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

Video correlation prediction method and device, equipment and storage medium

A correlation and video technology, applied in the field of video correlation prediction methods, equipment and storage media, and devices, can solve problems such as asymmetric correlation of recommended videos, and achieve the effect of improving accuracy

Active Publication Date: 2019-10-08
PEKING UNIV
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the current recommendation system is based on new videos. When recommending videos that users may be interested in, they often ignore the correlation between videos, treat all related videos equally, and the correlation between recommended videos is not high. symmetry

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 correlation prediction method and device, equipment and storage medium
  • Video correlation prediction method and device, equipment and storage medium
  • Video correlation prediction method and device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The specific embodiments of the present application will be described in detail below in conjunction with the accompanying drawings, but it should be understood that the protection scope of the present application is not limited by the specific embodiments.

[0034] Unless expressly stated otherwise, throughout the specification and claims, the term "comprise" or variations thereof such as "includes" or "includes" and the like will be understood to include the stated elements or constituents, and not Other elements or other components are not excluded.

[0035] figure 1 A schematic flow chart of the video correlation prediction method provided in Embodiment 1 of the present application, as shown in figure 1 As shown, the method includes:

[0036] S101. Obtain the source video sample and its related video list and unrelated video list; the related video list includes a plurality of related video samples sorted by relevance from large to small, and the unrelated video l...

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 correlation prediction method and device, equipment and a storage medium. The video correlation prediction method constructs and trains a semi-twin neural network modelto learn the relationship between related or unrelated videos, inputs a target source video and at least one to-be-predicted video into the semi-twin neural network model, and after the semi-twin neural network model analysis, outputs a correlation result between the to-be-predicted video and the target source video. Therefore, the video lacking the user behavior information can predict the videolist related to the video, and the correlation of the related videos is given, and the correlation among the related videos is symmetrical, and the accuracy of video recommendation is effectively improved.

Description

technical field [0001] The present application relates to the field of video data processing, in particular to a video correlation prediction method, device, equipment and storage medium. Background technique [0002] With the development of information technology and Internet technology, audio and video-based media data has slowly developed from scarcity to information overload. In the massive amount of data, how to find the information that the user is interested in, and how to mine and find more interesting and related information based on the information that the user finds is becoming more and more difficult. [0003] The recommendation system, as an information filtering platform, screens and filters massive data through specific algorithms to predict users' "preferences" for information. Generally speaking, as an effective solution to information overload, search engines require users to provide clear requirements in order to achieve accurate content recommendations,...

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
IPC IPC(8): G06F16/735G06N3/04G06N3/08H04N21/466
CPCG06F16/735G06N3/084H04N21/4668G06N3/045
Inventor 田永鸿李宗贤李晟薛岚天
Owner PEKING UNIV