Semantic matching method, device, medium and electronic device for question and answer text

A technology of semantic matching and semantic matching, applied in semantic analysis, electronic digital data processing, instruments, etc., can solve the problem of low accuracy of semantic matching, achieve the effect of accurate semantic matching and improve accuracy

Active Publication Date: 2022-01-11
TAIKANG LIFE INSURANCE CO LTD +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the embodiments of the present invention is to provide a semantic matching method, device, medium, and electronic equipment for question-and-answer texts, so as to overcome the problem of low accuracy of semantic matching for question-and-answer texts at least to a certain extent

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
  • Semantic matching method, device, medium and electronic device for question and answer text
  • Semantic matching method, device, medium and electronic device for question and answer text
  • Semantic matching method, device, medium and electronic device for question and answer text

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments may, however, be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete and fully convey the concept of example embodiments to those skilled in the art.

[0029] Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided in order to give a thorough understanding of embodiments of the invention. However, those skilled in the art will appreciate that the technical solutions of the present invention may be practiced without one or more of the specific details, or other methods, components, means, steps, etc. may be employed. In other instances, well-known methods, apparatus, implem...

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 present disclosure provides a method for semantic matching of question and answer texts, which includes using a recurrent neural network to obtain feature vector sequences with contextual local features of question texts and feature vector sequences with contextual local features of candidate answer texts; based on the question text and the The feature vector sequence with contextual local features of the candidate answer text and the attention weight of each feature vector in the feature vector sequence with contextual local features of the question text and the candidate answer, generating the contextual local features and global features of the question text According to the feature vector sequence of the question text and the feature vector sequence with context local features and global features of the candidate answer text; according to the feature vector sequence of the question text with context local features and global features, the features of the candidate answer text with context local features and global features A sequence of vectors that determine the semantic match between the question text and the candidate answer.

Description

technical field [0001] The present invention relates to the technical field of natural language processing, in particular to a semantic matching method, device, medium and electronic equipment for question and answer text. Background technique [0002] At present, the method of semantic matching of Q&A text based on deep learning may include the following steps: a word embedding model trained based on neural network is used to represent the text as a word vector, which has stronger semantic representation ability. Model text by constructing long-short-term memory network LSTM (Long Short-Term Memory) or gated recurrent unit GRU (Gated Recurrent Unit) and other deep learning models. Although these methods are less dependent on feature selection and extract shallow semantic information and contextual local features to a certain extent, they cannot represent a large number of key global features, thus reducing the accuracy of semantic matching of Q&A texts. [0003] It should ...

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): G06F16/332G06F40/30
CPCG06F40/30
Inventor 李渊刘设伟
Owner TAIKANG LIFE INSURANCE CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap