Product recommendation method, device and electronic equipment

A recommendation method and product technology, applied in the computer field, can solve the problems of insufficient products and low accuracy, and achieve the effect of improving richness and accuracy and improving user experience

Active Publication Date: 2017-12-01
BEIJING SANKUAI ONLINE TECH CO LTD
View PDF8 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present application provides a product recommendation method, which solves the problem of insufficient recommended products and low accuracy in the product recommendation method in the prior art

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
  • Product recommendation method, device and electronic equipment
  • Product recommendation method, device and electronic equipment
  • Product recommendation method, device and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] A product recommendation method disclosed in this application, such as figure 1 As shown, the method includes: Step 100 to Step 130.

[0027] Step 100, determine the user scenario of the user's access behavior.

[0028] The user scenario of the access behavior is determined according to the specific business requirements of the platform, and the user describes the specific scenario of the user behavior, which may include, for example: store arrival, takeaway, shopping mall, and business travel. Preferably, the user scenario of the access behavior is determined according to the access request information, context information, and user profile information.

[0029] During specific implementation, first, the access request information and real-time context information of the user's access behavior are determined, and the user profile information of the user who initiates the access behavior is determined.

[0030] The user access behavior in the embodiment of the present...

Embodiment 2

[0046] A product recommendation method disclosed in this embodiment, such as figure 2 As shown, the method includes: Step 200 to Step 270.

[0047] Step 200, acquiring training samples based on user behavior logs.

[0048] When training a sorting model, first collect training samples. The collected training samples can be user historical behavior logs and previous product data, such as the behavior logs and product data of all users of the O2O platform in the previous year; it can also include user real-time behavior logs and current online product data. During specific implementation, data will be screened according to different user behaviors. For example, training samples will be collected according to the skip-above principle. Products clicked by the user will be used as positive samples, and products that have not been clicked and have effective exposure will be used as negative samples. The time spent on the page after the user clicks screens positive samples. Dependi...

Embodiment 3

[0105] A product recommendation device disclosed in this embodiment, such as image 3 As shown, the device includes:

[0106] User scenario determination module 300, configured to determine the user scenario of user access behavior;

[0107] A product recommendation strategy and ratio determination module 310, configured to determine at least one product recommendation strategy that matches the user scenario determined by the user scenario determination module, and a product ratio recommended by each of the product recommendation strategies;

[0108] The candidate recommended product determination module 320 is used to select a product with a corresponding product ratio among the products recommended by each product recommendation strategy as a candidate recommended product;

[0109] The sorting module 330 is configured to sort the candidate recommended products determined by the candidate recommended product determination module through a pre-trained sorting model.

[0110]...

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 provides a product recommendation method and belongs to the technical field of computers. The method solves the problems in the prior art that recommended products are not rich enough and the accuracy is relatively low. The method comprises the following steps of determining a user scene of a user access behavior; determining at least one product recommendation strategy matched with the user scene and the product proportion recommended by each product recommendation strategy; selecting a product of the corresponding product proportion as a candidate recommendation product from all products recommended by each product recommendation strategy; and sequencing all candidate recommendation products according to a pre-trained sequencing model. According to the invention, the product recommendation is carried out by selecting a plurality of recommendation strategies suitable for the user scene according to the user scene. Therefore, the richness and the accuracy of recommended products are effectively improved.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to a product recommendation method and device, and electronic equipment. Background technique [0002] With the development of the mobile Internet, the local life-oriented services provided by the O2O (Online-to-Offline) platform have greatly facilitated people's lives, and the search demand on the O2O platform has also gradually increased, recommending products of interest to users. The need is also becoming more urgent. The existing recommendation method is based on the recommendation of the user's historical behavior, constructing the user item matrix, using recommendation methods based on collaborative filtering, similar content, user grouping, etc., to recommend items that the user may like, and the results are relatively simple. Even if one strategy is used as the main recommendation method, other strategies are used as supplementary recommendation methods. For ex...

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): G06Q30/06G06Q30/02G06Q50/12
CPCG06Q30/0255G06Q30/0263G06Q30/0631G06Q50/12
Inventor 陈文石曹佐刘志权潘强张弓
Owner BEIJING SANKUAI ONLINE 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