Book retrieval method based on feature extraction

A feature extraction and book technology, applied in the field of network communication, can solve problems such as unfavorable readers' selection, inability to meet user reading needs, time cost and human input, etc., to increase reading experience, save frequent queries, and fast processing speed. Effect

Active Publication Date: 2016-11-16
KUNMING UNIV OF SCI & TECH
View PDF1 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the common book retrieval methods often use books to be displayed in separate libraries, librarians to classify books regularly, and bookstore salespersons to explain books manually. This is not only in terms of efficiency but also not conducive to readers’ selection. The time cost and manpower input are large. Meet the reading needs of users

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
  • Book retrieval method based on feature extraction
  • Book retrieval method based on feature extraction
  • Book retrieval method based on feature extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] Embodiment 1: as figure 1 Shown:

[0027] Step1: Establish a book information library: collect data on the book information in the library, extract book label information, including book title, book field and book publishing information, and code and identify the collected books according to [field-name- Publisher-Publication Date], such as [Economic Management-Crazy Economics-Nanhai Publishing House-September 2013].

[0028] Step2: Establish a clustered book information library:

[0029] Step2.1: Bookmark clustering:

[0030] 1. First, integrate the bookmark information stored in sequence according to the code, and use the Spearman rank correlation coefficient method to establish the correlation coefficient between the book label sequence information, and define the calculation formula of the clustering reference coefficient as:

[0031] r s = 1 - 6 Σd ...

Embodiment 2

[0042] Embodiment 2: as figure 1 As shown, a book retrieval method based on feature extraction, firstly collects data for book information in the library, extracts book label information, codes and marks, builds a book information database, and stores book information; secondly, collects books based on book label information elements category, classify the clustered books as the original library source for retrieving books, and combine the original book tags to reorganize the book features, extract new feature phrases of each category of books, and use them as the clustered book information library; then, extract the user The frequency of accessing books falling into a certain category in the clustered library information base is used to establish a user access model to form a user reading pattern label as a user feature label value; finally, a matching correlation model is established to provide a list of retrieved books for successful matching users.

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 relates to a book retrieval method based on feature extraction, pertaining to the technical field of network communication. The method comprises following steps: firstly, collecting book information of a book library, extracting label information of books, coding and establishing a book information library to store book information; secondly, gathering books according to elements of book label information, coding books gathered as an original library source for book retrieval and combining with book original labels for book feature reconstruction, and extracting new feature words of a wide range of books as a collection book information library; then, extracting frequency of types of books visited by users in collection book information library, establishing a users' visit model to form users' reading mode labels as users' feature label values; and finally, creating a matching relevancy model for providing retrieval book lists for users who successfully match. The book retrieval method based on feature extraction is capable of retrieving visit features of users in a real-time manner so that user's visit demands can be precisely satisfied.

Description

technical field [0001] The invention relates to a book retrieval method based on feature extraction, which belongs to the technical field of network communication. Background technique [0002] With the rapid increase in the number of books and the promotion of reading books by relevant departments, more people have begun to re-open the reading experience of book knowledge. However, due to the various types of books and the large number of them, and they are all disorderly displayed in the book collection or library, it virtually increases the difficulty for people to consult books and affects people's reading experience. How to make people read books more conveniently and find the types of books they need more quickly in the fast-paced life is the core issue of book retrieval nowadays. However, the common book retrieval methods often use books to be displayed in separate libraries, librarians to classify books regularly, and bookstore salespersons to explain books manually...

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): G06F17/30G06K9/20G06K9/62
CPCG06F16/242G06V10/225G06F18/2321G06F18/22
Inventor 龙华刘永召
Owner KUNMING UNIV OF SCI & TECH
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