Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Text picture matching recommendation method based on deep learning

A text picture, deep learning technology, applied in the field of machine learning, can solve the problem of not being able to recommend pictures, and achieve the effect of improving accuracy and high-quality tour experience

Active Publication Date: 2020-06-26
XIAN UNIV OF TECH
View PDF11 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003]Currently, most of the matching algorithms for recommending pictures for texts search for pictures based on keywords entered by users, and cannot recommend pictures in the picture material library for the entire text

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
  • Text picture matching recommendation method based on deep learning
  • Text picture matching recommendation method based on deep learning
  • Text picture matching recommendation method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0046] The text and picture matching recommendation method based on deep learning of the present invention, such as figure 1 , the specific method specifically includes the following steps:

[0047] Step 1, collect the text containing pictures input by the user into the material database; separate the text material and the picture material.

[0048] Step 1.1, the entry person enters the system, and enters text and picture materials.

[0049] Step 1.2, separate text and pictures.

[0050] Step 2: Convolute the gray value of the image through the Laplacian mask, and then calculate the standard deviation to judge the clarity of the image. A certain threshold I is set, and if the calculated picture resolution is less than 1, the picture will be removed, and the subsequent matching steps will not be entered.

[0051] Step 3, using the OCR algori...

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 text and picture recommendation matching algorithm based on deep learning. The adopted recommendation method is based on a continuously rich user operation record database. According to the method, a keyword feature vector is constructed by using picture recognition and a keyword extraction algorithm based on feature vector distribution, and optimal matching recommendation of a picture and a text is realized by combining a user operation record database, a similarity algorithm of the vector and a similarity algorithm of a set. Therefore, after an entering person enters the text and the picture data, the display positions of the homepage picture and the entered picture which are entered this time in the text can be automatically recommended. Therefore, the work oftext understanding, manual picture selection and picture position adjustment of an entering person can be eliminated.

Description

technical field [0001] The invention belongs to the technical field of machine learning, and relates to a text-picture matching recommendation method based on deep learning, in particular to a content-best matching method of text and pictures. Background technique [0002] With the development of computer science and technology, the field of machine learning has also made progress with practical significance and application prospects in the direction of deep learning. This also provides a possible solution for how to perform optimal retrieval and matching in the huge ocean of information. Based on the large-scale popularization of Internet infrastructure, all walks of life have created the need to use machines to automatically match pictures for text. When uploading a text containing pictures, it is often necessary for the inputter to understand the subject of the text and choose a picture that can represent the subject of the entire text. Furthermore, it is necessary for ...

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): G06F16/58G06F16/535
CPCG06F16/5866G06F16/535
Inventor 孟海宁童新宇朱磊白涛王锋冯锴董林靖彭伟
Owner XIAN UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com