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

Next article recommendation method based on multi-dimensional Hawkes process and attention mechanism

A recommendation method and attention technology, applied in special data processing applications, instruments, electrical digital data processing, etc., can solve problems such as difficult to model long-term interests of users, unable to make full use of interactive sequence data of user items, etc., and achieve improved results Effect

Active Publication Date: 2020-01-14
HANGZHOU DIANZI UNIV
View PDF3 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing methods cannot make full use of the interaction sequence data of user items, and it is difficult to accurately model the user's dynamic interest reflected in the sequence and combine the user's long-term interest

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
  • Next article recommendation method based on multi-dimensional Hawkes process and attention mechanism
  • Next article recommendation method based on multi-dimensional Hawkes process and attention mechanism
  • Next article recommendation method based on multi-dimensional Hawkes process and attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] In order to describe the present invention more specifically, the technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0035] The present invention is based on the multidimensional Hawkes process and the next item recommendation method of the attention mechanism comprising the following steps:

[0036] (1) Collect user item interaction sequence data The user-item interaction sequence is an ordered set of interaction behaviors between users and items The user set and item set are U and I respectively.

[0037] (2) According to user u j sequence of interactions user u j , historical interaction behavior {(i 1 ,t 1 ),(i 2 ,t 2 ),…,(i m-1 ,t m-1 )} and target item i m The conditional density function of is modeled as:

[0038]

[0039] in: is user u j for the target item i m of general interest, Represents historical behavior h affecting user u j for ...

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 next article recommendation method based on a multi-dimensional Hawkes process and an attention mechanism. The method comprises the following steps: S1, acquiring an articlekey feature vector and a user interest vector based on the multi-dimensional Hawkes process and the attention mechanism; S2, predicting and modeling dynamic interests of the user; S3, recommending sequence-aware. According to the invention, the feature vector of the article and the user interest vector are extracted from the user article interaction sequence by using the multi-dimensional Hawkes process and the attention mechanism; the dynamic interests of the users are predicted by combining the interaction sequence records of the users, and finally, the interest preferences of the users andthe key feature vectors of the articles are comprehensively considered during recommendation, so that the recommendation effect is improved, and the recommendation accuracy is improved.

Description

technical field [0001] The invention belongs to the technical field of data mining and recommendation, and in particular relates to a next item recommendation method based on a multidimensional Hawkes process and an attention mechanism. Background technique [0002] Recommender systems can help users find relevant items from massive online content to reduce search costs, and predicting user behavior is one of the cores of realizing personalized recommendation systems. However, traditional methods usually suffer from problems such as low accuracy and insufficient data utilization, especially unable to meet users' real-time needs. The next item recommendation algorithm predicts the user's next behavior by combining the traditional recommendation algorithm with the user's interaction sequence, which improves the recommendation accuracy and user satisfaction rate to a certain extent. However, the existing methods cannot make full use of the user-item interaction sequence data, ...

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): G06F16/9535G06Q10/04
CPCG06Q10/04G06F16/9535
Inventor 张新王东京俞东进
Owner HANGZHOU DIANZI UNIV