Book retrieval recommendation method based on semantic information

A technology of semantic information and recommendation methods, applied in the field of book information management, can solve problems that affect users, cannot fundamentally solve the problems of keyword semantic multiplicity, time-consuming, etc., to ensure correctness and realize personalized recommended retrieval The effect of serving and optimizing keyword weight

Inactive Publication Date: 2019-11-15
XI'AN POLYTECHNIC UNIVERSITY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the current book retrieval model, users often spend a long time browsing the results one by one to determine whether they are the information they need. In some cases, users need to search multiple times to find the information they need, which brings great inconvenience to the user. , time-consuming, affecting the user's collection and learning of the required data, and cannot fundamentally solve the characteristics of keyword semantic multiplicity and sorting disorder

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 recommendation method based on semantic information
  • Book retrieval recommendation method based on semantic information
  • Book retrieval recommendation method based on semantic information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0068] The reader's borrowing data of Xi'an Polytechnic University Library is selected as the research object, and each reader's borrowing has a corresponding input data record. The present invention obtains the retrieval results of the information retrieval model based on semantic information fusion for six targeted user retrieval sentences. Match the search results with the search model based on keywords, and then calculate the relative accuracy of the search results. Table 1 shows the representative retrieval sentences and the data of the number of expanded words after blurring the keywords.

[0069] Table 1 Representative search sentences

[0070]

[0071]

[0072] For the fuzzified keywords, select the degree of emphasis on multiple keyword semantic information requirements For the value of the weight of the importance of multiple keyword semantic information requirements in step 5 (1), refer to Professor Thomas Sety for the weight a ij The proposed scale of 1 to 9...

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 book retrieval recommendation method based on semantic information. The book retrieval recommendation method comprises the following steps that 1, a user inputs retrieval information; step 2, the input retrieval information is processed and an initial retrieval word sequence is formed; step 3, semantic extension is performed on the initial search word sequence; step 4, semantic quantization and fuzzification are performed on the initial search word sequence; step 5, keyword weight calculation is carried out; and step 6, the matching degree of the initial search word input by the user and the book information in the system is calculated by using a semantic information fusion algorithm to obtain a book name required by the user. The invention discloses a book retrieval recommendation method based on semantic information, which reflects the intelligent level of a retrieval system and improves the book retrieval efficiency and accuracy.

Description

technical field [0001] The invention belongs to the technical field of book information management, and in particular relates to a book retrieval and recommendation method based on semantic information. Background technique [0002] A recommendation system is the process of using an e-commerce website to provide decision support and information services to customers. Recommender systems are currently widely used in many fields, and the academic community also has a high degree of research enthusiasm for recommender systems. With the deepening of research on recommender systems and the increasing demand for book retrieval, the use of recommender systems in the field of books to solve related problems has become become a research hotspot in recent years. Book retrieval activities have a long history of development. Simply speaking, book retrieval can be divided into broad book retrieval technology and narrow book retrieval technology. The generalized book retrieval technolog...

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): G06Q30/06G06F16/332G06F17/27
CPCG06Q30/0631G06F16/3322
Inventor 宋爱香马冲王思敏
Owner XI'AN POLYTECHNIC UNIVERSITY
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