On-line video recommending method recommending system, and processing system

A video recommendation and video technology, applied in the Internet field, can solve problems such as heavy workload, high cost, and lack of tag content, and achieve the effect of saving costs and improving accuracy

Inactive Publication Date: 2013-04-03
BEIJING QIHOO TECH CO LTD +1
View PDF6 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] Because the traditional online video label generation method needs to label the content of each online video, the workload is huge and the cost is high; and some online videos may lack label content, or the label strength of some online videos may be inaccurate

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
  • On-line video recommending method recommending system, and processing system
  • On-line video recommending method recommending system, and processing system
  • On-line video recommending method recommending system, and processing system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] A method for generating an online video tag disclosed in an embodiment of the present invention is introduced in detail.

[0043] refer to figure 2 , shows a flowchart of a method for generating an online video tag in an embodiment of the present invention.

[0044] Step 100, calculating the original tag matrix of each online video.

[0045] The above original label matrix of each online video includes a matrix of current label content and current label strength of each online video.

[0046] The above-mentioned online videos may refer to several online videos with similar tag content. The tag content of each online video is selected from the tag library that has been created. The tag content of each online video may be completely or partially the same.

[0047] For example, in the tag library of online videos, 5 tags are selected for 3 online videos V1, V2, and V3 as the tag content of 3 online videos, which are tags t1, t2, t3, t4, and t5, respectively. The specif...

Embodiment 2

[0080]A method for generating an online video tag disclosed in an embodiment of the present invention is introduced in detail.

[0081] refer to image 3 , shows a flowchart of a method for generating an online video tag in an embodiment of the present invention.

[0082] Step 200, calculating the original label matrix of each online video.

[0083] The above original label matrix of each online video includes a matrix of current label content and current label strength of each online video.

[0084] The original tag matrix of each online video can be expressed as VIDEO_TAG, each row of values ​​in the original tag matrix corresponds to an online video, the original tag matrix includes several rows of values, indicating that there are several online videos; the column of each column of values ​​in the original tag matrix Named the label content of each online video; each column value is the label strength of the label content. For example, the matrix D is obtained through t...

Embodiment 3

[0174] A method for generating an online video tag disclosed in an embodiment of the present invention is introduced in detail.

[0175] refer to Figure 4 , shows a schematic diagram of a method for generating an online video tag in an embodiment of the present invention.

[0176] Step 300, building an online video tag library based on online video domain knowledge.

[0177] The online video tag library includes tag content. Step 302: Count the historical records of online video watched by the terminal within a period to form an online video matrix of the terminal.

[0178] Step 304: Transpose the terminal online video matrix to form an online video terminal matrix.

[0179] Step 306, calculating online video similarity and generating an online video similarity matrix.

[0180] Step 308, calculate the original label matrix and combine it with the similarity matrix to calculate the transmitted label matrix.

[0181] Step 310: Generate a new label matrix based on the origi...

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 embodiment of the invention discloses an on-line video recommending method, an on-line video recommending system and a processing system, and aims to solve the problems that the tag content of each on-line video needs to be marked, and the tag intensity is inaccurate. The on-line video recommending system comprises a on-line video recommending module, an original tag matrix calculating module, a similarity matrix calculating module, a candidate tag matrix calculating module and a cyclic operation module, wherein the similarity matrix of each on-line video comprises a matrix of current tag content similarity degree of each on-line video; and the cyclic operation module is suitable for judging whether the candidate tag matrix calculating module of each on-line video meets preset conditions based on the original tag matrix and the candidate tag matrix of the on-line video, and when the preset conditions are met, the candidate tag matrix of the on-line video is the candidate matrix of the on-line video. The embodiment of the invention saves the cost of marking tag content and improves the accuracy of tag content and tag intensity.

Description

technical field [0001] The embodiments of the present invention relate to the Internet field, and in particular to an online video recommendation method, recommendation system and processing system. Background technique [0002] The generation of online video tags is an effective method to characterize online videos and is widely used in online video search and online video recommendation systems. An online video tag consists of tag content and tag strength. The tag content describes the features of the online video, and the tag strength indicates the importance of the feature. By checking the tag content, the terminal can distinguish the characteristics of the online video and confirm whether it may meet its viewing needs. By comparing the tag strengths of all the tags of an online video, the main features and secondary features of the online video can be known. If the main features are consistent with the viewing needs, it can be determined that the online video best mee...

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 Applications(China)
IPC IPC(8): G06F17/30
Inventor 杨浩吴凯
Owner BEIJING QIHOO TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap