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

Answer identification method and system of attention network based on energy enhancement

A recognition method and attention technology, applied in neural learning methods, biological neural network models, instruments, etc.

Pending Publication Date: 2020-12-15
成都数联铭品科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The object of the present invention is to overcome the above-mentioned defects existing in the prior art, provide a kind of answer recognition method and system based on the attention network, by enhancing the energy intensity vector of the output, solve or at least partly solve the problem caused by attention in the existing method. There are insufficient technical problems in the weight acquisition method, which significantly improves the accuracy of answer acquisition and recognition

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
  • Answer identification method and system of attention network based on energy enhancement
  • Answer identification method and system of attention network based on energy enhancement
  • Answer identification method and system of attention network based on energy enhancement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. The components of the embodiments of the invention generally described and illustrated in the figures herein may be arranged and designed in a variety of different configurations. Accordingly, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present invention.

[0045] see figure 1 , figure 1 It shows a schemati...

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 answer recognition method and system for an attention network based on energy enhancement, and the method comprises the steps: receiving a to-be-processed text through processing equipment, enabling the processing equipment to be internally provided with an attention network for processing the to-be-processed text, and obtaining a text sequence related to an answer, andreceiving the inputted to-be-processed text, obtaining a context vector; determining a basic attention vector of the context vector; acquiring an enhanced vector combination of each vector of the context vector based on the basic attention vector; and obtaining a target answer by adopting the attention network based on the enhanced vector combination. By utilizing the method disclosed by the invention, the accuracy and efficiency of obtaining the answers are improved by enhancing the energy intensity degree of the attention vectors, so that the method has obvious technical advantages and beneficial effects.

Description

technical field [0001] The invention relates to the technical field of natural language processing, in particular to an answer recognition method and system based on an energy-enhanced attention network. Background technique [0002] Reading comprehension, machine translation, and text summarization are the three core problems in the field of natural language processing (NLP). In the traditional solution, phrase-based translation systems complete them by dividing source sentences into multiple chunks and then translating them word by word. task, which leads to unsmooth translation output. The classic approach in the translation model of neural machine translation (NMT) is formulated by the encoder-decoder architecture (encoder-decoder), and the recurrent neural network is commonly used as the encoder and decoder. The general process of this type of model is to first send the pending text of the source sentence into the encoder, extract the last hidden representation and use...

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 Applications(China)
IPC IPC(8): G06F40/295G06F40/40G06F40/117G06N3/04G06N3/08
CPCG06F40/295G06N3/08G06F40/117G06F40/40G06N3/044G06N3/045Y02D10/00
Inventor 刘世林曾途吴桐杨李伟尹康韩远
Owner 成都数联铭品科技有限公司