Session recommendation method and system based on user interests

A technology of user interests and recommendation methods, which is applied in the field of conversational recommendation methods and systems based on user interests, can solve the problems of not fully considering the improvement of the recommendation effect of user preferences, and the inability to fully capture the conversion relationship between items and items, so as to achieve improved recommendation effect of effect

Pending Publication Date: 2020-12-22
QILU UNIV OF TECH
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The inventors found that most of the traditional session-based recommendation methods model the session as a sequence, which cannot fully capture the complex conversion relationship between items in the session
In addition, the traditional session-based recommendation method does not fully consider the user preference to improve the recommendation effect.

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 and system based on user interests
  • Session recommendation method and system based on user interests
  • Session recommendation method and system based on user interests

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] This embodiment provides a session recommendation method based on user interests;

[0038] Such as figure 1 As shown, the session recommendation method based on user interests includes:

[0039] S101: Construct a weighted directed conversation graph according to the acquired time series of items clicked by the user; obtain the final vector representation of each node in the weighted directed conversation graph;

[0040] S102: According to the final vector representation of each node in the weighted directed session graph, obtain an item embedding vector added with location information;

[0041] S103: Input the item embedding vector added with position information into the Transformer layer, and output the updated item embedding vector added with position information;

[0042] S104: Extract long-term interest representation and current preference representation from the updated item embedding vector added with location information, and obtain the final session embeddin...

Embodiment 2

[0138] This embodiment provides a session recommendation system based on user interests;

[0139] A conversational recommendation system based on user interests, including:

[0140] The session graph construction module is configured to: construct a weighted directed session graph according to the acquired item time series that the user has clicked; obtain the final vector representation of each node in the weighted directed session graph;

[0141] An embedding vector obtaining module, which is configured to: obtain an item embedding vector added with position information according to the final vector representation of each node in the weighted directed session graph;

[0142] An embedding vector updating module, which is configured to: input the item embedding vector adding position information into the Transformer layer, and output the updated item embedding vector adding position information;

[0143] The user preference extraction module is configured to: extract long-ter...

Embodiment 3

[0149] This embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein, the processor is connected to the memory, and the one or more computer programs are programmed Stored in the memory, when the electronic device is running, the processor executes one or more computer programs stored in the memory, so that the electronic device executes the method described in Embodiment 1 above.

[0150] It should be understood that in this embodiment, the processor can be a central processing unit CPU, and the processor can also be other general-purpose processors, digital signal processors DSP, application specific integrated circuits ASIC, off-the-shelf programmable gate array FPGA or other programmable logic devices , discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor, or the processor may be any conventional processor, o...

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 session recommendation method and system based on user interests, and the method comprises the steps: constructing a weighted directed session graph according to an obtainedarticle time sequence clicked by a user; obtaining a final vector representation of each node in the weighted directed session graph; according to the final vector representation of each node in the weighted directed session graph, obtaining an article embedding vector added with the position information; inputting the article embedding vector added with the position information into a Transformerlayer, and outputting the updated article embedding vector added with the position information; extracting a long-term interest representation and a current preference representation from the updatedarticle embedding vector added with the position information to obtain a final session embedding vector; and recommending candidate articles based on the final session embedding vector.

Description

technical field [0001] The present application relates to the technical field of session recommendation, in particular to a session recommendation method and system based on user interests. Background technique [0002] The statements in this section merely mention the background art related to this application, and do not necessarily constitute the prior art. [0003] Session-based recommendation methods have only become popular in recent years. This application found that the current mainstream method is to use recurrent neural networks and Markov chains. For example, combining the cyclic neural network with the session recommendation, consider the time change of user behavior. Another example is the use of gated recurrent units to redefine the classic recurrent neural network. Another widely used method is NARM, which consists of a global and local recurrent neural network recommender, simultaneously capturing users' sequential behavior and main purpose. On this basis,...

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): G06F16/9535G06N3/04G06N3/08
CPCG06F16/9535G06N3/084G06N3/048G06N3/045
Inventor 杨振宇王皓
Owner QILU UNIV OF TECH
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