A user portrait model construction method for university libraries based on multi-view dichotomous k-means

A library, multi-perspective technology, applied in character and pattern recognition, structured data retrieval, special data processing applications, etc., can solve the problems of lack of user portrait research and incomplete portrait.

Active Publication Date: 2021-12-17
ZHEJIANG UNIV OF TECH
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although user portraits have become a hot topic at present, there is still a lack of research on user portraits for library readers
Yao Yuan et al. used the vector space model to integrate the user portrait hierarchical model and temporal context factors to construct readers' academic portraits, but only considered retrieval and academic paper retrieval, and the user portraits were not comprehensive enough; Hu Changping combined basic user information and shared space By using the structural equation modeling method to construct readers' portraits; Kovacevic et al. proposed digital library recommendation services by mining and analyzing readers' information and search records, and at the same time used predictive classification to gather readers with the same hobbies together, thus forming Reader portraits, and use this to provide readers with personalized services

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
  • A user portrait model construction method for university libraries based on multi-view dichotomous k-means
  • A user portrait model construction method for university libraries based on multi-view dichotomous k-means
  • A user portrait model construction method for university libraries based on multi-view dichotomous k-means

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] The present invention will be further described below in conjunction with the accompanying drawings.

[0057] refer to Figure 1 to Figure 6 , a method for constructing a user portrait model of a university library based on multi-view dichotomous k-means, including the following steps:

[0058] The first step, raw data collection and processing

[0059] The library user portrait is to dig out the hidden information from the massive behavioral data as much as possible, so as to outline the overall picture of the user's information. User behavior data in academic libraries come from many different databases. The data collected in this study are reader information table (reader_info), electronic resource usage table (electronic_resources), book lending table (book_lend), library collection table (book_info), library entry data table (gate_info), IC space usage data (IC_use_info), self-service printing usage data (print_info). Since the collected raw data comes from var...

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

A method for constructing a user portrait model of an academic library based on multi-view dichotomous k-means. The user portrait model of an academic library is based on the behavior data generated by readers in the library. First, it passes data such as ETL from multiple business systems The cleaning tool summarizes the data, and uses the processed and summarized data to construct a multi-dimensional and multi-perspective reader feature system; then, through the multi-perspective dichotomous k-means algorithm based on the Mahalanobis distance, several reader groups are obtained through multi-perspective clustering, according to The characteristics of the reader group are used to extract the user characteristics; finally, the user portrait of the reader is constructed by using the visualization tool, and the accurate recommendation and service for the reader are realized according to the user portrait. The group characteristics obtained by the present invention realize accurate service and recommendation.

Description

technical field [0001] The invention relates to data mining, Mahalanobis distance, binary K-means algorithm, user portrait and behavior analysis, and is a method for constructing a user portrait model based on multi-view clustering. Background technique [0002] The library of a university is one of the three pillars of running a school. The quality of the library construction reflects the level of education and scientific research of the school from one aspect. The investment of the university in the library is huge every year. With the development of Internet technology, traditional libraries are gradually transforming into digital libraries. However, with the increase of library resources year by year, it is becoming more and more difficult for readers to find the resources they are interested in. With the advent of the era of big data, readers' reading needs, behaviors, methods and approaches have undergone tremendous changes compared with traditional reading methods. I...

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 Patents(China)
IPC IPC(8): G06F16/25G06K9/62
CPCG06F16/254G06F18/23213
Inventor 李伟方小刚胡云飞
Owner ZHEJIANG UNIV OF 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