Unlock instant, AI-driven research and patent intelligence for your innovation.

Session recommendation method based on social relationship and collaborative relationship

A social relationship and recommendation method technology, applied in the field of conversational recommendation based on social relationship and collaborative relationship, can solve the problems of reducing the importance and increasing the importance of the behavior closest to the recommended time, etc.

Inactive Publication Date: 2022-02-11
CHINA JILIANG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Methods for modeling ordered sequences, such as recurrent neural networks, will increase the importance of behaviors closest to the recommended time and reduce the importance of behaviors farther from the recommended time

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 social relationship and collaborative relationship
  • Session recommendation method based on social relationship and collaborative relationship
  • Session recommendation method based on social relationship and collaborative relationship

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to further understand the present invention, a conversation recommendation method based on social relations and collaborative relations provided by the present invention will be specifically described below in conjunction with specific embodiments, but the present invention is not limited thereto. The non-essential improvements and adjustments made still belong to the protection scope of the present invention.

[0036] First, the variables and formulas used need to be defined.

[0037] Definition 1. V: collection of items, and V=v 1 , v 2 ,...,v |V| , |V| represents the number of items in the item set.

[0038] Definition 2.s u : The current session is a collection of all interactive items in the current time period |s u |Represents the number of items in the session.

[0039] Definition 3.T: A hypergraph constructed based on all sessions and the collection of items in a session.

[0040] Definition 4.G: social network, which records the group structur...

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 social relation and a collaborative relation. According to the method, modeling is carried out on user interests according to current conversations of users and social networks of the users, and articles most likely to be interested by the users in the next step are recommended. The method is mainly composed of four parts: in the first part, all sessions and article sets in the sessions are used for constructing a hypergraph containing interaction relations between users and articles; in the second part, the hypergraph containing the interaction relation between the user and the article and the social network containing the social relation are combined to obtain an extended hypergraph; in the third part, article vector representation and session vector representation in the current session are obtained according to the heterogeneous hypergraph convolutional neural network; in the fourth part, user interests are obtained through an attention mechanism according to the item vector representation and the session vector representation in the current session; and finally, articles are recommended 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 conversation recommendation method based on social relations and collaborative relations. Background technique [0002] A session is a user's interactive behavior within a period of time. Session-based recommendation is based on the current session and recommends the item that the user clicks next. Traditional conversational recommendation systems use recurrent neural networks to model user interests, and recurrent neural networks model the sequence of items in a conversation to get the interests of target users. But recurrent neural networks ignore more complex collaborative information in conversations. Collaborative recommendation considers that users with the same behavior pattern have the same interests. Therefore, there are recent approaches that incorporate collaborative information into recommender systems. The usual method is to obtain the targ...

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): G06F16/9536G06N3/04G06N3/08G06Q50/00
CPCG06F16/9536G06Q50/01G06N3/08G06N3/045
Inventor 顾盼
Owner CHINA JILIANG UNIV