Unlock instant, AI-driven research and patent intelligence for your innovation.

A method and device for product recommendation based on user's picture preferences

A product recommendation and product technology, applied in the field of computer communication, can solve the problems of text description, image features or styles that cannot be described, and achieve the effect of optimized form, easy to find and select, comfortable shopping or search experience

Active Publication Date: 2022-01-07
唯品会(海南)电子商务有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But for the styles of commodities, such as the styles of clothes, some can rely on search, but more styles may not be simply described in words
And because the image of the product is the most intuitive, typically such as clothing, there are certain limitations in recommending the target product to the user only through the existing conventional query. Moreover, these image features or styles cannot be described by exact text, or the user does not intend to search by text category. At this time, the existing method of product recommendation based on the query cannot meet the user's needs.

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 device for product recommendation based on user's picture preferences
  • A method and device for product recommendation based on user's picture preferences
  • A method and device for product recommendation based on user's picture preferences

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] figure 1 It is a flow chart of the method for recommending products according to the user's picture preferences provided by Embodiment 1 of the present invention. Such as figure 1 As shown, the method for recommending products according to the user's picture preferences provided by the embodiment of the present invention includes the following steps:

[0035] 101. Establish a corresponding relationship between the attributes of the product knowledge graph and the image features included in the preset image.

[0036] Specifically, the correlation between each of the multiple attributes of the commodity knowledge map and the image features that can display the attribute is established, so that an attribute or attribute value corresponds to a specific image feature, and these image features are included in the preset picture middle.

[0037] 102. Identify a first image feature according to a picture selected by the user from preset pictures.

[0038] According to the pic...

Embodiment 2

[0054] figure 2 It is a flow chart of the method for recommending products according to the user's picture preferences provided by Embodiment 2 of the present invention, as shown in figure 2 As shown, the method for recommending products according to the user's picture preferences provided by the embodiment of the present invention includes the following steps:

[0055] 201. Create a product knowledge map, which includes the correlation between different types of products and product attribute categories and the correlation between different types of individuals in the same category.

[0056] Create a product knowledge map that contains a variety of product attribute features and their relationship networks, which include at least the correlation between different types of products and product attribute categories and the correlation between different individuals in the same category. The correlation here is also It can be called associativity, and it is used to achieve the...

Embodiment 3

[0074] see image 3 , the embodiment of the present invention provides a device 3 for product recommendation according to the user's picture preferences, including:

[0075] The creation module 31 is used to establish the corresponding relationship between the attributes of the product knowledge map and the image features contained in the preset picture;

[0076]The recognition module 32 is used to recognize the first image feature according to the picture selected by the user from the preset pictures;

[0077] The determination and display module 33 includes a determination sub-module 331 and a display sub-module 332. The determination sub-module 331 is used to determine the first attribute corresponding to the first image feature according to the corresponding relationship, and the display sub-module 332 is used to display the first attribute in a checkable manner. an attribute information;

[0078] The acquisition module 34, according to the first attribute information se...

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 method and a device for recommending commodities according to user's picture preferences, and belongs to the technical field of computer communication. The method includes: establishing a corresponding relationship between the attributes of the commodity knowledge graph and the image features contained in the preset pictures; identifying the first image feature according to the picture selected by the user from the preset pictures; and determining the first image feature according to the corresponding relationship. The first attribute corresponding to the image feature, and display the first attribute information in a checkable manner; according to the first attribute information selected by the user, obtain the product picture associated with the first attribute from the product knowledge graph list; perform image processing according to the product pictures selected by the user from the product picture list, and obtain product recommendation results. The invention satisfies the needs of users for shopping or searching according to diversified choices, improves the shopping experience of users, and can be widely used in the fields of e-commerce, network search, shopping guide and the like.

Description

technical field [0001] The present invention relates to the technical field of computer communication, in particular to a method and a device for recommending commodities according to user's picture preferences. Background technique [0002] Existing e-commerce shopping guides generally adopt the method of user search query or category query. But for the styles of commodities, such as the styles of clothes, some can rely on search, but more styles may not be simply described in words. And because the image of the product is the most intuitive, typically such as clothing, there are certain limitations in recommending the target product to the user only through the existing conventional query. Moreover, these image features or styles cannot be described by exact text, or the user does not intend to search by text category. At this time, the existing method of recommending products based on the query cannot meet the user's needs. In fact, if we use the object recognition tech...

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 Patents(China)
IPC IPC(8): G06Q30/06G06K9/00G06F16/583G06F16/36
CPCG06F16/583G06Q30/0631G06V20/30
Inventor 崔燕红郭师光刘宇董亚楠黄惠燕
Owner 唯品会(海南)电子商务有限公司