Sequence recommendation method, device and equipment based on self-attention mechanism

A recommendation method and attention technology, applied in the field of information services, can solve problems such as insufficient representation and differentiation of users' dynamic long-term preferences and short-term needs, loss of chronological information, and inaccurate objects recommended by recommendation methods.

Pending Publication Date: 2019-07-12
SUZHOU VOCATIONAL UNIV
View PDF4 Cites 67 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the existing recommendation methods based on self-attention do not consider the position of the sequence when modeling user dependence, resulting in the loss of temporal order information in the sequence, so that it is not enough to characterize and distinguish user dynamics and changing long-term preferences and Short-term demand further leads to inaccurate objects recommended by the recommendation method and poor user experience

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
  • Sequence recommendation method, device and equipment based on self-attention mechanism
  • Sequence recommendation method, device and equipment based on self-attention mechanism
  • Sequence recommendation method, device and equipment based on self-attention mechanism

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Please refer to figure 1 , figure 1 It is a flowchart of a sequence recommendation method based on a self-attention mechanism in an embodiment of the present invention, and the method includes the following steps:

[0058] S101. Obtain a historical behavior sequence of a target user, and divide the historical behavior sequence into a long-term behavior sequence and a short-term behavior sequence.

[0059] The target user may be a user to whom recommendation objects are to be pushed, wherein the recommendation objects to be pushed may be common recommendable objects such as movies, TV, web pages, advertisements, and product purchase links. Acquiring the historical behavior sequence of the target user may be specifically obtaining the access log of the target user, and determining the historical behavior sequence by using the access objects and access time recorded in the access log. For example, if music recommendation is to be performed, by obtaining the access log of...

Embodiment 2

[0137]Corresponding to the above method embodiment, the embodiment of the present invention also provides a sequence recommendation device based on the self-attention mechanism, the sequence recommendation device based on the self-attention mechanism described below is the same as the sequence recommendation device based on the self-attention mechanism described above The sequence recommendation methods can be referred to in correspondence with each other.

[0138] see Figure 5 As shown, the device includes the following modules:

[0139] The sequence processing module 101 is used to obtain the historical behavior sequence of the target user, and divide the historical behavior sequence into a long-term behavior sequence and a short-term behavior sequence;

[0140] The recommendation information module 102 is used to input the long-term behavior sequence and the short-term behavior sequence into the recommendation model for recommendation learning, and obtain the target recom...

Embodiment 3

[0154] Corresponding to the above method embodiment, the embodiment of the present invention also provides a sequence recommendation device based on the self-attention mechanism. The sequence recommendation device based on the self-attention mechanism described below is the same as the one based on the self-attention mechanism described above. The sequential recommendation methods of the attention mechanism can be referred to each other.

[0155] see Figure 6 As shown, the sequence recommendation device based on the self-attention mechanism includes:

[0156] memory D1 for storing computer programs;

[0157] The processor D2 is configured to implement the steps of the sequence recommendation method based on the self-attention mechanism in the above method embodiment when executing the computer program.

[0158] Specifically, please refer to Figure 7 , Figure 7 A specific structural diagram of a sequence recommendation device based on a self-attention mechanism provided ...

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 sequence recommendation method based on a self-attention mechanism, and the method comprises the following steps: obtaining a historical behavior sequence of a target user, and dividing the historical behavior sequence into a long-term behavior sequence and a short-term behavior sequence; inputting the long-term behavior sequence and the short-term behavior sequence intoa recommendation model for recommendation learning to obtain a target recommendation object, wherein the recommendation model is a multi-layer self-attention network sequence recommendation model integrating long-term and short-term preferences of the user; and pushing the target recommendation object to the target user. According to the method, the long-term preference and the short-term demand of the target user can be learned, so that the target recommendation object better conforms to the time-based change preference of the target user, the recommendation is more accurate, and the user experience can be improved. The invention further discloses a sequence recommendation device and equipment based on the self-attention mechanism and a readable storage medium which have corresponding technical effects.

Description

technical field [0001] The present invention relates to the technical field of information services, in particular to a sequence recommendation method, device, equipment and readable storage medium based on a self-attention mechanism. Background technique [0002] With the continuous development of mobile Internet technology, sequence recommendation has become more and more extensive and multifaceted in many applications. Examples include music list recommendation, product purchase recommendation, and advertisement click prediction. In such applications, a user's behavior is modeled as a time-ordered behavior sequence, and the user's subsequent behavior is influenced by his previous historical behavior. Therefore, it is particularly important to model complex sequential interactions between users and items to generate personalized recommendations. [0003] The model based on Markov Chain (MC) is the earliest sequence recommendation method, which assumes that the user's nex...

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): G06F16/9535
CPCG06F16/9535
Inventor 鲜学丰张婷婷赵朋朋
Owner SUZHOU VOCATIONAL UNIV
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