A method and apparatus for training a multimedia file search ranking model

A technology for multimedia files and sorting models, which is applied in the computing field and can solve problems such as affecting the sorting accuracy of search models.

Pending Publication Date: 2019-03-22
青岛聚看云科技有限公司
View PDF12 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] In the same way, if the search results containing hot noise data are used as sampl

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 and apparatus for training a multimedia file search ranking model
  • A method and apparatus for training a multimedia file search ranking model
  • A method and apparatus for training a multimedia file search ranking model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0104] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts all belong to the protection scope of the present invention.

[0105] refer to figure 1 Shown, in the embodiment of the present invention, in the embodiment of the present invention, the detailed process of setting up the multimedia file search sorting model is as follows:

[0106] Step 100: Determine the set keywords, and obtain search results corresponding to each keyword, wherein a search result contains at least one multimedia file corresponding to the corresponding keyword.

[0107] Step 110: Calcul...

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 computer technology and discloses a method and apparatus for training a multimedia file search ranking model, which is used for improving the sorting accuracy of search results. The method is, After identifying the keywords and the corresponding search results, calculating a ranking annotation function value of a search result corresponding to each keyword, and generates corresponding sample data, wherein, the sorting label function value is positively correlated with the clicked times of the multimedia file and the association degree of the subject type between the multimedia files, and the sample data whose sorting label function value meets the preset condition is screened out, the preset algorithm is used for model training, and the corresponding multimedia file search sorting model is generated. In this way, the sample data whose keywords are consistent with the search intention of the search results can be screened, the quality of the sample data is improved, the ranking accuracy of the multimedia file search ranking model obtained by training can be effectively improved, and the ranking optimization problem of the search results is solved.

Description

technical field [0001] The invention relates to computing technology, in particular to a training method and device for a multimedia file search and sort model. Background technique [0002] In the prior art, when a user searches for multimedia files (for example, movie search) on a smart TV, the smart TV usually returns search results in a list form according to keywords input by the user. In order to provide users with more accurate search results, it is necessary to conduct search model training based on existing historical search data. However, using existing historical search data for search model training has the following defects: [0003] 1) After the smart TV receives the keyword input by the user, it will present all the multimedia files containing the keyword as search results. [0004] However, from the current feedback results, the search results that only contain keywords often contain high noise data. [0005] For example, assuming that the keyword entered b...

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): G06F16/43G06F16/438
Inventor 赵明徐钊于松袁丽王永选杨梅
Owner 青岛聚看云科技有限公司
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