An item recommendation method based on collaborative filtering

A recommendation method and collaborative filtering technology, applied in the field of recommendation systems, can solve problems such as unreasonableness, and achieve the effect of improving profits, efficient intelligent information filtering technology, and helping products expand boundaries

Active Publication Date: 2022-02-01
东北大学秦皇岛分校
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although it has superior performance, it assumes that all historically interacted items of a user contribute equally to the representation of user preference, which is clearly unreasonable

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
  • An item recommendation method based on collaborative filtering
  • An item recommendation method based on collaborative filtering
  • An item recommendation method based on collaborative filtering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to make the purpose, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. The specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0036] An item recommendation method based on collaborative filtering, comprising the following steps:

[0037] Step 1: If figure 1 As shown, when representing a user, Multi-hot encoding is used to represent u by using all items that user u has interacted with in the case of implicit feedback. In this case, the user’s Multi-hot encoding passes through the embedding layer and generates a set of vectors , where each vector represents a historical item associated with the user, and the target item to be predicted uses one-hot encoding to obtain its embedding vector through the embedding layer. Calculate the prediction...

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 present invention provides an item recommendation method based on collaborative filtering, which relates to the technical field of recommendation systems. The present invention introduces special dynamic weights to better predict user u's preference for item i. This dynamic weight will use the attention mechanism to Estimate, evaluate the recommendation performance through recall and precision, improve the effectiveness and recommendation quality of the recommendation system, and confirm that the attention mechanism is helpful for estimating the contribution of historical items that the user has interacted with to the user's preference representation , making the personalized recommendation more accurate. Using dot multiplication attention and self-attention to calculate the attention score respectively, and achieved remarkable results. At the same time, the transformer model was combined with the recommendation algorithm and compared with the conventional embedding model, showing the improvement of the recommendation effect.

Description

technical field [0001] The invention relates to the technical field of recommendation systems, in particular to an item recommendation method based on collaborative filtering. Background technique [0002] Collaborative Filtering (CF for short) is the earliest and well-known recommendation algorithm. The main functions are prediction and recommendation, which are not only deeply studied in academia, but also widely used in the industry. The algorithm discovers the user's preferences by mining the user's historical behavior data, and recommends items with similar tastes to users based on different preferences. Collaborative filtering recommendation algorithms are mainly divided into two categories, namely user-based collaborative filtering algorithm (User-based Collaborative Filtering, referred to as UserCF) and item-based collaborative filtering algorithm (Item-based Collaborative Filtering referred to as ItemCF). To put it simply: people of a feather flock together and th...

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 Patents(China)
IPC IPC(8): G06F16/9536
CPCG06F16/9536
Inventor 郑莹吕艳霞
Owner 东北大学秦皇岛分校
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