Natural language intention understanding method in man-machine interaction

A natural language and human-computer interaction technology, applied in the field of human-computer interaction, can solve problems such as being susceptible to noise interference, achieve broad market prospects, improve system generalization ability, and strengthen the effect of generalization ability

Active Publication Date: 2016-07-20
SHANGHAI JIAO TONG UNIV
View PDF9 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantage of this method is that it is ea

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
  • Natural language intention understanding method in man-machine interaction
  • Natural language intention understanding method in man-machine interaction
  • Natural language intention understanding method in man-machine interaction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0025] In the embodiment of the present invention, the interaction with the home service robot through natural language is realized, including music playing, mail sending and receiving, TV control, cooking, telephone, air conditioning control, weather forecast and system setting eight categories of instructions, a total of 60 intents , which basically covers the main content of home services, and uses a tree structure to represent this instruction system, such as figure 2 shown. When the user wants to initiate an operation to call Zhang San, he can say "Call Zhang San". In this command system, a four-layer intent tree is set up, which is progressive layer by layer, and the operation is divided in great detail. The intent we refer to is the node in the intent tree, which recognizes each user instruction, identifies which node is in the corresponding intent tree, and then conducts a dialogue management according to the context to guide the user to the end of the intent tree to...

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 natural language intention understanding method in man-machine interaction.The method comprises the steps that intention labeling is conducted on text natural language instruction data, and each sentence of text is labeled with an intention; the text is vectorized, on the basis of a traditional text vector space model, information of parts of speech of a text instruction is fused, and a new text representation model, namely, a vector space model of the parts of speech is defined; a stackable denoising auto-encoder is applied to natural language instruction intention understanding, and the high-order characteristic of the instruction is extracted; at last, training and prediction are conducted through a support vector machine, and intention understanding of the natural language instruction is achieved.According to the natural language intention understanding method in man-machine interaction, more semantic information in the natural language instruction can be excavated, the recognition rate of intention understanding is increased, the stackable denoising auto-encoder is adopted, random noise is added during the training process, the actual application scene is more approached, and a model obtained from training has higher generalization capacity.

Description

technical field [0001] The invention relates to the technical field of human-computer interaction, in particular to a method for a machine to understand the intention of a natural language spoken by a human in human-computer interaction, and can be widely used in the fields of service robots, smart home, smart home appliances, voice navigation, etc. Understanding of human-computer interaction voice control commands. Background technique [0002] With the development of social economy, the demand for machines is increasing day by day, and its application scope is becoming wider and wider. Efficient and friendly human-computer interaction is a very important link that affects its wide application. In practical applications, there are various ways of interaction, mainly including: touch interaction, somatosensory interaction, voice interaction, etc. Among the many ways of interaction, it is the most direct and convenient way to interact with machines through voice, especially...

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): G06F17/27G06F17/28
CPCG06F40/30G06F40/40
Inventor 赵群飞李瀚清蒋天峰
Owner SHANGHAI JIAO TONG UNIV
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