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

Method and device for identifying question type

A recognition method and a recognition device technology, which are applied in mechanical mode conversion, computer parts, graphic reading, etc., can solve problems such as the inability to accurately obtain the purpose of the test questions, the inability to accurately express in voice, and the limited use of voice products. Achieve the effects of avoiding device recognition actions, reducing device power consumption, and lowering requirements

Active Publication Date: 2022-07-01
GUANGDONG XIAOTIANCAI TECH CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Especially for voice electronic products used by children, such as learning machines, there will be a disadvantage when children use this voice product in the course of homework. When they do not know the words or cannot grasp the content of the test, they cannot express it accurately or do not know how to express it. , leading to the limited use of voice products in the process of analyzing semantics, and it is impossible to accurately obtain the test intent of the question type

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 identifying question type
  • Method and device for identifying question type
  • Method and device for identifying question type

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] The invention discloses a question type identification method, the embodiment is as follows figure 1 shown, including:

[0050] S101 collects the user's voice information;

[0051] S102 judges whether the voice information is recognition trigger information;

[0052] S103, when it is determined that the voice information is recognition trigger information, obtain the action information of the user;

[0053] S104, according to the action information of the user, obtain the question type image to be identified;

[0054]S105 performs image processing on the title image to be identified, to obtain title text information in the title image to be identified;

[0055] S106 Input the question type text information into the trained question type identification model, and identify and output the examination intention corresponding to the question type.

[0056] This solution obtains the question type identification model based on machine learning, and then uses the question t...

Embodiment 2

[0067] On the basis of the above embodiment, before the user uses the intelligent voice device to identify the question type, a question type identification model needs to be obtained through machine learning. Machine learning can use the acquired question type training sample set to train the initial question type recognition model, and obtain a trained question type recognition model. Specifically, as figure 2 shown, including:

[0068] S201 uses the acquired question type training sample set to train the initial question type identification model, and obtains a trained question type identification model;

[0069] S202 collects the user's voice information;

[0070] S203 judges whether the voice information is recognition trigger information;

[0071] S204, when it is determined that the voice information is recognition trigger information, obtain the action information of the user;

[0072] S205, according to the action information of the user, obtain the question imag...

Embodiment 3

[0077] In another embodiment of the method of the present invention, on the basis of the above method embodiment, for step S201, the initial question type identification model is trained by using the acquired question type training sample set, and the trained question type identification model is refined. . Specifically, as image 3 As shown, the question type identification method of this embodiment includes:

[0078] S301 establishes a question type library, and the question type library contains various question types;

[0079] S302 extracts the characteristics of each type of question type, and obtains the keywords and examination intention of each type of question type;

[0080] S303 According to the keywords and examination intentions of various types of questions, establish the classification of question type intentions,

[0081] S304 uses the question type and question type intention classification in the question type database to train the initial question type ide...

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 a question type identification method and device, wherein the question type identification method includes: collecting user's voice information; judging whether the voice information is identification trigger information; when it is judged that the voice information is identification trigger information, acquiring the user's action information; according to the user's action information, obtain the question type image to be identified; perform image processing on the question type image to be identified to obtain the question type text information in the question type image; input the question type text information into the trained question type recognition model , to identify the test intent corresponding to the output question type. The present invention solves the problem that when users do not know the words or cannot grasp the content of the examination, they cannot accurately express or do not know how to express them in speech, which leads to the limited use of speech products in the process of parsing semantics and the inability to accurately obtain the examination intention of the question type. technical problem.

Description

technical field [0001] The invention relates to the field of artificial intelligence, and in particular, to a question type identification method and device. Background technique [0002] With the development of artificial intelligence, smart device products have gradually entered people's lives, and their intelligence and convenience have been increasingly recognized by users. [0003] At present, there are many voice device products on the market. The user only needs to issue an instruction through the voice, and the voice device will execute the command according to the user's voice product after receiving the instruction. However, human language has diverse expressions and complex structural characteristics. The same meaning can have many expressions, and the same expression can have many meanings in different environments. Especially for the voice electronic products used by children, such as learning machines, the use of voice products by children in the process of ho...

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): G06F3/01
Inventor 魏誉荧
Owner GUANGDONG XIAOTIANCAI TECH CO LTD
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