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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


