Personalized book recommendation method based on combinational algorithm

A technology of combining algorithms and recommendation methods, applied in the field of computer information, it can solve the problems of inaccurate data, user preference errors, insufficient historical data information, etc., and achieve the effect of easy promotion, high recommendation accuracy and recall rate.

Active Publication Date: 2018-04-20
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF7 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method has the following shortcomings: the existing system mainly reverses the user identity through the age, gender, occupational characteristics, product brand and mobile phone type of the registered user. The reason is that there are many inaccuracies in the data, which leads to a very low accuracy rate of user identity category determination, which in turn causes a large error in the inference of user preference, which affects the effect of book recommendation
However, for users with fewer access to the reading platform system, there may not be enough historical data information; and the current system lacks a reliable basis for judging user identities due to various restrictions, and the accuracy of user category judgment is low
Therefore, there is a large error in the inference of user preferences.

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
  • Personalized book recommendation method based on combinational algorithm
  • Personalized book recommendation method based on combinational algorithm
  • Personalized book recommendation method based on combinational algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0041] The technical solution in this embodiment will be clearly and completely described below in conjunction with the embodiment of the present invention. Apparently, the described embodiment is only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0042] A method for recommending personalized books based on a combined algorithm, comprising the following steps:

[0043] S1: Extract keywords from the content information such as the title and introduction of the new book, and then obtain the feature vector of the book, and use these keywords to mark the book.

[0044] S2: Obtain the user's feature vector according to the feature vector of the books browsed or downloaded by the user, and then obtain the user's rating value for a new ...

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 personalized book recommendation method based on a combinational algorithm and relates to the field of computer information. The method comprises the steps that keyword extraction is performed on content information of books, and feature vectors of the books are solved; a score of a certain new book by a user is solved; ''a user behavior inverted list and query indexes''and ''a book behavior inverted list and query indexes'' are generated; a similarity file and query indexes, including similar user indexes and query indexes and similar book indexes and query indexes,are generated; and a book recommendation index to the user is calculated according to the similar user indexes and query indexes and the similar book indexes and query indexes. Through the method, the problem that an existing book recommendation method has a large error in inference of user preferences, and consequently a good book recommendation effect cannot be achieved is solved.

Description

technical field [0001] The present invention relates to the field of computer information suitable for recommending books according to user preferences, in particular to a method for recommending personalized books based on a combined algorithm. Background technique [0002] There are many methods for recommending e-books to users in the prior art. The first method is to infer the user's reading preference based on the user's past reading history data, and then recommend corresponding e-books to the user according to the inferred reading preference. However, in this method, there are certain deficiencies in the inference of users’ reading preferences, mainly because: the categories of books provided by the reading platform are unevenly distributed, and there are many original books, which are usually mainly concentrated in categories such as romance and time travel; At the same time, since the main user groups of mobile phone reading users are students, migrant workers, and ...

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): G06F17/30
CPCG06F16/2462G06F16/9535
Inventor 高建彬单良
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
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