Social group recommendation method, system and device and storage medium

A recommendation method and group technology, applied in data processing applications, instruments, calculations, etc., can solve problems such as the influence of extreme value of member distribution, decline in recommendation accuracy, over-fitting, etc., to enhance accuracy and communication capabilities, and improve communication ability, the effect of improving accuracy

Active Publication Date: 2022-05-17
UNIV OF SCI & TECH OF CHINA
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional heuristic aggregation strategy is affected by the extreme value of the distribution of member preferences, and cannot accurately model the group
[0004] With the development of deep learning technology, researchers propose to use representation learning technology to learn complex group preference feature representation, and use attention mechanism to learn the weight of each user in group decision-making, but these methods do not take into account most groups Due to the sparsity of historical interaction data, using insufficient data for training will cause serious overfitting problems and lead to a decrease in recommendation accuracy

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
  • Social group recommendation method, system and device and storage medium
  • Social group recommendation method, system and device and storage medium
  • Social group recommendation method, system and device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] Embodiments of the present invention provide a social group recommendation method, such as Figure 2 As shown, it mainly includes the following steps:

[0037] Step 1: Build a social group recommendation model and obtain social network data.

[0038] In an embodiment of the present invention, the social network data mainly includes the following three types of data: group and item interaction data, group user interaction data with items, and social network diagrams between users within the group; the above three types of data are conventional data, users can be collected through the Internet.

[0039] Step 2: Train the social group recommendation model.

[0040] During the training stage, the social network data is input to the social group recommendation model, and three types of information are extracted by the social group recommendation model:

[0041] 1) Use the relationship between nodes in the social network graph to calculate the social influence representation vector...

Embodiment 2

[0125] The present invention also provides a social group recommendation system, which is mainly based on the method provided in the foregoing embodiment one, such as Figure 5As shown, the system mainly includes:

[0126] Model building unit for building social group recommendation models,

[0127] Data information acquisition unit, which is used to obtain group and item interaction data, user interaction data with items within the group, and social network diagrams between users in the group;

[0128] Training unit, applied to the training stage; in the training stage, the social group recommendation model, using the relationship between the nodes in the social network graph to calculate the corresponding user's social influence representation vector; based on the user's interaction data with the user's social influence in the group, the user's feature representation vector is calculated by means of influence diffusion, and based on the group and the item interaction data, comb...

Embodiment 3

[0133] The present invention further provides a processing apparatus, such as Figure 6 Shown, which comprises, mainly: one or more processors; memory for storing one or more programs; wherein, when the one or more programs are executed by the one or more processors, such that the one or more processors implement the method provided in the foregoing embodiments.

[0134] Further, the processing apparatus further comprises at least one input device and at least one output device; in the processing apparatus, the processor, memory, input device, output device is connected by a bus.

[0135] In an embodiment of the present invention, the specific type of memory, input device and output device is not limited; for example:

[0136] The input device can be a touch screen, an image acquisition device, a physical button or a mouse;

[0137] The output device can be a display terminal;

[0138] The memory may be random access memory (RAM) or non-volatile memory, such as disk storage.

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 social group recommendation method, system and device, and a storage medium, which can directly and automatically calculate the social influence of a user from a user social network, and enhance the accuracy and propagation ability of group recommendation by using the social influence of the user. The deeper feature representation of the user can be obtained by using a user influence diffusion method, and meanwhile, the influence of each user in the decision process is learned by using an attention mechanism when the preference of the group is modeled, so that the group feature representation is more effectively obtained; and finally, single user recommendation and group user recommendation tasks are optimized at the same time through a combined learning mode, the performance of a social group recommendation model is improved, the accuracy of group recommendation is improved, and the propagation capability of group recommendation is improved.

Description

Technical field [0001] The present invention relates to the field of article recommendation technology, in particular to a social group recommendation method, system, device and storage medium. Background [0002] The advent of the Internet era and the rise of social networks have enabled information to be disseminated and exchanged without hindrance, according to statistics, in 2020, the number of global Internet users reached 4.54 billion, and the number of Internet users in China reached 904 million. The explosion of information in social networks has created a serious problem of information overload, and recommendation algorithms are able to recommend content that interests users according to their preferences. There are a large number of groups in social networks in which users come together through the same interests or specific events. Most of the existing studies have focused on individual recommendations and ignored group recommendations. as Figure 1 As shown, the grou...

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 Applications(China)
IPC IPC(8): G06F16/9536G06Q50/00
CPCG06F16/9536G06Q50/01
Inventor 毛震东张勇东胡博白嘉萌
Owner UNIV OF SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap