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

A Text Search Method Based on Flat Algorithm

A flattening, algorithmic technology, applied in the field of text search based on flattening algorithms, can solve problems such as

Active Publication Date: 2019-12-03
XIANGTAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But the current search engine is about 48% in recall and precision, and there is no algorithm that exceeds 50%

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 Text Search Method Based on Flat Algorithm
  • A Text Search Method Based on Flat Algorithm
  • A Text Search Method Based on Flat Algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0108] A text search method based on a flattening algorithm, the method includes the following steps:

[0109] 1) Obtain a text summary to form a document set D;

[0110] 2) segment the documents in the document set D, d i (d i ∈D), to obtain the set of sentences

[0111] 3) Set of sentences Perform word segmentation and obtain word sets

[0112] 4) Calculate the word set any two words in The number of co-occurrences between f c ;

[0113] 5) with the word W k is a node, the number of co-occurrences f c For edges, construct an undirected weighted graph, such as Figure 6 shown;

[0114] 6) According to the keyword set K={k submitted by the user i |i=1,2,3...n}, determine the association relationship of any set of keywords in the undirected weighted graph;

[0115] 7) Calculate and restore the path between words with a flat algorithm, and present the relationship in the form of a picture.

[0116] When performing step 6), expand the search in the followin...

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

Disclosed is a text search method based on a flattening algorithm. The method is characterized by comprising the following steps that 1, a text summary is obtained, and a document collection is formed; 2, a document in the document collection is subjected to segmentation, and a sentence set is obtained; 3, the sentence set is subjected to word segmentation, and a word set is obtained; 4, the co-occurrence frequency between any two words in the word set is calculated; 5, the words are adopted as nodes, the co-occurrence frequency is adopted as the edge, an undirected weighted graph is constructed; 6, according to a keyword set submitted by a user, the incidence relation in the undirected weighted graph of any one keyword set is determined; 7, the flattening algorithm is adopted for calculating and reducing paths between the words, and the incidence relation is shown in a picture mode. The flattening algorithm is adopted for calculating and reducing the paths, and the incidence relation is shown in the picture mode, so that the search recall rate and accuracy are greatly improved.

Description

technical field [0001] The invention relates to the field of information retrieval, in particular to a text search method based on a flattening algorithm. Background technique [0002] Currently, Web retrieval mainly uses PageRank and Hilltop algorithms, and external links are used for retrieval. In terms of plain text retrieval, the BM25 formula is used, which mainly calculates the functionality related to a query word and a certain text. But the current search engine is about 48% in recall and precision, and there is no algorithm that exceeds 50%. [0003] The text search method used in this application is based on the flattening algorithm, drawing on the frequency and weight of the basic co-occurrence relationship, and the principle of depth-first, breadth-first and pruning in the image search method, so as to accurately find between several words within milliseconds. relationship. Contents of the invention [0004] In view of the deficiencies in the above-mentioned ...

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): G06F16/332G06F16/33
CPCG06F16/3328G06F16/334
Inventor 欧阳建权周晴宇郑浩刘天明
Owner XIANGTAN UNIV