Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for identifying complex intentions in task type multi-round dialogue

A recognition method, a technology in dialogue, applied in the direction of neural learning methods, biological neural network models, instruments, etc., can solve problems such as difficulties, and achieve the effect of avoiding dialogue turns

Active Publication Date: 2019-10-08
PEKING UNIV +1
View PDF4 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This also makes it difficult for the current dialogue system to cope with the transformation of complex intentions in multiple rounds of dialogue, and it is even more difficult to predict the user's next possible intention in advance based on the existing dialogue content.

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
  • Method for identifying complex intentions in task type multi-round dialogue
  • Method for identifying complex intentions in task type multi-round dialogue
  • Method for identifying complex intentions in task type multi-round dialogue

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] Below by example the present invention will be further described.

[0031] Suppose there are t rounds of task-style dialogue. In the tth dialogue round, the multi-intent tracking and recognition module converts the current round of questions Q t , the answer statement R of the previous round t-1 , and the information slot content S of the current round t Input a gate structure controller g t , to get the intent I of the current round of dialogue sentences t . Then the "proactive prediction" mechanism partly uses an intent transition matrix to predict the user's next possible intent I t+1 . I t+1 For the next intent to transfer to. This method obtains the information in the information slot through the method of sequence labeling, and fills it into an information slot memory that can be shared globally. Afterwards, the system in the scheme will, according to the identified current round intent I t , and the corresponding information slot contents are searched i...

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 provides a method for identifying the complex intentions in the task type multi-round dialogue, and belongs to the field of natural language processing. The method is characterized by defining a task of multi-intention tracking and recognition, introducing a whole set of intention transfer mode set, designing a door structure controller to better utilize the information in the dialogue and identify the intention of the current round of the dialogue in the dialogue process. In addition, the method can predict the next possible intention of the user when the current dialogue intention is finished, and provide the useful information in advance. The mechanism of the prepositive prediction can borrow the information from other related intentions, so that a long dialogue round is avoided to a certain extent. After the dialogue intention of the current round and the potential next round is obtained, the method generates a reply by combining the intention and the information slotaccording to a template library pre-defined manually, so that the more natural dialogue reply result is obtained.

Description

technical field [0001] The present invention provides a method for recognizing and predicting complex intentions in task-type multi-round dialogues, which specifically includes: identifying the current round of dialogue intentions according to the gate structure controller, predicting the next round of dialogue intentions according to the proactive feedback mechanism, and using the pre-set Defined templates for reply generation. The invention belongs to the field of natural language processing. Background technique [0002] Task-based dialogue systems have a wide range of application scenarios, such as airline ticket booking, online customer service, and so on. In the task-based dialogue system, the user interacts with the machine through natural language to obtain the required information or answers. [0003] The "intent" of a task-based dialog is what the user wants to achieve. In order to achieve this purpose, the system usually needs some specific information called "...

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): G06F16/245G06F16/332G06N3/04G06N3/08
CPCG06F16/3329G06F16/245G06N3/084G06N3/044
Inventor 王厚峰施晨
Owner PEKING UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com