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

Personalized recommendation system and method based on interaction records

A technology for interactive recording and recommendation methods, which is used in sales/rental transactions, data processing applications, instruments, etc. to reduce losses and improve recommendation effects.

Pending Publication Date: 2022-06-07
FUDAN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current recommendation system still has major defects in solving "commodity cold start" and "user cold start". It can only recommend preset products or popular products, and there is no way to make full use of existing information to make targeted recommendations. recommend

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
  • Personalized recommendation system and method based on interaction records
  • Personalized recommendation system and method based on interaction records
  • Personalized recommendation system and method based on interaction records

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, further detailed description will be made below in conjunction with the accompanying drawings and specific embodiments:

[0040]figure 1 It is a personalized recommendation system based on interactive records of the present invention. The system includes: an interactive record data processing module, a data space division module, an interactive graph construction and model training module, a non-interactive record commodity and user module, a multi-level division and search module, Spatial vector index module and recommendation result generation module. Among them: the interaction record data processing module performs data cleaning, attribute selection and coding on the interaction records between users and commodities; the data space division module uses the spatial division method to divide the commodity data and user data; the interactio...

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 belongs to the technical field of electronic commodity recommendation, and particularly relates to a personalized recommendation system and method based on interactive records. The system comprises an interaction record data processing module, a data space division module, an interaction graph construction and model training module, a non-interaction record commodity and user module, a multi-level division search module, a space vector index module and a recommendation result generation module. According to the method, a novel model structure and a novel method process are provided, interaction record data are used, high-quality representation vectors are generated for existing commodities and users, known information is fully utilized in a cold start scene, a personalized scheme is provided through a multi-level division model, a cold start recommendation result is optimized, and the overall recommendation effect is improved.

Description

technical field [0001] The invention belongs to the technical field of electronic commodity recommendation, and in particular relates to a personalized recommendation system and method based on interaction records. Background technique [0002] At present, the recommendation system has been widely used in various platforms such as e-commerce platforms, long and short video platforms, news platforms, etc., and has generated huge benefits, especially in the interaction and recommendation scenarios between products and users under the e-commerce platform. made great progress. However, the current recommendation system still has major defects in solving the "cold start of goods" and "cold start of users". recommend. At the same time, limited by the huge scale of products and users and the huge number of requests to the recommender system, the recommender system usually needs to generate appropriate representation vectors for the products and users, and provide a fast search fu...

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 孙未未张新宇
Owner FUDAN UNIV
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