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

Improved collaborative filtering recommendation method based on user characteristics

A collaborative filtering recommendation and user feature technology, applied in the Internet field, can solve the problems of low accuracy of information recommendation and failure to meet various needs, and achieve the effect of improving recommendation quality, small error, and accurate user similarity

Inactive Publication Date: 2017-11-07
TIANJIN UNIV
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In the traditional user-based collaborative filtering algorithm, the calculation of user similarity only uses the common rating of users, ignoring many other problems, such as: the problem of user value scale, the utilization of user feature information, and the evaluation of items that are not shared by users. considerations, etc., resulting in low accuracy of information recommendation, unable to meet various needs in practical applications

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
  • Improved collaborative filtering recommendation method based on user characteristics
  • Improved collaborative filtering recommendation method based on user characteristics
  • Improved collaborative filtering recommendation method based on user characteristics

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] On the basis of the traditional user-based collaborative filtering algorithm, the embodiment of the present invention normalizes the user rating data, adopts the improved Jaccard similarity coefficient method as the user rating similarity measurement method, and adds the user rating data For the consideration of feature information, the linear combination of user attribute similarity and user rating similarity is used as the end user similarity, and then the end user similarity is used to perform neighbor calculation to generate a recommendation list, see figure 1 , the method includes the following steps:

[0034] 101: Obtain the average rating of all users, correct the original user rating range according to the average rating of all users, and use the corrected user rating interval mean and all user average ratings to correct the original user rating to obtain normalization Processed user ratings;

[0035] Through the processing of step 101 above, the average rating...

Embodiment 2

[0048] The scheme in embodiment 1 is further introduced below in conjunction with specific calculation formulas and examples, see the following description for details:

[0049] 201: Normalize the user rating data;

[0050] First traverse the historical rating records of each user to get the average rating of each user:

[0051]

[0052] Among them, R ui Indicates user u's rating on item i; n is the number of items rated by user u.

[0053] Reset the user's rating range to the following formula:

[0054]

[0055]Among them, m represents the number of all users; min(Ru1, Ru2,...,Run) represents the lowest score in user u's scoring record, max(Ru1, Ru2,...,Run) represents the highest score in user u's scoring record .

[0056] After the above processing, the average value of the user rating interval is k, and the value of k is as follows:

[0057]

[0058] The user rating after correcting the rating interval should be calculated according to the following formula: ...

Embodiment 3

[0108] Combined with the specific experimental data, Figure 2-Figure 4 The scheme in embodiment 1 and 2 is carried out feasibility verification, see the following description for details:

[0109] (1) Normalization of user ratings:

[0110] Firstly, the user evaluation matrix is ​​generated according to the user's historical rating records, and the matrix form is as follows: figure 2 shown. Every non-zero value in the matrix is ​​traversed and normalized to obtain a new user rating matrix.

[0111] (2) User similarity calculation:

[0112] Traverse all users in the user evaluation matrix except user u, and calculate the pairwise similarity between them and user u. The calculation process is as image 3 As shown, firstly, according to the rating records, the improved Jaccard similarity coefficient method is used to calculate the rating similarity between user u and other users, and then compare the gender, age, and occupational characteristics information of user u and 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 an improved collaborative filtering recommendation method based on user characteristics. The method comprises the following steps that according to the mean opinion score of all users, an original user opinion score range is amended, according to the mean value of the modified user opinion score range and the mean opinion score of all users, original user opinion scores are amended, and after normalization processing, user opinion scores are obtained; according to the user opinion scores obtained after normalization processing, adjustment and normalization processing are conducted on the mean value of score difference values, through the combination with an original Jaccard similarity coefficient, the improved Jaccard similarity coefficient is obtained, and the similarity of the user opinion scores is obtained; according to the gender, age and job characteristic information of users, the similarity of user attributes is calculated; the similarity of the user opinion scores and the similarity of user attributes are combined to serve as the final user similarity, and nearest neighbor computing is conducted, and a recommendation list is generated. The method improves the recommendation quality of the traditional user-based collaborative filtering algorithm and reduces the influence of the data sparseness problem to a certain extent.

Description

technical field [0001] The invention relates to the Internet field, in particular to an improved collaborative filtering recommendation method based on user characteristics. Background technique [0002] With the rapid development of the Internet, it is more and more convenient to obtain information, but in the face of such a huge amount of information, it is impossible to browse and make full use of it by manpower alone, so the research on personalized recommendation methods emerges as the times require. [0003] Collaborative filtering recommendation algorithm is the earliest recommendation algorithm, and its branch user-based collaborative filtering algorithm is the most common collaborative filtering algorithm, which is widely used because of its high accuracy. [0004] In the process of realizing the present invention, the inventor finds that at least the following disadvantages and deficiencies exist in the prior art: [0005] In the traditional user-based collaborati...

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
IPC IPC(8): G06F17/30G06K9/62
CPCG06F16/9535G06F18/22
Inventor 张蕾曹艺迪
Owner TIANJIN 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