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

A group recommendation method and system based on attention mechanism

A recommendation method and attention technology, applied in data processing applications, instruments, computing, etc., can solve the problems of ignoring the user's influence weight, unable to make group decisions, etc., to improve the recommendation performance, improve user satisfaction, and achieve significant effects.

Active Publication Date: 2022-04-15
SHANDONG NORMAL UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Most of the existing memory-based and model-based group recommendation methods use predefined group recommendation strategies, which cannot dynamically make group decisions; and ignore the influence weight of each user in the group. Users in different groups , the user's weight is also different, and the user's weight plays different roles and influences in determining different types of projects

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
  • A group recommendation method and system based on attention mechanism
  • A group recommendation method and system based on attention mechanism
  • A group recommendation method and system based on attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] The present disclosure provides a group recommendation method based on an attention mechanism, including the following steps:

[0052] (1) According to the user's interest feature data, calculate the interest similarity between users, and construct potential preference groups through clustering methods;

[0053](2) Calculate the weight of each user in the potential preference group, based on the weight of each user, use the attention mechanism network to fuse the preferences of users in the potential preference group, and calculate the potential preference group’s influence on a single item predictive score;

[0054] (3) Obtain the items to be recommended, and complete the group recommendation according to the prediction scores of potential preference groups for different items.

[0055] Further preferably, said step (1) includes:

[0056] According to the user's rating of the item, the user's interest characteristics are obtained, and the improved density peak cluste...

Embodiment 2

[0100]Embodiment 2, the present disclosure provides a group recommendation system based on an attention mechanism, which is characterized in that it includes:

[0101] The potential preference group building module obtains the user's interest characteristic data, calculates the interest similarity between users, and constructs the potential preference group through a clustering method;

[0102] The preference fusion module uses the attention mechanism network to calculate the weight of each user in the potential preference group, based on the weight of each user, performs preference fusion for the users in the potential preference group, and calculates the potential preference group for each user. Predicted scores for individual items;

[0103] The recommendation module obtains the items to be recommended, and completes the group recommendation according to the prediction scores of potential preference groups for different items.

[0104] Further preferably, in the preference...

Embodiment 3

[0107] Embodiment 3, the present disclosure provides a computer device, including a memory, a processor, and computer instructions stored in the memory and run on the processor. When the computer instructions are run by the processor, the following steps are implemented, including:

[0108] Obtain the user's interest feature data, calculate the interest similarity between users, and construct potential preference groups through clustering methods;

[0109] Use the attention mechanism network to calculate the weight of each user in the potential preference group, based on the weight of each user, perform preference fusion for users in the potential preference group, and calculate the prediction of the potential preference group for a single item Score;

[0110] Obtain the items to be recommended, and complete the group recommendation according to the predicted scores of different items by the potential preference groups.

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

This disclosure provides a group recommendation method and system based on an attention mechanism. By preprocessing user data information, the improved density peak clustering method is used to discover potential groups of users, so that users with high similarity Classify into a group; use the attention mechanism network for the members in the group, design the attention mechanism model (AMGR) to calculate the weight of the members in the group, and perform preference fusion; use the neural collaborative filtering (NCF) framework to interactively learn data and predict users Or group prediction scores for different items, so as to realize group recommendation. This disclosure is more comprehensive than traditional methods, and practice has proved that this method is effective for actual data sets.

Description

technical field [0001] The present disclosure relates to a group recommendation method and system based on an attention mechanism. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Currently, recommender systems are widely used in many online information systems, such as social media sites, e-commerce platforms, etc., to help users choose products that meet their needs. Most of the recommendation systems today are designed for individual users. However, with the popularity of social media, people are more and more inclined to organize and participate in community group activities. Group recommendation is different from personal recommendation. It needs to be A group of users make recommendations. In group recommendation, not only the preferences of a single user but also the preferences of users in the entire group need to be considered, ...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/9536G06F16/9535G06Q50/00
CPCG06F16/9536G06F16/9535G06Q50/01
Inventor 丁艳辉徐海燕
Owner SHANDONG NORMAL UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com