Picture recommendation method, apparatus and device, and storage medium

A recommendation method and picture technology, applied in the computer field, can solve problems such as poor recommendation effect and lower user experience, and achieve the effect of improving user experience and optimizing recommendation effect

Inactive Publication Date: 2018-09-21
MOBVOI INFORMATION TECH CO LTD
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since most of the existing solutions need to artificially classify and label each dial to be selected in advance, and only select the dial that should be recommended for the user based on the user's selection behavior, the recommendation effect is not good, reducing the 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
  • Picture recommendation method, apparatus and device, and storage medium
  • Picture recommendation method, apparatus and device, and storage medium
  • Picture recommendation method, apparatus and device, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0078] figure 1 It is a schematic flowchart of a picture recommendation method provided in Embodiment 1 of the present invention. The method can be applied to the situation of recommending pictures that conform to the user's style for the user, and the method can be executed by a picture recommendation device, which can be composed of hardware and / or software, and generally can be integrated in the online business server and all the pictures that include the picture recommendation function. in the terminal. Specifically include the following:

[0079] S110. Acquire first historical image operation information of the user, where the first historical image operation information includes: an operation image and an operation type corresponding to the operation image.

[0080] Optionally, the recent picture selection records of the target user in the online store can be retrieved to obtain the user's first historical picture operation information, wherein the operation picture in...

Embodiment 2

[0096] figure 2 It is a schematic flowchart of a method for recommending pictures provided in Embodiment 2 of the present invention. This embodiment is optimized on the basis of the foregoing embodiments, and provides an optimal picture recommendation method. Specifically, the content feature vector is further optimized to include a picture feature vector and a description feature vector. Specific steps are as follows:

[0097] S210. Acquire first historical image operation information of the user, where the first historical image operation information includes: an operation image and an operation type corresponding to the operation image.

[0098] S220. Perform feature extraction on the operation picture to obtain a corresponding picture feature vector.

[0099] Optionally, a CNN algorithm may be used to extract features from the operation picture. Exemplarily, a floating-point number matrix can be obtained by preprocessing the operation picture first, that is, one operat...

Embodiment 3

[0112] image 3 It is a schematic flowchart of a method for recommending pictures provided by Embodiment 3 of the present invention. This embodiment is optimized on the basis of the above embodiments, and provides an optimal picture recommendation method. Specifically, it further optimizes the update training of the picture classification model matching the user according to the content feature vector and the behavior feature vector. Specifically include the following:

[0113] S310. Acquire first historical image operation information of the user, where the first historical image operation information includes: an operation image and an operation type corresponding to the operation image.

[0114] S320. Acquire a content feature vector corresponding to the operation picture.

[0115] S330. Obtain a behavior feature vector corresponding to the operation type.

[0116] S340. Input the content feature vector and the behavior feature vector into the original classification mod...

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

Embodiments of the present invention disclose a picture recommendation method, apparatus and device, and a storage medium. The method comprises: acquiring first historical picture operation information of a user, wherein the first historical picture operation information comprises: an operation picture and an operation type corresponding to the operation picture; acquiring a content feature vectorcorresponding to the operation picture; acquiring a behavior feature vector corresponding to the operation type; determining a picture classification model that matches the user according to the content feature vector and the behavior feature vector; and acquiring a picture that matches an output result of the picture classification model, and recommending the picture to the user. According to the technical scheme of the present invention, the recommendation effect can be optimized and the user experience can be improved.

Description

technical field [0001] Embodiments of the present invention relate to computer technology, and in particular to a picture recommendation method, device, equipment and storage medium. Background technique [0002] With the launch of smart watches, users can choose to install the watch face as the watch wallpaper, and the corresponding watch face wallpaper store came into being. After downloading the watch face, the user can switch between different watch faces on the watch as the watch wallpaper. If they don’t like it, the user will delete the watch face . If a recommendation service is added to the user's process of selecting a dial to recommend wallpapers that meet the user's preferences, the user's selection time can be greatly saved. [0003] The traditional dial recommendation service is mainly to recommend dials with the same label or the same category as the dials used before for the user according to the user's historical selection records. Since most of the existin...

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): G06F17/30G06K9/62G06N3/04G06N3/08
CPCG06N3/084G06N3/045G06F18/241
Inventor 汪剑
Owner MOBVOI INFORMATION TECH CO LTD
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