Commodity picture searching method and device

A technology of image search and product, applied in the search field, can solve problems such as poor user experience, inaccurate search results, and inability for users to find products

Inactive Publication Date: 2018-03-30
广州唯品会研究院有限公司
View PDF5 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Since the search results returned by searching for pictures by pictures contain a large number of pictures that the user is not trying to search for, the search results are very inaccurate, resulting in poor user experience; while searching for pictures by combining pictures with manual selection of categories can get effective search results, However, it is impossible for users to quickly and accurately find a certain product, such as the product to be searched for of a specified brand, the product to be searched for with a specified pattern feature, or the product to be searched for a specified color, etc.
[0005] Therefore, the accuracy of image search results in the prior art is not high, and it is impossible for users to quickly and accurately search for corresponding products, resulting in poor user experience

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
  • Commodity picture searching method and device
  • Commodity picture searching method and device
  • Commodity picture searching method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0094] The embodiment of the present invention provides a product image search method, refer to figure 1 As shown, the method includes:

[0095] 101. Extract a plurality of first tags from a picture input by a user, and obtain a first tag selected by the user among the plurality of first tags.

[0096] Specifically, extracting multiple first tags from the picture input by the user, the process may include:

[0097] Identify the product to be searched in the picture;

[0098] Extract multiple features of the product to be searched, and the features are used to characterize the product to be searched;

[0099] Obtain a trained recognition model, and when multiple features of the product to be searched are input to the trained recognition model, determine that the label output by the trained recognition model is the first label of the product to be searched;

[0100] Among them, to obtain a trained recognition model, the process may include:

[0101] Construct a training sample picture set, ...

Embodiment 2

[0112] The embodiment of the present invention provides a product image search method, refer to figure 2 As shown, the method includes:

[0113] 201. Extract multiple first tags from a first picture input by a user, and extract multiple second tags from a second picture input by the user.

[0114] Specifically, extracting multiple first tags from the first picture input by the user, the process may include:

[0115] Extracting multiple first tags from the first picture input by the user includes:

[0116] Identify the first product in the first picture;

[0117] Extract multiple first features of the first product, the first features are used to characterize the first product;

[0118] Obtain a trained recognition model, and when multiple first features are input to the trained recognition model respectively, determine that the label output by the trained recognition model is the first label of the first product;

[0119] Extracting multiple second tags from the second picture input by t...

Embodiment 3

[0134] The embodiment of the present invention provides a product image search method, refer to image 3 As shown, the method includes:

[0135] 301. Identify the product to be searched in the picture input by the user.

[0136] Among them, there are one or more products to be searched identified from the picture.

[0137] The product to be searched can be clothing, food, cosmetics, furniture, daily necessities or other commodities.

[0138] Specifically, the process may include:

[0139] a. Get the picture entered by the user.

[0140] Among them, there is at least one picture input by the user.

[0141] Specifically, acquiring the user's trigger operation on the input picture function icon on the client;

[0142] Under the trigger of the trigger operation, the picture input interface pops up;

[0143] Get the picture input by the user by uploading pictures or taking pictures.

[0144] Among them, the client can be a terminal with a camera, such as a smart phone, a tablet computer, etc.; th...

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 commodity picture searching method and device, and belongs to the technical field of searching. The method comprises the following steps that: extracting a plurality of firsttags from a picture input by a user, and obtaining the first tag selected by the user from the plurality of first tags; extracting a second tag from commodity description information input by the user; and according to the selected first tag and second tag, carrying out commodity picture searching, and outputting a commodity picture searching result. By use of the embodiment of the invention, thefirst tag and the second tag are combined to carry out the commodity picture searching so as to enable a search result to more conform to user intentions, so that the accuracy of the picture searching result is improved, the user can quickly and accurately search the corresponding commodity, and user experience is improved.

Description

Technical field [0001] The present invention relates to the field of search technology, in particular to a method and device for searching commodity pictures. Background technique [0002] There is an increasing need to search for pictures on the Internet or search for relevant information based on pictures. [0003] At present, the search method based on pictures is mainly to search pictures through pictures, and search pictures through pictures combined with user selection categories. Among them, the process of searching pictures through pictures is: the user uploads a picture, and the system includes the picture information and the picture library. Compare each of the pictures and show the most similar pictures to the user; the process of manually selecting category search pictures through picture combination is: the user uploads a picture, selects the picture category at the same time, and the system combines the category and picture information to display it to the user The m...

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): G06F17/30G06Q30/06
CPCG06Q30/0625G06F16/583G06F16/5866
Inventor 郭安琪张智祺徐然黄惠燕
Owner 广州唯品会研究院有限公司
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