Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Collaborative filtering recommendation method and system based on time-efficient neighbor credible selection

A collaborative filtering recommendation and time-effective technology, which is applied in digital data information retrieval, instruments, calculations, etc., can solve user reliability fluctuations, recommendation system anti-attack, difficulty in guaranteeing recommendation stability and credibility, and recommendation result interference or misleading problems, to achieve the effect of improving the degree of confidence and alleviating the problem of unreliable selection of neighbors

Pending Publication Date: 2022-08-05
NANJING AUDIT UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] To sum up, the existing technology fails to deal with the two problems that may interfere or mislead the recommendation results, which may interfere with or mislead the recommendation results, such as abnormal changes in user interests and fluctuations in user reliability during recommendation, making the recommendation system more resistant to attack and recommendation. Stability and reliability are difficult to guarantee

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 and system based on time-efficient neighbor credible selection
  • Collaborative filtering recommendation method and system based on time-efficient neighbor credible selection
  • Collaborative filtering recommendation method and system based on time-efficient neighbor credible selection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] Embodiment 1: The concrete steps of this embodiment are as follows:

[0080] Step S1, the aging neighbor screening unit first uses the aging weight function w(t) to calculate the aging weight of the target user's neighbors on the common scoring item, and then calculates the interest similarity calculation model based on the Pearson correlation coefficient that includes the aging weight. The aging similarity between each neighbor and the target user is obtained, and finally the aging neighbors are dynamically screened for the target user according to the aging similarity. The specific process is:

[0081] Step S1.1, calculate the target user u through the similarity of interest a with its neighbor user u i ∈NS(u a ) of the time-effect similarity TSD(u a ,u i );

[0082]

[0083] In formula (1), r ak and r ik respectively u a and u i for item i k ∈CRIS(u a ,u i ) rating; means u a In its corresponding scoring item RIS(u a ), the mean of ratings over al...

Embodiment 2

[0124] Embodiment 2: Table 1 is the target user Mike and his neighbor u in this embodiment 1 -u 7 in item i 1 -i 5 On the scoring and scoring (normalized) time, the similarity between Mike and seven neighbors was calculated using traditional PCC and PCC with aging weights, respectively.

[0125] (1) The results obtained by the former are {0.4852, 0.3225, 0.0369, 0.0678, 0.4111, 0.3025, 0.4135} (Mike similarity threshold 0.2914), and the filtered Mike nearest neighbor set is {u 1 ,u 2 ,u 5 ,u 6 ,u 7 };

[0126] (2) The results obtained by the latter are {0.5064, 0.2965, 0.0846, 0.0791, 0.4090, 0.3001, 0.4472} (Mike aging similarity threshold 0.3033), and the filtered Mike aging neighbor set is {u 1 ,u 5 ,u 7 }.

[0127] with u 6 For example, its sum u 5 Although it is consistent with Mike in the score value, because the time interval between its score and Mike's score is much larger than u 5 The time distance from Mike causes it to be excluded from Mike's neighbor...

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 and system based on time-efficient neighbor credible selection, the score of a target user on a target project is predicted according to a score matrix, and the method specifically comprises the steps of time-efficient neighbor screening, credible neighbor selection and score prediction. According to the collaborative filtering recommendation method based on time-dependent neighbor credible selection, two time-varying factors of user interest abnormal transition and recommendation reliability fluctuation are fully considered, and recommendation to the target user is completed by sequentially utilizing three steps of time-dependent neighbor screening, credible neighbor selection and target user score prediction; and the problems of low collaborative filtering recommendation precision, poor stability and weak user general picture injection attack resistance under the condition of data sparsity are relieved.

Description

technical field [0001] The invention relates to information recommendation technology, in particular to a collaborative filtering recommendation method and system based on time-sensitive neighbor trusted selection. Background technique [0002] In recent years, with the large-scale migration of social production and people's life to the information space, the phenomenon of information lost caused by information overload has become increasingly serious. In order to help people filter out useful information from the rapidly expanding data, recommender systems emerge as the times require. At present, technologies such as content-based recommendation, collaborative filtering recommendation, association rule-based recommendation, utility-based recommendation, knowledge-based recommendation, and hybrid recommendation have been widely used in various e-commerce platforms to improve user stickiness and reduce service bounce rates. , Help users build an information cocoon room. Acc...

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): G06F16/9536
CPCG06F16/9536
Inventor 韩志耕范远哲陈耿张晓东伍之昂周婷吴慧玲
Owner NANJING AUDIT UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com