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

Session recommendation method, session recommendation device and storage medium

A recommendation method and node technology, applied in the fields of instrumentation, computing, electrical and digital data processing, etc., can solve problems such as over-smoothing, repetition and redundancy of feature information, and difficulty in capturing users' long-term interests, so as to improve adaptability and increase conversion. , to correct the effect of session representation

Pending Publication Date: 2022-02-08
SHENZHEN UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Conversational recommendation is a challenging task. Most of the existing techniques only consider inferring time preferences from sequences. Such item sequences may not fully capture the complex transition relationship between items. In addition, they are used to model item characteristics. The network structure is not enough to effectively model items, and it is difficult to capture long-term interest of users
Although some global graph-based graph recommendation models have been proposed recently, they still adopt and session Figure 1 Consistent or similar models essentially learn the features based on the conversation flow, which can easily lead to over-smoothing, resulting in repetition and redundancy of feature information

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
  • Session recommendation method, session recommendation device and storage medium
  • Session recommendation method, session recommendation device and storage medium
  • Session recommendation method, session recommendation device and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The following will clearly and completely describe the technical solutions in the embodiments of the application with reference to the drawings in the embodiments of the application. Apparently, the described embodiments are only some of the embodiments of the application, not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts belong to the scope of protection of this application.

[0032] The term "and / or" appearing in this application may be an association relationship describing associated objects, indicating that there may be three relationships, for example, A and / or B may indicate: A exists alone, and A and B exist simultaneously , there are three cases of B alone. In addition, the character " / " in this application generally indicates that the contextual objects are an "or" relationship.

[0033] The terms "first", "second" and the like in the specification and clai...

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 provides a session recommendation method, session recommendation equipment and a storage medium, the session recommendation method comprises the following steps: determining node features, the nodes being nodes in a global item relation network; constructing a hierarchical attention network according to the node features, wherein the hierarchical attention network is used for storing the node features; reconstructing the hierarchical attention network based on the virtual connection to obtain a target hierarchical attention network; generating a target convolutional network according to the node features; and predicting a user behavior according to the target hierarchical attention network and the target convolutional network. For the user data appearing in the form of the session, the user preference and the project general attribute in the session are effectively considered, and the session representation with self-feedback regulation is generated, so that a better recommendation effect is obtained.

Description

technical field [0001] The invention relates to the field of artificial intelligence, in particular to a conversation recommendation method, conversation recommendation equipment and a storage medium. Background technique [0002] Conversational recommendation method is an effective means to solve information overload, aiming to capture users' interests to provide personalized recommendations. In recent years, the research and application of session-based recommendation has received more and more attention. Research on how to use user session information to further improve recommendation accuracy and user satisfaction has become the main task of session-based recommendation systems. [0003] Conversational recommendation is a challenging task. Most of the existing techniques only consider inferring time preferences from sequences. Such item sequences may not fully capture the complex transition relationship between items. In addition, they are used to model item characteris...

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): G06F16/332G06F16/9535
CPCG06F16/3329G06F16/9535
Inventor 曹文明刘伊善
Owner SHENZHEN UNIV