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

A User Behavior Prediction Method Integrating Group Behavior

A prediction method and user technology, applied in prediction, neural learning methods, data processing applications, etc., can solve problems such as not considering the impact of user behavior, and achieve the effect of improving accuracy

Active Publication Date: 2022-08-05
SHANGHAI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, most of the existing user behavior prediction algorithms do not take into account the influence of the group behavior of the user group on user behavior

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 User Behavior Prediction Method Integrating Group Behavior
  • A User Behavior Prediction Method Integrating Group Behavior
  • A User Behavior Prediction Method Integrating Group Behavior

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Aiming at the problem that the current user behavior prediction algorithm considers the influence of the user's group on the user behavior is seldom studied, the present invention proposes a user behavior prediction algorithm integrating group behavior, so as to study the effect of the user group's behavior on the user's behavior. What impact does the next action have. The invention adopts a variety of community division methods to divide the user relationship graph into groups, and through the vectorized representation of user actions and the LBL model, the user can be represented by his own behavior in a specific time period, which makes the subsequent user behavior prediction. More beneficial because the user representations are derived from the action embedding matrix. The present invention aggregates the behaviors of individual users in a group by introducing an attention mechanism, so as to objectively and effectively represent group behaviors. In this process, i...

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 user behavior prediction method integrating group behavior. The invention is based on the user's historical behavior and the user relationship graph in the social network, firstly uses the classical community detection algorithm to find the groups in the social relationship graph to provide the basis for the next operation; discretizes the user's historical record and uses the user behavior to embed the representative User embedding; then, based on the attention mechanism, the user embedding of users in each group gets the representation of each group; finally, the user embedding of each user and the group embedding representation of the user group are combined to obtain a new user embedding. Then, the user embedding sequence is input into the GRU recurrent neural network for user behavior prediction. A large number of experimental results on three real data sets have verified that the algorithm of the present invention has a great improvement in HR and MAP indicators compared with the user behavior prediction algorithm that only considers the user's historical behavior and the user's neighbor behavior.

Description

technical field [0001] The invention relates to the field of user behavior prediction, in particular to a user behavior prediction method integrating group behavior. Background technique [0002] The continuous decentralization of science and technology has brought about the widespread popularity of smart devices. With the reduction of the cost of computers and smart phones, the interaction barriers between social networks and the living world have been broken, and the number of active users has surged. Applications led by Sina Weibo, WeChat, QQ, etc. have penetrated into everyone's life, and social networks are gradually affecting the way of life of the public. Mobile social networks have shown their strong charm and great prospects on a global scale, and they have also provided a large number of related user behavior samples for related research. [0003] However, how to filter information reasonably and efficiently has become a difficult problem for users. One of the bi...

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): G06Q10/04G06Q50/00G06N3/04G06N3/08
CPCG06Q10/04G06Q50/01G06N3/04G06N3/08
Inventor 戴东波胡莎莎李卫民
Owner SHANGHAI UNIV