Unlock instant, AI-driven research and patent intelligence for your innovation.

Intent recognition method, device, equipment and storage medium

A recognition method and intent technology, which is applied in the computer field, can solve the problems of complex implementation and the need to improve the accuracy of user intent recognition, and achieve the effects of improving accuracy, reducing implementation complexity, and improving compilation efficiency

Active Publication Date: 2021-11-23
BEIJING 58 INFORMATION TTECH CO LTD
View PDF0 Cites 0 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 recognition method, device, equipment and storage medium
  • Intent recognition method, device, equipment and storage medium
  • Intent recognition method, device, equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0099] Embodiments of the present invention provide a intent identification method, such as figure 1 As shown, the method includes:

[0100] S101, in response to meaning;

[0101] S102, based on the document-based question and answer DBQA template compiled by the predefined lexical template and the syntactive template, the intentional data is matched;

[0102] S103 identifies the semantics represented by the intentive figure according to the result of the match.

[0103] The term template and syntax template in the embodiment of the present invention are predefined; meaning data in the embodiment of the present invention can be a text / sentence input by a user.

[0104] The embodiment of the present invention matches the intent data by the DBQA template compiled by the lexical template and the syntact template, effectively improves the accuracy of the user intentively identification; and generates the word DBQA template by compiling the lexical template and syntax template to rea...

Embodiment 2

[0136] Embodiments of the present invention provide a intent identification method, such as Figure 4 As shown, the method includes:

[0137] S201, in response to meaning picture;

[0138] S202, establishing a lexical template and syntax template; optionally, establishing a lexical template comprises: obtaining a target string and a target string collection corresponding to each of the standard meaning based on each standard meaning; in the corresponding target character The string and the corresponding target string set set the assignment operator to create the entry template for each target string; the term template is generated based on the entry template of the respective target strings;

[0139] S203, based on the document-based question and answer DBQA template compiled by the predefined lexical template and the syntactive template, the intentional drawing data is matched;

[0140] S204, based on the result of the match, identify the semantics represented by the intentive dat...

Embodiment 3

[0197] Embodiments of the present invention provide a intent identification method, such as Figure 4 As shown, the method includes:

[0198] S201, in response to meaning picture;

[0199] S202, establish a lexical template and syntax template; optionally, establish a syntax template includes: obtaining a target string associated with each standard problem; determines the core of each standard problem in the related target string String and matching strings, the core string is used to classify the intended data to a standard problem, the matching string is used to match the intent data; establish the description according to the reference operator and the core string Each standard problem template; according to the reference operator and the matching string, one or more sentence type templates are established under each of the standard problem templates; the various standard problem templates and sentence type template are generated according to the established standard problem tem...

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 present invention discloses an intention recognition method, device, equipment and storage medium. The intention recognition method includes: responding to intention data; The intent data is matched; according to the matching result, the semantics represented by the intent data are identified. The invention effectively improves the accuracy rate of user intention recognition, effectively reduces the implementation complexity of the DBQA template, and effectively improves the compilation efficiency.

Description

Technical field [0001] The present invention relates to the field of computer, and more particularly to a intended identification method, apparatus, device, and storage medium. Background technique [0002] Existing DBQA (Document-Base Question Answering, Document-based Q & A) System or intelligent customer service system generally combines two techniques for machine learning and natural language, or using EBQA to input the user into the sentence and the sentence in the Knowledge Base Matching; or using a single FastText text classification technology, the user input text is identified based on the BOWSA (Bag-Words Semantic Analysis, the Bag semantic analysis) method fused. [0003] However, the existing DBQA system or intelligent customer service system is complex, and the accuracy of the user intention is to be improved. Inventive content [0004] In order to overcome the above defects, the technical problem to be solved by the present invention is to provide an intended metho...

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 Patents(China)
IPC IPC(8): G06F16/332G06F40/211G06F40/30G06F40/289G06F40/186
CPCG06F40/186G06F40/211G06F40/289G06F40/30
Inventor 郝杰
Owner BEIJING 58 INFORMATION TTECH CO LTD