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

Session recommendation method based on capturing user long and short term interest heterogeneous hypergraph

A recommendation method, long-term and short-term technology, applied in the field of Internet services, can solve problems such as unable to capture links

Inactive Publication Date: 2022-05-03
CHINA JILIANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the long-term interest and short-term interest of the same user are related. Modeling the long-term and short-term interest of the user alone cannot capture the connection between the two.

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
  • Session recommendation method based on capturing user long and short term interest heterogeneous hypergraph
  • Session recommendation method based on capturing user long and short term interest heterogeneous hypergraph
  • Session recommendation method based on capturing user long and short term interest heterogeneous hypergraph

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] In order to further understand the present invention, a session recommendation method based on capturing the heterogeneous hypergraph of users' long-term and short-term interests provided by the present invention will be described in detail below in conjunction with specific embodiments, but the present invention is not limited thereto. Non-essential improvements and adjustments made under the core guiding ideology still belong to the protection scope of the present invention.

[0039] The problem of this method is defined as recommending the next item of interest to the user based on the sequence of interacting items in all the user's sessions. That is, based on user u i historical session sequence of and the current session Predict the user's next interaction item. Among them, the historical session sequence is sorted in chronological order, user u i current session of subscript is session The length of the sequence of items within, v j is user u i in se...

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 discloses a session recommendation method based on a heterogeneous hypergraph for capturing long and short term interests of a user, which is used for recommending a next interested article to the user based on an interactive article sequence in all sessions of the user. The forward propagation part of the invention is mainly composed of five parts. The first part is to construct a heterogeneous hypergraph containing user hyperedges and session hyperedges from session sequences of all users; the second part is to obtain an article vector, a session vector and a user vector by using a heterogeneous hypergraph neural network; the third part is to obtain the current interest of the user based on the gate loop unit network according to the current session of the user; in the fourth part, the current interest of the user, the session vector and the user vector are combined to obtain the interest of the user; and 5, recommending articles to the user according to the interest of the user.

Description

technical field [0001] The invention belongs to the technical field of Internet services, and in particular relates to a session recommendation method based on heterogeneous hypergraphs capturing users' long-term and short-term interests. Background technique [0002] A session refers to a sequence of items that a user interacts with over a period of time, and is generally divided by the time interval between user actions. The session-based recommendation method refers to modeling the user's interests based on the sequence of items in the session, and recommending the next item of interest to the user. Session recommendation methods are classified into single-session based recommendation models and multi-session based recommendation models. The single-session recommendation method refers to using only the item sequence in the current session to capture the user's current interest and make recommendations. The multi-session recommendation method divides all the item sequenc...

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): G06F16/9535G06N3/04
CPCG06F16/9535G06N3/044G06N3/045
Inventor 顾盼
Owner CHINA JILIANG 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