Memory network-based intention recognition method under multi-round dialogues

A recognition method and network technology, applied in the field of neural network learning of memory network, can solve the problems of limited memory ability of rnn and lstm

Inactive Publication Date: 2018-11-16
南京柯基数据科技有限公司
View PDF4 Cites 33 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The memory of the cyclic neural network is an internal memory method, which is realized by rnnCell or lstmCell,

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
  • Memory network-based intention recognition method under multi-round dialogues
  • Memory network-based intention recognition method under multi-round dialogues
  • Memory network-based intention recognition method under multi-round dialogues

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] In order to understand the above-mentioned purpose, features and advantages of the present invention more clearly, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0055] refer to figure 1 , the concrete steps of the inventive method are described below:

[0056] A1. Input the English Wikipedia corpus downloaded from the Wikipedia website, process the corpus, and only keep valid texts.

[0057] A2. Construct the co-occurrence matrix of words based on the corpus, let the co-occurrence matrix be X, and its elements be X ij . x ij The meaning of the representation is: in the entire corpus, the number of times word i and word j co-occur in a window. Use the window to traverse the entire corpus to obtain the co-occurrence matrix X.

[0058] A3. Combined with the co-occurrence matrix X, use the GloVe model to train the word vector model.

[0059] A4. Generate a word vector model.

...

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 memory network-based intention recognition method under multi-round dialogues. A neural network model combining a recurrent neural network, a memory network and an attentionmechanism is mainly adopted. The method comprises the steps of firstly performing mathematical processing on a language; secondly encoding each round of the dialogue by utilizing the recurrent neuralnetwork to obtain an encoding vector of the dialogue; thirdly storing historical dialogue information by utilizing an external memory; fourthly, selecting the historical dialogue information related to an intention of the current round of the dialogue from the memory through an attention mechanism, thereby obtaining an encoding vector of the historical information; fifthly, for the current dialogue encoding vector and the historical dialogue encoding vector, judging whether the historical information is introduced in a classifier or not by utilizing a control gate, thereby obtaining encoding information which is finally used for classification; and finally, obtaining the intention of each round of the dialogue by utilizing the multi-label classifier.

Description

technical field [0001] The invention belongs to the dialogue field of natural language processing, and relates to a neural network learning method of a memory network. Background technique [0002] With the continuous improvement of people's living standards, the emergence of artificial intelligence equipment actually meets the "small rigid needs" of the public's psychology, such as smart speakers, one of the artificial intelligence equipment. Smart services such as playing music through voice control, or turning off the lights while lying in bed in winter, have greatly facilitated people's lives to a certain extent. The explosive growth of the domestic smart speaker market in 2017 is astonishing, and the sales data in 2017 is enough to show the popularity of smart speakers in China. This year was the fastest-growing year for the smart speaker market, and many brands quickly won the market through their own software or hardware advantages. Of course, behind the success, th...

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): G06F17/27G06F17/30G06N3/04G06N3/08
CPCG06N3/084G06F40/216G06N3/048
Inventor 杨成彪吴刚
Owner 南京柯基数据科技有限公司
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