Intent identification method, intent identification device, intent identification equipment and storage medium

A recognition method and intent technology, applied in the computer field, can solve the problems of complex implementation and the need to improve the accuracy of user intent recognition

Active Publication Date: 2018-11-23
BEIJING 58 INFORMATION TTECH CO LTD
View PDF6 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, the implementation of the existing DBQA system or intelligent customer service system is complex, and the accuracy of user intent recognition needs to be improved

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
  • Intent identification method, intent identification device, intent identification equipment and storage medium
  • Intent identification method, intent identification device, intent identification equipment and storage medium
  • Intent identification method, intent identification device, intent identification equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0099] An embodiment of the present invention provides an intention identification method, such as figure 1 As shown, the method includes:

[0100] S101, responding to intent data;

[0101] S102. Match the intent data according to the document-based question-and-answer DBQA template compiled from the pre-generated lexical template and syntactic template;

[0102] S103. Identify the semantics represented by the intent data according to the matching result.

[0103] In the embodiment of the present invention, the lexical template and the syntactic template are pre-generated; in the embodiment of the present invention, the intent data may be text / sentence input by the user.

[0104] In the embodiment of the present invention, the intent data is matched by the DBQA template compiled from the lexical template and the syntactic template, which effectively improves the accuracy of user intent recognition; and by compiling the lexical template and the syntactic template to generate ...

Embodiment 2

[0136] An embodiment of the present invention provides an intention identification method, such as Figure 4 As shown, the method includes:

[0137] S201, responding to intent data;

[0138] S202, establish a lexical template and a syntactic template; optionally, establishing a lexical template includes: according to each standard meaning, obtaining a target character string and a target character string set corresponding to each standard meaning; Assignment operator is set between string and described corresponding target string collection, to set up the entry template of each target string; Generate described lexical template according to the entry template of each target string set up;

[0139] S203. Match the intent data according to the document-based question-and-answer DBQA template compiled from the pre-generated lexical template and syntactic template;

[0140] S204. Identify the semantics represented by the intent data according to the matching result.

[0141] In...

Embodiment 3

[0197] An embodiment of the present invention provides an intention identification method, such as Figure 4 As shown, the method includes:

[0198] S201, responding to intent data;

[0199] S202, establishing a lexical template and a syntactic template; optionally, establishing a syntactic template includes: obtaining a target string related to each standard question; determining the core of each standard question in the related target string string and matching string, the core string is used to classify the intent data into a standard question, the matching string is used to match the intent data; according to the reference operator and the core string, establish the Each standard question template; according to the reference operator and the matching character string, set up one or more sentence pattern templates under each standard question template; generate the set of standard question templates and sentence pattern templates according to the establishment Syntax temp...

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 intent identification method, an intent identification device, intent identification equipment and a storage medium. The intent identification method includes: responding tointent data; carrying out matching on the intent data according to document-based question answering (DBQA) templates compiled by pre-generated morphology templates and syntax templates; and identifying, according to a result of matching, semantics represented by the intent data. The method effectively improves an accuracy rate of user intent identification, effectively reduces realization complexity of the DBQA templates, and effectively improves compilation efficiency.

Description

technical field [0001] The present invention relates to the field of computers, in particular to an intention recognition method, device, equipment and storage medium. Background technique [0002] The existing DBQA (Document-Base Question Answering, document-based question answering) system or intelligent customer service system generally combines two technologies of machine learning and natural language processing, or uses EBQA to literally hard-code the sentences entered by the user and the sentences in the knowledge base. Matching; or use a single Fasttext text classification technology, BOWSA (Bag-Of-Words Semantic Analysis) method based on the fusion of multi-granularity feature sequences to identify the intention of the user input text. [0003] However, the implementation of existing DBQA systems or intelligent customer service systems is complex, and the accuracy of user intent recognition needs to be improved. Contents of the invention [0004] In order to overc...

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): G06F17/30G06F17/27G06F17/24
CPCG06F40/186G06F40/211G06F40/289G06F40/30
Inventor 郝杰
Owner BEIJING 58 INFORMATION TTECH CO LTD
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