Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A dialogue management method based on a state tree

A dialogue management and state tree technology, applied in the fields of natural language processing and machine learning, can solve problems such as customers omitting questions and answers and being unable to respond, and achieve the effect of reducing data maintenance, avoiding unresponsiveness, and facilitating addition, deletion, checking and modification

Inactive Publication Date: 2019-06-25
SHANDONG SYNTHESIS ELECTRONICS TECH
View PDF11 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem to be solved by the present invention is to provide a dialogue management method based on a state tree to solve the phenomenon of being unable to respond to various omitted questions and answers of customers

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
  • A dialogue management method based on a state tree
  • A dialogue management method based on a state tree
  • A dialogue management method based on a state tree

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0021] This embodiment is based on an intelligent dialogue system and provides a dialogue management method based on a state tree structure. By storing context states such as slot values, entities, and intentions in the tree structure, a more flexible question-and-answer mode can be realized. In addition, the dialogue management method based on the state tree structure can provide more concise and effective question-and-answer logic for data maintainers and question-and-answer mode designers. This method can also be used on any device equipped with an intelligent dialogue system, such as a mobile phone, a computer, an intelligent robot, and the like.

[0022] The state-based dialogue management method of this embodiment uses topics as the basic dialogue unit, and stores the topic states in single-round dialogue and multi-round dialogue in the state tree structure. The state tree takes the current topic as the root node and reflects the above context of the topic. The QA intent...

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 dialogue management method based on a state tree. The topic state is stored in the dialogue process in a state tree structure and the context can be utilized to understand the real intention of the client to a greater extent, the question and answer efficiency is greatly improved, the phenomenon that various omission questions and answers of a client cannot be responded is effectively avoided, meanwhile, the dialogue management method can achieve multiple dialogue modes based on context omission, data can be conveniently added, deleted, checked and modified, and the data maintenance amount is greatly reduced.

Description

technical field [0001] The invention relates to a dialog management method based on a state tree, which is a system method for performing multiple rounds of interaction on customer questions based on context information, and belongs to the fields of natural language processing and machine learning. Background technique [0002] Dialog Management (DM) controls the process of man-machine dialogue, and DM decides the response to the user at the moment according to the dialogue context status information. Currently, task-driven multi-turn dialogues are the most common. Taking the financial industry as an example, the user has a clear purpose such as remittance, payment, etc., and the dialogue system needs to interact with the customer for multiple rounds to determine what materials the customer should bring and how to handle business under different conditions. Within the scope of the same topic, the customer may derive many other sub-questions based on the topic. At the same t...

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): G06F16/332G06F16/33G06F17/27G06Q30/02
Inventor 申冲张传锋朱锦雷
Owner SHANDONG SYNTHESIS ELECTRONICS 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
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