A method and system for strategy rule dialogue advance and intention discrimination

A discriminant method and rule-based technology, applied in special data processing applications, instruments, unstructured text data retrieval, etc., can solve the problems of disordered dialogue models, inability to predict the direction of dialogue, and the identification of user intentions

Inactive Publication Date: 2019-01-18
南京瓦尔基里网络科技有限公司
View PDF3 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a method and system for policy rule dialogue advancement and intention discrimination, aiming to solve the problems in the existing man-machine dialogue system based on the confusion of the dialogue model based on the man-machine multi-round dialogue, unable to predict the direction of the dialogue and determine the user's intention

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 method and system for strategy rule dialogue advance and intention discrimination
  • A method and system for strategy rule dialogue advance and intention discrimination

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments.

[0027] Such as figure 1 Shown, a kind of policy rule dialog promotion and intention discriminating method of the present invention include:

[0028] S1. According to the user input results, language understanding technology is used to parse it into predefined semantic slots and grammatical rules, convert user input information into structured information, and detect user intention targets based on user input information.

[0029] Among them, after natural language understanding, a semantic representation needs to be used. There are three main ways of semantic representation, distribution semantics, frame semantics and model theory semantics. Semantic slots are pre-defined according to different scenarios. There are typically two representation types, one are utterance-level categories, such as user intent and utteran...

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 strategy rule dialogue advancing and intention judging method and system. The method comprises the following steps: S1, adopting predefined semantic slot and grammatical rules to convert user input information into structured information; S2, generating a corresponding semantic environment according to the intention of the structured information and the user input information; S3, triggering the next state operation according to the semantic environment and the state representation of the state tracker; S4, mapping according to the triggered state operation to generate different information replies to different conversation behavior replies templates. The invention can predefine semantic slot, for different conversations, retrieve Background Database, the system generates the semantic environment, triggers the operation according to the corresponding rules, pushes forward the multi-round dialogues with the user, judges the user's intention from the dialogues,and continuously decides the next optimal action according to the current state during the dialogues, so as to assist the user to complete the task of obtaining information or services most effectively.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method and system for policy rule dialogue promotion and intention discrimination. Background technique [0002] The human-computer dialogue system is a human-computer interaction system based on natural language. Through the dialogue system, users can use the neural network dialogue generation model to complete specific tasks during multiple rounds of dialogue. The human-computer dialogue system provides a more natural and convenient way of human-computer interaction, and has broad application prospects. [0003] Among them, the policy rule is the basic module of the policy system, which binds a series of behaviors and conditions, and evaluates the conditions to decide whether to execute the behavior. [0004] In the existing human-computer dialogue system, the neural network dialogue generation model has problems such as easy to generate universal rep...

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): G06F16/332G06F16/33
Inventor 徐恒
Owner 南京瓦尔基里网络科技有限公司
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