Method and device for realizing natural language understanding in human-computer interaction system

A natural language understanding and human-computer interaction technology, applied in the field of natural language understanding, can solve problems such as the accuracy of performance-limited word segmentation methods, the inability to dynamically update dictionaries, and the flooding of dictionary knowledge, so as to provide acquisition efficiency and save manual labeling costs , the effect of improving performance

Pending Publication Date: 2021-04-09
HUAWEI TECH CO LTD
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the method of introducing dictionary knowledge into natural language understanding tasks mainly has two problems. On the one hand, only through word matching, the noise will be very large, and dictionary knowledge will be submerged; , the performance of such a system will be limited by the accuracy of the word segmentation method, and the model needs to be pre-trained according to the dictionary, so the model cannot dynamically update the dictionary

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 and device for realizing natural language understanding in human-computer interaction system
  • Method and device for realizing natural language understanding in human-computer interaction system
  • Method and device for realizing natural language understanding in human-computer interaction system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0105] In order to facilitate understanding of the embodiments of the present application, some terms or concepts used in the embodiments of the present application are firstly introduced below.

[0106] (1) Term disambiguation model

[0107] The input of the entry disambiguation model includes sentences and entry information, the entry information is used to represent the entries contained in the sentence, and the entry disambiguation model is used to judge the words represented by the entry information clause conforms to the semantics of the stated statement.

[0108] Wherein, the term information may represent one or more terms included in the sentence, and each term may be a reasonable term or an unreasonable term in the sentence. The reasonable term mentioned here refers to the term conforming to the semantics of the sentence, otherwise it is an unreasonable term.

[0109] For example, when the sentence is "I want to hear that it will rain tomorrow.", the entries in the...

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 and a related device for realizing natural language understanding in the field of artificial intelligence. According to the technical scheme provided by the invention, the information of the entries in the statement input by the user can be inquired from the dictionary, disambiguation processing is carried out on the entry information, and then the intention and related key information of the statement are understood according to the entry information obtained through disambiguation. According to the technical scheme provided by the invention, the performance of natural language understanding can be improved without additional data annotation, and the system for realizing natural language understanding is simple to maintain, so that the user experience can be improved.

Description

[0001] This application claims the priority of the Chinese patent application submitted to the State Intellectual Property Office of China on May 20, 2020, with the application number 202010429245.1 and the application name "Method and device for realizing natural language understanding in human-computer interaction system", all of which The contents are incorporated by reference in this application. technical field [0002] The present application relates to the field of artificial intelligence, in particular to a method and device for realizing natural language understanding in a human-computer interaction system. Background technique [0003] Artificial intelligence (AI) is a theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, acquire knowledge and use knowledge to obtain the best results. In other words, artificial intelligence is the branch of compute...

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): G06F40/211G06F40/289G06F40/30G06F16/35
CPCG06F40/211G06F40/289G06F40/30G06F16/35
Inventor 王宝军张钊徐坤张宇洋尚利峰李林琳
Owner HUAWEI TECH 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