A library intelligent search sorting method and system

A technology of intelligent search and sorting methods, applied in neural learning methods, digital data information retrieval, instruments, etc., can solve problems such as keyword retrieval and retrieval failure, save human resources and difficulty in use, avoid the increase of computing resources, and ensure prediction. The effect of efficiency

Inactive Publication Date: 2020-02-18
CHONGQING UNIV OF ARTS & SCI
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] Existing library book retrieval methods generally use keyword matching. At the same time, in order to reduce workload and complexity, most retrieval systems use keyword matching of book titles and authors. The search for keywords that do not match the title of the book will fail;

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 library intelligent search sorting method and system
  • A library intelligent search sorting method and system
  • A library intelligent search sorting method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] The present invention will be further described below in conjunction with drawings and embodiments.

[0047] As shown in the figure, the library intelligent search sorting method provided by this embodiment includes the following steps:

[0048] Obtain search information;

[0049] Use the circular convolutional network to process the retrieval information and extract the feature vector;

[0050] Send the feature vector into the convolutional neural network, and output the prediction vector with the same dimension as the number of books in the library;

[0051] Use the softmax function to normalize the prediction vector to generate the prediction probability corresponding to each book;

[0052] Sort the predicted probabilities, and output the sorting results according to the probability from high to low;

[0053] Store the book prediction ranking results in the database.

[0054] Also includes the following steps:

[0055] According to the sorting results and the bo...

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 an intelligent search sorting method of a library. The intelligent search sorting method comprises the following steps: firstly, establishing an intelligent search model training device and an intelligent search predication sorting model; obtaining search information; treating the search information by utilizing a cyclic convolution network and extracting an information characteristic vector; carrying out normalization computing on the characteristic vector of the search information by utilizing a softmax function; calculating a book sequence through the intelligent search predication sorting model and storing in a database; predicating an error degree by utilizing an accumulated error computing model; determining whether the intelligent search predication sorting model is updated or not according to the size of an accumulated error value. Compared with a traditional search system matched with a title and an author keyword, the method provided by the invention is more flexible and the search accuracy of a searched keyword which is not in the book title is improved; the intelligent search model training device and the database are arranged so that the system has a self-adaptive learning capability and manpower participation is reduced; manpower resources are saved and the utilization difficulty are saved; an intelligent search sorting system which has own book characteristics of the library and habits of a lot of users can be more conveniently distributed.

Description

technical field [0001] The invention relates to the technical field of automatic book detection, in particular to a library intelligent search and sorting method and system for accurate prediction and recommendation. Background technique [0002] Existing library book retrieval methods generally use keyword matching. At the same time, in order to reduce workload and complexity, most retrieval systems use keyword matching of book titles and authors. The search for keywords that do not match the title of the book will fail; [0003] Therefore, there is a need for an intelligent search and ranking method and system for libraries that can accurately predict and recommend. Contents of the invention [0004] The object of the present invention is to propose a method and system for intelligently searching and sorting libraries for accurate prediction and recommendation. [0005] The purpose of the present invention is achieved through the following technical solutions: [0006...

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): G06F16/245G06F16/248G06N3/08
CPCG06F16/245G06F16/248G06N3/08
Inventor 于慧胡雪华徐小红
Owner CHONGQING UNIV OF ARTS & SCI
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