each video sequencing process, so that the technical scheme has very high sequencing efficiency, and video recommendation can be efficiently and accuratelycarried out.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to a video sorting method, device, electronic equipment and storage medium. Background technique [0002] With the advancement of technology and the popularization of the Internet, more and more people transmit information and share life through video, and it is increasingly important to make personalized and effective video recommendations from massive video libraries. In the prior art, a machine learning method can be used to estimate a user's click-through rate on a video, thereby sorting recommended videos according to the click-through rate. [0003] Among them, the machine learning method is a video recommendation technology based on large-scale discrete deep learning. By transforming user features and video features into another space through a neural network, and then learning the parameters in the neural network by minimizing the loss function, it can Estim...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/74
Inventor 蔡锦龙
Owner BEIJING DAJIA INTERNET INFORMATION TECH CO LTD