Unlock instant, AI-driven research and patent intelligence for your innovation.

Automatic library book classification method

An automatic classification and library technology, applied in the field of information management, can solve the problems of insufficient classification information, low efficiency, and failure to provide corresponding reference information, etc., and achieve the effect of saving cost, manpower and material resources, and convenient operation

Inactive Publication Date: 2019-04-19
ZAOZHUANG UNIV
View PDF4 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, this classification method has the defects of low efficiency and insufficient classification information, and cannot provide corresponding reference information for the audience to choose

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
  • Automatic library book classification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0027] Such as figure 1 A method for automatic classification of library books, comprising:

[0028] Step 1. Determine the mature model and put the data into the feature database;

[0029] Specifically: read the names of all books and the corresponding bookshelves and convert the book names into Chinese characters, and use the Chinese language model combined with related models used to generate word vectors or common weighting techniques for information retrieval data mining to perform word segmentation to form feature vectors. Among them, n is a positive integer greater than or equal to 1, and the number of categories is determined according to the number of book categories to which the bookshelf belongs;

[0030] Divide the feature vectors of the existing books and the corresponding bookshelf numbers into 3 blocks, the ratio is 7:1.5:1.5, of which 70% are used for training the model, 15% are used for testing the training accuracy and continuously adjusting the model to make...

Embodiment 2

[0041] Such as figure 1 A method for automatic classification of library books, comprising:

[0042] Step 1. Determine the mature model and put the data into the feature database;

[0043] Specifically: read the names of all books and the corresponding bookshelves and convert the book names into Chinese characters, and use the Chinese language model combined with related models used to generate word vectors or common weighting techniques for information retrieval data mining to perform word segmentation to form feature vectors. Among them, n is a positive integer greater than or equal to 1, and the number of categories is determined according to the number of book categories to which the bookshelf belongs;

[0044] Divide the feature vectors of the existing books and the corresponding bookshelf numbers into 3 blocks, the ratio is 7:1.5:1.5, of which 70% are used for training the model and 15% are used for testing the training accuracy and continuously adjusting the model to a...

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 the field of information management, in particular to an automatic library book classification method. The method comprises the steps that 1, determining a mature model, and putting data into a feature database; 2, obtaining characters of the covers of the books to be classified; Step 3, obtaining image information to be classified; 4, matching with a feature database; And5, outputting book classification information according to the information carried in the image information. According to the method, the effect of quickly and automatically carrying out corresponding classification on the to-be-detected books is achieved, meanwhile, the method is convenient to operate, and cost, manpower and material resources are effectively saved.

Description

technical field [0001] The invention relates to the field of information management, in particular to an automatic classification method for library books. Background technique [0002] Based on the development and promotion of electronic technology, digital office has become more and more popular among users. Compared with traditional paper office, digital office has the advantages of high efficiency, easy management and environmental protection. Based on the long-term digital office, people are more and more inclined to recommend and search on the Internet in terms of reading. [0003] Under the good environment of public reading, each region has correspondingly built places such as libraries for the public to borrow books, but at the same time of building such places, because of the need to store a large number of books, this requires a lot of work Books should be classified and stored accordingly, that is, books of the same category need to be placed in corresponding bo...

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): G06K17/00G06K9/00G06K9/62G06F17/27
CPCG06K17/0022G06F40/289G06V30/413G06V30/418G06V30/287G06F18/22
Inventor 林聪
Owner ZAOZHUANG UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More