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

Method for intention recognition and corresponding system, computer equipment and medium

An intent and corresponding technology, applied in the field of computer equipment and computer-readable storage media, to achieve the effects of personalized configuration, reduction of dependencies, and realization of configuration

Active Publication Date: 2021-11-02
北京元年科技股份有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The object of the present invention is to provide a solution that can solve or alleviate at least one of the above problems

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
  • Method for intention recognition and corresponding system, computer equipment and medium
  • Method for intention recognition and corresponding system, computer equipment and medium
  • Method for intention recognition and corresponding system, computer equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to make the above and other features and advantages of the present invention clearer, the present invention will be further described below in conjunction with the accompanying drawings. It should be understood that the specific embodiments given herein are for the purpose of explaining to those skilled in the art, and are only exemplary rather than restrictive.

[0041] figure 1 A method 100 for intent recognition according to an embodiment of the present invention is schematically shown. The method 100 may include step S110 and step S120.

[0042] In step S110, a query request from a user is received, and the query request may be represented by an input text. The input text may be various possible user input texts, such as colloquial expressions and omitted expressions from the user.

[0043] In step S120, processing steps are performed in response to the query request. The processing steps may include a word segmentation obtaining step (step S122), a jud...

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 provides a method for intention recognition and a corresponding system, computer equipment and a medium. The method comprises the following steps: receiving an input text representing a query request from a user, and responding to the input text to execute the following steps: analyzing the input text to obtain a corresponding target segmented word and a related segmented word type; judging whether a matched configured intention category exists in the configured intention categories or not for the query request; if the judgment result is positive, determining that the matched configured intention category is a target query intention category of the query request, and if the judgment result is negative, adding a new configured intention category, and taking the new configured intention category as the target query intention category of the query request; and filling the slot position of the target query intention category with the target segmented word of the corresponding type to determine the target query intention of the query request. The method supports the addition of new intention categories, facilitates the dynamic configuration and personalized configuration, and improves the user experience.

Description

technical field [0001] The present invention relates to the field of intent recognition, and more specifically, to a method for intent recognition, a corresponding system, computer equipment, and a computer-readable storage medium. Background technique [0002] At present, there are many intent query methods, such as rule classification based on dictionaries and templates, and intent recognition based on classification models. There are some problems with these methods. For example, rule classification based on dictionaries and templates involves the construction of dictionaries and templates, which usually requires professionals in related fields to complete the construction of dictionaries and templates on the basis of understanding the business in this field, which consumes a lot of manpower and time. Intent recognition based on classification models involves marking text and intent types, and relies on a large amount of data and tag pairs. It is difficult to expand new ...

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): G06F16/33G06F16/35G06F40/205G06F40/284
CPCG06F16/3344G06F16/35G06F40/205G06F40/284
Inventor 邹常林
Owner 北京元年科技股份有限公司
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