Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Book recommendation method and device based on user borrowing behavior-interest prediction

A recommendation method and user technology, applied in the field of big data, can solve problems such as inability to accurately locate the core needs of users, and achieve the effect of improving user satisfaction

Active Publication Date: 2021-11-02
XI'AN POLYTECHNIC UNIVERSITY
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above research cannot accurately locate the core 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 recommendation method and device based on user borrowing behavior-interest prediction
  • Book recommendation method and device based on user borrowing behavior-interest prediction
  • Book recommendation method and device based on user borrowing behavior-interest prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0121] Execute steps 1 and 2:

[0122] Using the offline borrowing data of a provincial library, 100,000 user behavior records and 600,000 book resource data of 10,000 users were randomly selected as the experimental data set. Among them, users have attributes such as user number, age, gender, and occupation, and books have attributes such as book number, book name, category, author, and publishing house. Data preprocessing includes deduplication, outlier processing, missing value processing, and time format normalization.

[0123] Execute step 3:

[0124] The preprocessed data is visualized through the third-party library wordcloud library and the drawing library matplotlib library in python to display the word cloud graph. Based on the visualization, the data is basically labeled and divided into facts according to the type of label generation. There are three types of basic tags: class tags, text tags, and rule tags. User tags are stored in the format of a two-dimensional...

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 recommendation method and device based on user borrowing behavior-interest prediction. The method comprises the following steps: acquiring user borrowing behavior data; based on the user borrowing behavior data, determining basic feature tags, and determining prediction class feature tags by adopting a weight calculation algorithm TFIDF and a cosine similarity method; and inputting the basic feature tag and the prediction type feature tag into a neural network model DeepFM established based on a factorization machine to carry out Embedding feature vectorization, carrying out feature crossing on feature vectors, inputting the feature vectors into a deep neural network, and outputting a recommendation result. The interest prediction label is constructed on the basis of analyzing the borrowing behavior of the library user, and book recommendation is carried out on the user by adopting DeepFM. According to the method, a user behavior tag system is effectively constructed, personalized recommendation is performed in combination with user interests, core requirements of users are accurately positioned, and user satisfaction is improved.

Description

technical field [0001] The present invention relates to the field of big data, in particular to a book recommendation method and device based on user borrowing behavior-interest prediction. Background technique [0002] With the rise of digital libraries in the era of big data, mining users' reading preferences and recommending books has become an inevitable trend. With the rapid development of mobile Internet and self-media, users' attention is constantly shifting from computer to mobile. How to effectively grasp the user's focus in the shortest time and continuously improve user satisfaction has always been an urgent problem to be solved in the recommendation system. [0003] At present, the neural network model (Deep Factorization Machine, hereinafter referred to as DeepFM) based on the factorization machine has been widely used in CTR (Click-Through-Rate) fields such as recommendation and advertisement. The memory ability of regression and the generalization ability of...

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): G06F16/9535G06N3/04G06N3/08G06Q30/06
CPCG06F16/9535G06N3/08G06Q30/0631G06N3/045Y02D10/00
Inventor 赵雪青
Owner XI'AN POLYTECHNIC UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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