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

Automatic dialogue intention recognition system based on linguistic rule generation

An automatic recognition system and linguistic technology, applied in the field of semantic recognition, can solve problems such as heavy manual workload and inaccurate recognition of dialogue intentions

Pending Publication Date: 2021-04-09
中通天鸿(北京)通信科技股份有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] For this reason, the present invention provides an automatic dialogue intent recognition system based on linguistic rules to solve the existing problems of inaccurate dialogue intention recognition and heavy manual workload

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
  • Automatic dialogue intention recognition system based on linguistic rule generation
  • Automatic dialogue intention recognition system based on linguistic rule generation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0024] This embodiment discloses a system for automatically identifying dialogue intentions based on linguistic rules. The system includes: a word segmentation module, a linguistic rule generation module, an intention model group generation module, and a model similarity calculation module. The word segmentation module will Sentences are divided into words, and the linguistic rule generation module marks the words with their respective syntax and semantic information. The intention model group generation module has deduplicated and merged intentions, and each intention generates a semantic model group. The model similarity calculation module calculates the similarity between two models.

[0025] The word segmentation module will segment the complete sentence, and divide the sentence into multiple words according to commonly used vocabulary and sentence segmentation for subsequent processing; the linguistic rule generation module will mark each word on the basis of the common in...

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 an automatic dialogue intention recognition system based on linguistic rule generation. The system comprises a word segmentation module, a linguistic rule generation module, an intention model group generation module, and a model similarity calculation module. The word segmentation module is used for carrying out word segmentation on sentences, the linguistic rule generation module marks respective syntax and semantic information on words, the intention model group generation module performs duplication elimination and combination by taking intention as a unit, each intention generates a semantic model group, and the model similarity calculation module calculates the similarity between two models. According to the invention, the problems of inaccurate dialogue intention recognition and large manual workload in the prior art are solved.

Description

technical field [0001] The invention relates to the technical field of semantic recognition, in particular to a dialog intention automatic recognition system generated based on linguistic rules. Background technique [0002] There are generally two existing methods for dialogue intent recognition: one is regular matching based on dictionary templates; the other is intent recognition based on deep learning classification models. Regular matching based on dictionary templates is composed of rule templates based on regular expressions that are manually summarized. By performing regular matching on each round of dialogue, different dialogue texts are identified as different intentions. The disadvantage of this technology is that the workload of manually summarizing the rules is heavy, and the simple regular matching of keywords cannot fully recognize the semantics. When a sentence hits the regular matching rules of two intentions at the same time, the system cannot judge. [00...

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): G06F16/332G06F40/289G06F40/30
CPCG06F16/3329G06F40/289G06F40/30
Inventor 冷月
Owner 中通天鸿(北京)通信科技股份有限公司
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