Collaborative filtering recommendation method based on time correlation and coverage of items

A collaborative filtering recommendation and time correlation technology, applied in the field of recommendation, can solve the problem of lack of weight, and achieve the effect of improving classification accuracy, reducing gaps, and improving prediction accuracy.

Active Publication Date: 2021-09-24
LIAONING NORMAL UNIVERSITY
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the traditional item-based collaborative filtering algorithm predicts the score, item a and item b get the same predicted score, and do not have a higher weight

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
  • Collaborative filtering recommendation method based on time correlation and coverage of items
  • Collaborative filtering recommendation method based on time correlation and coverage of items
  • Collaborative filtering recommendation method based on time correlation and coverage of items

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The present invention provides a collaborative filtering recommendation method based on the temporal relevance and coverage of items, such as figure 1 As shown, follow the steps below:

[0037] Step 1. Statistically obtain the two-dimensional table of items rated by users:

[0038] Let U and I denote the user set and item set respectively; R∪{*} denotes the rating set, where (*) means that the item has not been rated by the user; T∪{ο} denotes the time set when the item is rated by the user, where (ο ) indicates that the scoring time is empty; r u,x ∈R∪{*} represents user u's rating on item x; t u,x ∈T∪{ο} represents the rating time of user u on item x; Indicates the average value of item x rated by users;

[0039] Specifically, user set U={user 1, user 2, user 3, target user}, item set I={item 1, item 2, item 3, item 4, item 5, target item 1, target item 2}, scoring The value range of R is [1,5], the value range of the scoring time T is from June 2016 to June 201...

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 collaborative filtering recommendation method based on the temporal correlation and coverage of items, proposes a temporal correlation function, and applies it to the calculation of similarity between items, that is, the temporal correlation function can be applied to collaboration to the greatest extent possible. In the filtering algorithm, the weight of the items that have been rated for a long time can be effectively reduced, the relationship between the items can be more accurately reflected, the gap between the predicted score and the actual score can be reduced, and the prediction accuracy can be improved; The coverage function of the relationship between the item and the target user's hobby, and it is applied to calculate the predicted score of the item, so that when the item calculates the predicted score, its neighboring items will get a higher weight, so that the item has a higher The predicted score is easier to be recommended to the target user, which effectively improves the classification accuracy.

Description

technical field [0001] The present invention relates to the technical field of recommendation, in particular to a collaborative filtering recommendation method based on time correlation and coverage of items that can simultaneously improve prediction accuracy and classification accuracy. Background technique [0002] The recommendation system can intelligently perceive the user's interests or needs through the user's personal information, realize high-quality recommendation of information, and effectively solve the problem of "information overload". The item-based collaborative filtering algorithm has become one of the most successful methods in the field of recommendation technology due to its good scalability, such as Amazon and Taobao. The item-based collaborative filtering algorithm has two core steps: item similarity calculation and item prediction scoring. [0003] In the traditional item-based collaborative filtering algorithm, all items have the same weight in the t...

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): G06Q30/06
CPCG06Q30/0631
Inventor 张志鹏任永功邹丽崔晓松
Owner LIAONING NORMAL UNIVERSITY
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