Commodity combination recommendation method and device, electronic equipment and readable storage medium

A recommendation method and commodity technology, applied in business, electronic digital data processing, forecasting, etc., can solve the problems of high failure rate of commodity combination and new demand unable to match target commodity combination, etc.

Pending Publication Date: 2019-10-01
BEIJING SANKUAI ONLINE TECH CO LTD
View PDF0 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, due to changes in user needs, the new needs cannot be matched to the corresponding target product combination, resulting in a high failure rate for product combination recommendation

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 combination recommendation method and device, electronic equipment and readable storage medium
  • Commodity combination recommendation method and device, electronic equipment and readable storage medium
  • Commodity combination recommendation method and device, electronic equipment and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] Reference figure 1 , Which shows a flowchart of the steps of a method for recommending a product combination in an embodiment of the present disclosure, which is specifically as follows.

[0034] Step 101: Obtain user demand information and commodities provided by the target merchant.

[0035] The embodiments of the present disclosure can be applied to an online sales platform. A merchant can enter the platform and sell products. The platform can combine and recommend products provided by the merchant to users who visit the merchant or users who need to recommend a combination of products.

[0036] Among them, the user demand information is used to indicate the user's conditions for the product combination, which can be limited from multiple dimensions. For example, for the dish combination, it can be expressed from the dimension of ingredients, including: chicken, fish, vegetables, etc., or from the dimension of taste , Including: super spicy, slightly spicy, not spicy, etc.,...

Embodiment 2

[0056] Reference image 3 , Which shows a flowchart of specific steps of a method for recommending a product combination in another embodiment of the present disclosure, which is specifically as follows.

[0057] Step 201: Obtain user demand information and commodities provided by the target merchant.

[0058] For this step, refer to the detailed description of step 201, which will not be repeated here.

[0059] Step 202: For each user demand information, obtain a candidate product set that meets the user demand information from the product.

[0060] In the embodiment of the present disclosure, the user demand information may be one or more. When the user demand information is one, only one candidate product in the candidate product combination needs to meet the user demand information; when the user demand information is multiple At this time, the candidate product combination needs to meet multiple user demand information at the same time. It can be that one candidate product in the...

Embodiment 3

[0128] Reference Image 6 , Which shows a structural diagram of a product combination recommendation device in another embodiment of the present disclosure, which is specifically as follows.

[0129] The demand and commodity acquisition module 301 is used to acquire user demand information and commodities provided by the target merchant.

[0130] The candidate product combination generating module 302 is configured to generate a candidate product combination according to the product and the user demand information.

[0131] The commodity knowledge acquisition module 303 is configured to acquire commodity knowledge corresponding to the commodity from a preset commodity knowledge graph.

[0132] The candidate score prediction module 304 is used to predict the candidate score of the candidate product combination based on the user demand information and the product knowledge through the product combination score prediction model obtained by pre-training.

[0133] The product combination rec...

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 invention provide a commodity combination recommendation method and device, electronic equipment and a readable storage medium. The commodity combination recommendation method comprises the steps: obtaining user demand information and a commodity provided by a target merchant; generating a candidate commodity combination according to the commodity and the user demand information; obtaining commodity knowledge corresponding to the commodity from a preset commodity knowledge map; predicting candidate scores of the candidate commodity combinations according to the user demand information and the commodity knowledge through a commodity combination score prediction model obtained through pre-training; and recommending the candidate commodity combination to the user accordingto the candidate score. The candidate scores of the candidate commodity combinations can be predicted in real time according to the user demand information for recommendation, and the recommended candidate commodity combinations can be adjusted in real time according to the user demand information, and the recommendation success rate can be improved.

Description

Technical field [0001] The embodiments of the present disclosure relate to the field of personalized recommendation technology, and in particular to a method, device, electronic device, and readable storage medium for recommending a combination of commodities. Background technique [0002] In the field of personalized recommendation, the system can not only recommend related products to users, but also recommend product combinations to users, so that users do not need to match products by themselves. For example, in the field of food delivery, the system can recommend a set meal to users, thereby reducing the time for users to select multiple dishes and match them. [0003] In the prior art, commodity combinations are mainly generated offline by the system, and specific commodity combinations can be generated and marked according to the specific needs of users. When recommending a product combination to a user, first, obtain the user's needs; then, according to the demand, select ...

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
IPC IPC(8): G06Q30/06G06F16/36G06F16/9535G06K9/62G06Q10/04
CPCG06Q30/0631G06F16/367G06Q10/04G06F16/9535G06F18/214
Inventor 杨林路坤罗震
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