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

User behavior sequence recommendation method based on attention mechanism and convolutional neural network

A convolutional neural network, recommendation method technology, applied in the field of user behavior sequence recommendation, can solve problems such as insufficient learning of user long-term preferences

Pending Publication Date: 2019-07-26
SUZHOU VOCATIONAL UNIV
View PDF5 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method only takes the user embedding matrix as the user's long-term preference, which is not enough to learn the user's long-term preference

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
  • User behavior sequence recommendation method based on attention mechanism and convolutional neural network
  • User behavior sequence recommendation method based on attention mechanism and convolutional neural network
  • User behavior sequence recommendation method based on attention mechanism and convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0115] First, we use U={u 1 ,u 2 ,...,u M} represents a set of M users, V={v 1 , v 2 ,...,v N} represents a collection of N items in the source domain. Each user generates a sequence of interactions with a sequence of items This sequence is arranged in chronological order, where t represents a relative time index rather than an absolute time, |L u |Indicates the user's interaction sequence length. With the above symbolic representations, our sequential recommendation task is defined as follows, where we focus on extracting information from implicit feedback and user interaction sequential feedback data (e.g., users' continuous check-in and purchase transaction records). When given a user u and his historical interaction sequence L u , our purpose is to mine the user's long-term preference and short-term preference from the interaction records to recommend a set of items that user u may interact with in the next period of time.

[0116] related method

[0117] (1) Gr...

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 sequence recommendation method based on an attention mechanism and a convolutional neural network, and the method comprises the following steps: collecting previous behavior data of a user as long-term preference interaction sequence data; calculating the weight of each behavior data in the long-term preference interaction sequence data by using an attentionmechanism algorithm, and calculating the long-term preference of the user according to the weight; selecting behavior data within a period of time as short-term preference interaction sequence data;according to the short-term preference interaction sequence data, calculating the short-term preference of the user by using a convolutional neural network algorithm; splicing the long-term preferenceand the short-term preference of the user to generate user behavior sequence recommendation. Compared with a conventional interaction method of fitting users-projects-or relations among projects, themethod can effectively and quickly combine long-term and short-term preferences to recommend to the user.

Description

technical field [0001] The present invention relates to a user behavior sequence recommendation method, more specifically, to a user behavior sequence recommendation method based on an attention mechanism and a convolutional neural network. Background technique [0002] With the continuous development of mobile Internet technology, the amount of information on the network is rapidly expanding and increasing exponentially, and the problems of information overload and information wandering on the network are becoming more and more serious. In order to provide users with satisfactory information and services, recommender systems emerged as the times require, and have become a research field that many researchers pay attention to. The recommendation system performs information filtering by predicting the user's preference for information resources. [0003] With the rapid development of the platform economy, many companies such as Amazon, Taobao and Uber are creating their own ...

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): G06Q30/02G06N3/08G06N3/04
CPCG06Q30/0255G06Q30/0277G06N3/084G06N3/045
Inventor 鲜学丰赵朋朋刘建
Owner SUZHOU VOCATIONAL UNIV