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

Multi-feature matching text matching method, terminal and readable storage medium

A matching method and technology for text to be matched, applied in the field of natural language processing, can solve the problems of low text matching accuracy and ignore the overall semantic information of the text, and achieve the effect of improving the matching accuracy

Pending Publication Date: 2022-05-10
CHONGQING UNIV OF POSTS & TELECOMM
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the above existing methods, the use of keywords will cause the overall semantic information of the text to be ignored, and the use of deep learning representation methods will ignore the fine-grained information in the text, resulting in low text matching accuracy

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
  • Multi-feature matching text matching method, terminal and readable storage medium
  • Multi-feature matching text matching method, terminal and readable storage medium
  • Multi-feature matching text matching method, terminal and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] like figure 1 As shown, the first embodiment provides a text matching method for multi-feature matching, the method includes the following steps:

[0031] Step S1, obtaining the text to be matched and the candidate text, and performing preprocessing on the text to be matched and the candidate text;

[0032] Step S2, performing N-Gram-based multi-granularity analysis on the preprocessed text to obtain text sequences at different granularities, and vectorizing the text sequences to obtain text vectors;

[0033] Step S3, input the text vector column into the deep learning language model for training, and obtain the coding vectors of the text to be matched and the candidate text;

[0034] Step S4, performing similarity calculation on the encoding vector of the text to be matched and the encoding vector of the candidate text, and then summing and taking an average to obtain the matching degree of the text to be matched and the candidate text.

[0035] The present invention...

Embodiment 2

[0063] Based on the same idea, Embodiment 2 of the present application provides a multi-feature matching terminal, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, The steps of the method are carried out.

[0064] image 3 A schematic diagram of the physical structure of the terminal provided in Embodiment 1 of the present invention, as shown in image 3 As shown, the terminal may include: a processor (processor) 310, a communication interface (CommunicationsInterface) 320, a memory (memory) 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 complete the interaction through the communication bus 340 communication between. The processor 310 can invoke a computer program stored in the memory 330 and operable on the processor 310 to execute the text matching methods provided in the above-mentioned embodiments,...

Embodiment 3

[0067] Based on the same idea, Embodiment 3 of the present application provides a computer-readable storage medium, where the computer-readable storage medium stores a computer program, and the computer program implements the steps of the method when executed by a processor.

[0068] In addition, the above-mentioned logic instructions in the memory 330 may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the embodiment of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium , including several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of ...

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 multi-feature matching text matching method, a terminal and a readable storage medium, relates to the field of natural language processing, and solves the problem that an existing text matching method ignores fine-grained information in a text and overall semantic information of the text, obtains a to-be-matched text and a candidate text, and improves the matching efficiency. Preprocessing the text to be matched and the candidate text; performing N-Gram-based multi-granularity analysis on the preprocessed text to obtain a text sequence under different granularities, and vectorizing the text sequence to obtain a text vector; inputting the text vector column into a deep learning language model for training to obtain coding vectors of the to-be-matched text and the candidate text; performing similarity calculation on the coding vectors of the to-be-matched text and the candidate text, summing and averaging to obtain the matching degree of the to-be-matched text and the candidate text; according to the method, fine-grained lexical item semantic information and coarse-grained text overall semantic information are combined, so that the text matching accuracy is improved.

Description

technical field [0001] The present invention relates to the field of natural language processing, more specifically, it relates to a multi-feature matching text matching method, a terminal and a readable storage medium. Background technique [0002] With the rapid development of the information age, all kinds of text information are flooding the network world. In network search, how to efficiently and accurately match text information has become an effective guarantee for major Internet platforms to provide data search services. [0003] In the prior art, text matching is often extracted by a single keyword, and matched with the overall semantics of the text trained by the deep learning representation method. However, in the above existing methods, the use of keywords will cause the overall semantic information of the text to be ignored, and the use of deep learning representation methods will ignore the fine-grained information in the text, resulting in low text matching a...

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): G06F16/335G06F40/289G06F40/30G06K9/62G06N3/04G06N3/08
CPCG06F16/335G06F40/30G06F40/289G06N3/08G06N3/045G06F18/22
Inventor 夏书银杨宁张勇
Owner CHONGQING UNIV OF POSTS & TELECOMM