Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Commodity recommendation method and device combining RPA and AI

A product recommendation and product technology, applied in the field of data processing, can solve the problems of high similarity, low conversion rate of recommended product purchase, etc.

Pending Publication Date: 2021-01-29
BEIJING LAIYE NETWORK TECH CO LTD +1
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, the above-mentioned method of recommending products based on the search terms purchased by the user in the history completely relies on the products purchased in the user's history to recommend products, resulting in a high degree of similarity between the recommended products and the products purchased by the user in the history, and the purchase conversion rate of the recommended products is low. high

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 recommendation method and device combining RPA and AI
  • Commodity recommendation method and device combining RPA and AI
  • Commodity recommendation method and device combining RPA and AI

Examples

Experimental program
Comparison scheme
Effect test

example 1

[0037] In this example, the page information currently browsed by the user is determined. The page information may include page identification information, page content information, page type information, etc., and the recommended scene information is determined according to the page information. The recommended scene information can be arbitrarily distinguished from different recommended scenarios. The identification information of the information, for example, can be numbers, letters, or text descriptions, etc. Wherein, when the recommended scene information is a text description, the recommended scene information can include "recommended scene based on product details", "according to package balance Recommended scenarios", etc.

[0038] In this example, the product category to be recommended can be determined according to the page information. For example, when the page information is the displayed clothing category, the product category to be recommended is a category relat...

example 2

[0041] In this example, the page information is obtained, the preset corresponding relationship is queried, and the recommended scene information corresponding to the page information is obtained. For example, when the page information is the page identifier, if the page identifier corresponding to the page browsed by the user is the traffic margin view If the page is identified, the preset pairing relationship is queried, and the corresponding recommended scene information determined is a recommended scene based on the package traffic balance.

[0042] In this embodiment, the deep learning model can be trained based on NLP technology, the input of the deep learning model is page information, and the output is recommended scene information.

example 3

[0044] In this example, the current shopping scene information includes current holiday information, for example, if it is currently Christmas, the recommended scene is a recommended scene based on Christmas.

[0045] Step 102, determine candidate recommended commodities corresponding to the recommended scenario information, and determine a ranking strategy set corresponding to the recommended scenario information, wherein the ranking strategy set includes at least one sorting strategy.

[0046] As a possible implementation, the corresponding recall strategy set can be determined based on the recommendation scene information, wherein the recall strategy set includes at least one recall strategy, and the candidate recommended product is determined according to at least one recall strategy contained in the recall strategy set, where , since the recommended scene information is related to the user's purchase intention, at least one recall strategy determined according to the recom...

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 commodity recommendation method and device combining RPA and AI, and relates to the technical field of AI and RPA, and the method comprises the steps: obtaining the current shopping scene information, and determining the recommendation scene information corresponding to the current shopping scene information; determining candidate recommended commodities corresponding to the recommended scene information, and determining a sorting strategy set corresponding to the recommended scene information, wherein the sorting strategy set comprises at least one sorting strategy; sorting the candidate recommended commodities according to the at least one sorting strategy; and determining a target recommended commodity based on the sorted candidate recommended commodities, generating recommendation data of the target recommended commodity, and outputting the recommendation data. Therefore, different sorting strategies are adapted to sort the to-be-recommended commodities according to different shopping scene information, and the conversion rate of the commodities recommended to the user is ensured.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular to a product recommendation method and device combining RPA and AI. Background technique [0002] Robotic Process Automation (RPA) uses specific "robot software" to simulate human operations on computers and automatically execute process tasks according to rules. [0003] Artificial Intelligence (Artificial Intelligence), the English abbreviation is AI. It is a new technical science that studies and develops theories, methods, technologies and application systems for simulating, extending and expanding human intelligence. Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and produce a new intelligent machine that responds in a manner similar to human intelligence. Research in this field includes robotics, speech recognition, image recognition, natural language processing and expert systems, etc. Among t...

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): G06Q30/06
CPCG06Q30/0631
Inventor 张金明王建周胡一川汪冠春
Owner BEIJING LAIYE NETWORK TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com