A method for recommending scientific literature based on author frequent patterns
A frequent pattern and recommendation method technology, applied in the field of recommendation system, can solve the problems of increasing space overhead and maintenance cost
Inactive Publication Date: 2019-04-05
BEIJING UNIV OF TECH
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
If you directly use the author item set to calculate the frequent pattern, there will be some problems. For example, there are three author item sets: {Li Qi, Wang Lei, Li Long}, {Li Qi, Wang Lei, Song Jia} and {Wang Lei, Yang Zhi, Zhang Min }, when the confidence level is set to 2, we can get the frequent item {Li Qi, Wang Lei}. If we want to get the documents corresponding to this item set, we have to scan all the documents, although some indexing techniques can be used to reduce Scan time complexity
But it will also increase the cost of space overhead and maintenance
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0033] Step 1. Use 10 million document collections grabbed from the Internet as the data set of this invention. It is parsed into structured data and stored in the database table D. The table fields are: ID (unique number), author (author of the document), keyword (keyword) and title (name of the document) and other fields (table data) As shown in Table 1). Create a T_fp_authors_papers table in the database to store the author's frequent item set and its corresponding document ID set. The table fields are: ID (table unique number), authors (author frequent item set) and papers (document unique number ID set, where each Use "," as the separator for each number);
[0034] Table 1 Data format in table D
[0035] ID
author
keyword
title
...
100
Li Ke, Wang Hong, Liu Gang
...
...
...
101
Li Ke, Song Jia, Liu Gang, Li Qi
...
...
...
102
Liu Gang, Wang Hong, Li Qi
...
...
...
103
Li Ke, Wang Hong, Song Jia, Liu Dong
...
...
...
[0036] Set the minimum support to n, n is usually 3, and c...
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
Login to View More Abstract
The invention discloses a scientific and technical literature recommendation method based on an author frequent pattern. The scientific and technical literature recommendation method comprises the following steps: adding a function of processing literature ID (Identity) (the unique number of the literature) into a Fp-growth algorithm, constructing the author frequent pattern, a literature set corresponding to the author frequent pattern, literature published by the author and a literature set corresponding to a keyword, and removing the literature browsed by a user to construct a literature recommendation candidate set. The invention also constructs a scoring system which sorts the candidate sets according to the descending order of the scores to recommend ten literatures with the highest score to the user.
Description
Technical field [0001] The invention belongs to the field of recommendation systems and relates to a method for recommending scientific and technological documents based on frequent patterns of authors. Background technique [0002] The emergence and popularization of the Internet has brought a lot of information to users, but with the rapid development of the Internet, the amount of information on the Internet has increased significantly, making users unable to obtain the part that is really useful for them when facing a large amount of information. Information, the efficiency of the use of information is reduced, which is the so-called information overload problem. A very potential way to solve the problem of information overload is the recommendation system, which is a personalized information recommendation system that recommends information and products that interest users to users based on their information needs and interests. [0003] The initial motivation of association ...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/9535
CPCG06F16/951
Inventor 李玉鑑杨凯文
Owner BEIJING UNIV OF TECH