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
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
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.
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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