Natural language dialogue system intention deep learning method

A deep learning and dialogue system technology, applied in natural language data processing, speech analysis, speech recognition, etc., can solve problems such as labor-intensive, inexhaustible rules, continuous evolution, etc., to achieve the effect of improving accuracy and ensuring accuracy

Pending Publication Date: 2022-03-25
SHANDONG UNIV OF SCI & TECH
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above rule-based natural language understanding method has at least the following technical problems: 1) The setting of rules usually depends on domain knowledge, which requires professionals to set and consumes manpower
2) Because of the diversity of natural language expressions, a large number of rules need to be set to cover different expressions, but even so, it is impossible to exhaust all the rules
3) Rule-based methods cannot continue to evolve based on actual data for self-learning. When encountering problems, they can only be solved by continuously setting new rules
However, it is not used as an evaluation dimension in the above scheme, which will lead to distortion of the understanding of the user's intention and affect the user's experience

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 dialogue system intention deep learning method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] A kind of natural language dialog system intention deep learning method of this embodiment (such as figure 1 shown), including:

[0051] S1 acquires the dialogue text information to be analyzed and the user's voice signal when describing the dialogue text information.

[0052] Usually, in the process of human-computer interaction, dialogue text information to be parsed in the process of human-computer interaction is obtained. Users mainly conduct human-computer interaction through voice. When the user performs human-computer interaction by voice, after receiving the voice signal input by the user, voice recognition may be performed on the received voice signal to obtain text information corresponding to the voice information. At this point, the voice signal and dialogue text information are completed.

[0053] S2 Determine the word vector of each word segment in the dialogue text information.

[0054] Specifically, after the dialogue text information to be parsed is...

Embodiment 2

[0069] The difference between this embodiment and Embodiment 1 is that in this embodiment, the emotion recognition model is also used to determine the scene of the user according to the noise in the speech signal, and judge whether to mark all word vectors as neutral.

[0070] Determine the user's scene based on the noise in the speech signal, including:

[0071] Obtain the background signal between the speech segmentation signals;

[0072] Match the background signal with the preset noise library, and if the matching degree exceeds the threshold, the determination of the scene where the user is located is completed.

[0073] For example, when the user is in a subway or other noisy environment, the user's expression tends to be more realistic / efficiency-maximizing, and carries less related emotions. In this scenario, what is needed is to eliminate the interference of emotion recognition and quickly recognize it to improve user experience. Moreover, compared with the prior ar...

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 relates to the field of artificial intelligence, natural language understanding and service robots, in particular to a natural language dialogue system intention deep learning method, which comprises the following steps: acquiring to-be-analyzed dialogue text information and a voice signal when a user describes the dialogue text information; determining a word vector of each segmented word in the dialogue text information; segmenting the voice signal according to each segmented word in the dialogue text information to obtain a voice segmentation signal, and then performing emotion calibration according to an emotion recognition model and a word vector corresponding to the voice segmentation signal; according to an intention recognition model and the word vector, generating an intention type of the dialogue text information; and obtaining an intention element extraction model corresponding to the intention type. According to the method, intention understanding can be assisted by utilizing the emotional information transmitted by the user during dialogue, and the analysis accuracy is improved.

Description

technical field [0001] The invention relates to the fields of artificial intelligence, natural language understanding and service robots, in particular to a method for deep learning of intent in a natural language dialogue system. Background technique [0002] Dialogue System is a human-computer interaction system based on natural language. Through the dialogue system, people can use natural language to interact with the computer for multiple rounds to complete specific tasks, such as information query, service acquisition, etc. The dialogue system provides a more natural and convenient way of human-computer interaction, and is widely used in vehicle, home, customer service and other scenarios. [0003] Among them, Natural Language Understanding (Natural Language Understanding) is the core module in the dialogue system. The goal of natural language understanding is to convert the text information of natural language into a semantic representation (Semantic Representation) ...

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): G10L15/04G10L15/16G10L15/18G10L15/26G10L25/63G06F16/33G06F16/332G06F40/284G06F40/289
CPCG10L15/04G10L15/16G10L15/1822G10L15/26G10L25/63G06F16/3329G06F16/3343G06F40/284G06F40/289
Inventor 宫晨羽王雪婷王一凡
Owner SHANDONG UNIV OF SCI & TECH
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