Recommendation method and system of video text labels

A technology of text labeling and recommendation methods, applied in the field of video text label recommendation, can solve problems such as laborious and laborious, uneven label quality, difficulty in video search and recommendation, and achieve the effect of ensuring accuracy

Inactive Publication Date: 2013-06-19
SHENGLE INFORMATION TECH SHANGHAI
View PDF0 Cites 76 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional video sites may prompt users to input by themselves, or manually mark by editors. However, these input and editing methods are too time-consuming and labor-intensive, because firstly, most users are unwilling to take the initiative to enter tags; secondly, because the quality of tags manually entered by users It is uneven and there is a lo

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
  • Recommendation method and system of video text labels
  • Recommendation method and system of video text labels
  • Recommendation method and system of video text labels

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Such as figure 1 As shown, the present invention provides a kind of recommendation method of video text label, comprising:

[0052] Step S1, periodically obtain domain words from the Internet and add them to a domain dictionary;

[0053]Step S2, segmenting the text information of each video according to the domain words in the domain dictionary to generate several candidate keywords;

[0054] Step S3, carry out attribute category label to each candidate keyword, specifically, can subdivide various candidate keyword attribute categories, such as the part-of-speech category of the candidate keyword, the position of occurrence (whether it appears in the title, and whether it is in the user tag Occurrence), the frequency of occurrence of candidate keywords, whether the candidate keywords are named entities, whether they are field words, etc., the part-of-speech categories may include person names, place names, organization names, content words, idioms, adjectives, abbrevia...

Embodiment 2

[0097] Such as Figure 4 As shown, the present invention also provides a recommendation system for video text tags, including a domain dictionary module 1, a candidate keyword module 2, an attribute tag module 3, a weight acquisition module 4, a text tag module 5 and a correlation module 6.

[0098] The domain dictionary module 1 is used to regularly obtain domain words from the Internet to add to a domain dictionary.

[0099] Candidate keywords module 2 is used to carry out word segmentation to the text information of each video according to the field words in the field dictionary to generate several candidate keywords, specifically by word segmentation and Generate candidate keywords to ensure that the source of candidate keywords is sufficient. Even if any item of text information in the title, description or user tags is missing, there will still be more accurate recommendation results for video text tags.

[0100] The attribute tagging module 3 is used to tag each candid...

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 a recommendation method and system of video text labels. The method comprises: obtaining field words from the web to replenish a field dictionary at regular intervals; according to the field words in the field dictionary, carrying out segmentation on text information of each video to generate a plurality of candidate keywords; labeling an attribute type of each candidate keyword; according to the attribute type of each candidate keyword, obtaining a comprehensive weight number of the candidate keyword; sorting weight numbers of all the candidate keywords in descending order, and choosing several candidate keywords with the comprehensive weight numbers in the top as the video text labels. The recommendation method and system of the video text labels can automatically generate a video text label list, accurately summarize content of video and contribute to application such as video retrieval and excavation of relative videos.

Description

technical field [0001] The invention relates to a method and system for recommending video text tags. Background technique [0002] As the Internet enters the era of Web 2.0, content generated by users, such as text, pictures, videos, music, etc., gradually occupy the Internet and become the main body of content on the Internet, and the content generated by users tends to be diversified in form and quantity also showed explosive growth. [0003] In addition, due to the popularity of photography and camera equipment, users can record videos more conveniently, so some video sites are rising rapidly. How to describe, organize and search massive videos is a very important requirement. Text tags are the most precise and general descriptions of content posted by users, and each tag consists of a word or phrase. Traditional video sites may prompt users to input by themselves, or manually mark by editors. However, these input and editing methods are too time-consuming and labor-in...

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): G06F17/30G06F17/27
Inventor 宋海涛陈运文刘作涛纪达麒
Owner SHENGLE INFORMATION TECH SHANGHAI
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