Recommendation information acquisition method, device, system, server and storage medium

A technology of recommending information and obtaining method, applied in the field of recommending information obtaining method, system, server and storage medium, and device, can solve the problems of inconsistent label content, inability to accurately search user dress images, reducing the accuracy and efficiency of recommended information, etc. , to achieve the effect of improving the accuracy

Active Publication Date: 2018-11-16
深圳市雅阅科技有限公司
View PDF5 Cites 28 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, since image tags are often manually defined, it often leads to inconsistencies in the tag content set by different users for the same image, reducing the accuracy and efficiency of the recommended information obtained. For example, an image of a girl wearing a dress on a shopping website, The defined tags can include casual wear, girls, skirts, etc. When a user enters a dress on a shopping website, it is often impossible to accurately search for the dress image that the user wants to view

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 information acquisition method, device, system, server and storage medium
  • Recommendation information acquisition method, device, system, server and storage medium
  • Recommendation information acquisition method, device, system, server and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] In order to actively push recommended information to users without requiring users to input search keywords, the inventors of the present invention propose to use content-based image search to obtain recommended information pushed to users. Refer to figure 1As shown in the flow chart, after obtaining the search image that the user cares about (such as the image selected by the user), it is usually to extract the global image of the search image as a whole to obtain the label mapped to by the global image feature, such as figure 1 Tags such as casual clothes and girls in the image, and then use the tag to filter in the image database, that is, filter the candidate image with the tag, and push it to the user client as the user's recommendation information.

[0055] However, the explicit description of image tags has great limitations and instability, because not all search image content can be described by tags, and for abstract search images, it is impossible to define ta...

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 provides a recommendation information acquisition method, device, system, server and storage medium. A business server generates a search request and sends the same toa search server for a search image associated with the provided business information; the search server extracts global image characteristic and multiple region object characteristics of the search image so as to form the search image characteristic, the similarity search is performed on a candidate image so as to obtain a corresponding candidate recommendation set and feed back to the business server to store. Visibly, since the image characteristic is not affected by an artificial factor, the technical problem that a search result is inaccurate since the similarity search is performed basedon an image label is solved; and the evidence for performing the similarity further comprises the region object characteristics of the search image, and the accuracy of the searched recommendation information is improved.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a recommended information acquisition method, device, system, server and storage medium. Background technique [0002] Nowadays, in the process of users browsing webpages through the Internet, such as browsing shopping webpages, news webpages, funny picture webpages and other application scenarios, the image search method is usually used, that is, the similarity search is performed on the user's current browsing image in the database, and the The obtained search result is fed back to the user as recommendation information, so that the user can understand the information related to the currently browsed image. [0003] At present, when image search is performed, it is often realized by using the text label of the image. Specifically, the user enters the search keyword on the client terminal, and the client sends the search keyword to the corresponding service serve...

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 李习华申瑞珉戴宇荣
Owner 深圳市雅阅科技有限公司
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