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

A method, device, server and computer-readable storage medium for recommending videos

A technology for recommending video and video, applied in image communication, selective content distribution, electrical components, etc., can solve the problem of inaccurate recommendation, achieve the effect of overcoming recommendation hotspots and improving accuracy

Active Publication Date: 2020-11-03
JUHAOKAN TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of this, the present invention provides a method, a device, a video recommendation server, and a computer program-readable storage medium for recommending videos based on a video content similarity algorithm, so as to solve the problem of emphasizing the common preference of different users for videos based on a collaborative filtering algorithm. , and judging by the similarity between video content that different users’ preferences for different videos are related to each other, there is a problem of inaccurate recommendation

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
  • A method, device, server and computer-readable storage medium for recommending videos
  • A method, device, server and computer-readable storage medium for recommending videos
  • A method, device, server and computer-readable storage medium for recommending videos

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] Please refer to figure 2 , is a flowchart of a method for recommending videos based on a video content similarity algorithm in an exemplary embodiment of the present invention, and the method includes the following specific steps:

[0033] Step S210: Based on the associated data recorded in the two-dimensional matrix for representing the display state transition between the first videos, generate an association index of the first video;

[0034] In the process of watching a video, the user will select the video classification of interest on the video classification page according to personal preference, and then select the video of interest in the video classification according to the video description information, and after the video is played, the user loses interest It will stop watching the video and open other videos. During this process, the user operation generates vector related parameters. The vector related parameters are used to indicate that the user operat...

Embodiment 2

[0088] Based on the same idea, Embodiment 2 of the present invention also provides a device for recommending videos based on a video content similarity algorithm. The device can be implemented by software, or by hardware or a combination of software and hardware. Taking software implementation as an example, the device for processing test data of the present invention, as a device in a logical sense, is formed by reading the corresponding computer program instructions in the memory through the CPU equipped with it and then running it.

[0089] Please refer to Figure 7 , is an apparatus 700 for recommending videos in an exemplary embodiment of the present invention. The apparatus is applied to a client device, and the basic operating environment of the apparatus includes CPU, memory and other hardware. From a logical point of view, the apparatus The logical structure of 700 is as follows Figure 7 shown, including:

[0090] A correlation index calculation unit 710, configure...

Embodiment 3

[0098] refer to Figure 8 As shown, the third embodiment of the present invention also provides a video recommendation server 800, the server 800 includes a processor 820 connected to the control bus 810, a memory 830, and a computer program stored in the memory 830, the computer program can run on the processing In the processor, when the processor 820 runs the computer program, the method steps described in the first embodiment are implemented.

[0099] Wherein, when running the aforementioned computer program in processing 820, the processor 820 reads the video and its video information from the recommended video library 840 through the control bus 810, and the communication interface 850 connected to the control bus 810 communicates with the client. , so as to push the second video in the recommended video collection to the aforementioned client.

[0100] Optionally, the present invention provides a computer-readable storage medium, where at least one or a set of instructio...

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 relates to the content recommendation technology field and provides a video recommendation method and an apparatus, a server and a computer readable storage medium. The method comprisesthe following steps of based on a condition that an association vector used for expressing display state transfer among first videos is recorded in a two-dimensional matrix, generating an associationindex of the first videos; according to a content similarity between the first videos and second videos and the association index, acquiring recommendation indexes of the second videos; and based on asequence after the recommendation indexes are ordered, determining a recommended video set pushed to a user from the second videos. Common preferences among the users have a hot spot recommendation problem and the preferences of the different users are determined to be associated through the similarity of video contents so that the recommended videos are not accurate. In the invention, the aboveproblem is overcome and accuracy of recommending the videos to the users is increased.

Description

technical field [0001] The present invention relates to the technical field of content recommendation, in particular to a method, device, video recommendation server and computer storage medium for recommending videos based on a video content similarity algorithm. Background technique [0002] In related technologies, a video recommendation system includes a client and a server communicating with the client. The server receives behavior data generated by the user through an application installed on the client (hereinafter referred to as user behavior data, for example: historical ratings of videos, playback duration, etc.) , number of clicks, etc.), or video content stored on the client (for example: actor, video type, etc.), such as recommending videos on the server to the client based on user preference or similarity of video content. [0003] At present, there are two main algorithms for finding recommended videos on the server: collaborative filtering algorithm based on ...

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): H04N21/25H04N21/262H04N21/442H04N21/458H04N21/466H04N21/482
CPCH04N21/252H04N21/26258H04N21/26291H04N21/44222H04N21/4586H04N21/4662H04N21/4667H04N21/4668H04N21/4826
Inventor 史小龙徐钊王洁
Owner JUHAOKAN TECH CO LTD