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
CN112115352APending Publication Date: 2020-12-22QILU UNIV OF TECH
4 Cites 8 Cited by

Patent Information

Authority / Receiving Office
CN ยท China
Patent Type
Applications(China)
Current Assignee / Owner
QILU UNIV OF TECH
Publication Date
2020-12-22

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

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.
Need to check novelty before this filing date? Find Prior Art

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