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

Question segmentation method and device based on question number and text line, equipment and medium

A technology of text lines and question numbers, which is applied in the field of smart devices, can solve problems such as fuzzy test papers, models that cannot distinguish two adjacent questions, and multiple adjacent questions that cannot be separated.

Active Publication Date: 2020-09-11
GUANGDONG XIAOTIANCAI TECH CO LTD
View PDF9 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in some cases, the distribution of questions is more complex, and adjacent questions often have no clear boundaries, and the model sometimes cannot distinguish between two adjacent questions, so there are cases where multiple adjacent questions cannot be separated
In addition, since the picture to be recognized is uploaded by the user, there are blurring, tilting, folding and occlusion of the test paper, which reduces the accuracy of question segmentation to a certain extent.

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
  • Question segmentation method and device based on question number and text line, equipment and medium
  • Question segmentation method and device based on question number and text line, equipment and medium
  • Question segmentation method and device based on question number and text line, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0087] see figure 1 , figure 1 It is a schematic flowchart of a topic segmentation method disclosed in an embodiment of the present invention. like figure 1 As shown, the topic segmentation method includes the following steps:

[0088] 110. Acquire the target page picture, and detect the question number information and text line information in the target page picture.

[0089] The target page image includes one or more layouts, and each layout includes one or more questions. The image of the target page can be obtained by taking photos of carriers such as workbooks, exercise books, and test papers through an image acquisition device such as a camera. The image acquisition device can be integrated into smart devices, such as placing the carrier on a point reader or a tutor In the front, the carrier is photographed through the front camera of the smart device, or the image acquisition device is a discrete device capable of communicating with the smart device. The target pag...

Embodiment 2

[0152] see Figure 7 , Figure 7 It is a structural schematic diagram of a topic segmentation device disclosed in an embodiment of the present invention. like Figure 7 As shown, the topic segmentation device may include:

[0153] An acquisition unit 210, configured to acquire the target page picture, and detect the question number information and text line information in the target page picture;

[0154] A clustering unit 220, configured to determine the boundary coordinate information of each text line according to the text line information and the question number information, and use the boundary coordinate information to perform clustering to obtain one or more categories;

[0155] The first segmentation unit 230 is configured to use the minimum value of the boundary coordinates in each category as the boundary value of the layout, and perform layout segmentation on the target page picture to obtain one or more layouts;

[0156] The construction unit 240 is configured ...

Embodiment 3

[0186] see Figure 8 , Figure 8 It is a schematic structural diagram of an electronic device disclosed in an embodiment of the present invention. like Figure 8 As shown, the electronic equipment may include:

[0187] a memory 310 storing executable program code;

[0188] a processor 320 coupled to the memory 310;

[0189] Wherein, the processor 320 invokes the executable program code stored in the memory 310 to execute some or all of the steps in the method for segmenting a topic based on a question number and a text line in Embodiment 1.

[0190]The embodiment of the present invention discloses a computer-readable storage medium, which stores a computer program, wherein the computer program causes the computer to execute some or all of the steps in the method for segmenting a topic based on a question number and a text line in Embodiment 1.

[0191] The embodiment of the present invention also discloses a computer program product, wherein, when the computer program pro...

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 embodiment of the invention discloses a question segmentation method and device based on topic numbers and text lines, equipment and a medium. The method comprises the steps of obtaining a targetpage picture, and detecting question number information and text line information in the target page picture; determining boundary coordinate information of the text lines, and clustering to obtain categories; taking the minimum value of the boundary coordinates in the category as the boundary value of the layout, and carrying out layout segmentation on the target page picture to obtain the layout; determining leading rows and non-leading rows of the layout, and determining the leading row associated with each non-leading row according to the position relationship between the leading rows andthe non-leading rows so as to construct questions by the leading rows and the non-leading rows; and calculating boundary information of the questions according to the text line information of the leading lines and the non-leading lines in the questions, and segmenting each question. According to the method of the invention, by combining the question number and the text line information, the structural relationship of the questions is fully mined, the problem that the adjacent questions are easy to confuse is solved, and the question segmentation accuracy is improved.

Description

technical field [0001] The present invention relates to the technical field of intelligent equipment, in particular to a method, device, electronic equipment and storage medium for segmenting a topic based on a topic number and a text line. Background technique [0002] The current method for the topic segmentation method in the image is usually to train an end-to-end topic segmentation model, and divide different topics according to the topic range. However, in some cases, the distribution of questions is more complex, and adjacent questions often have no clear boundaries, and the model sometimes cannot distinguish between two adjacent questions, so there are cases where multiple adjacent questions cannot be separated. In addition, because the pictures to be recognized are uploaded by users, there are blurring, tilting, wrinkles and occlusions in the test paper, which reduces the accuracy of question segmentation to a certain extent. Contents of the invention [0003] In...

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
IPC IPC(8): G06K9/00G06K9/20G06K9/34G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V30/414G06V10/22G06V10/267G06N3/045G06F18/23213Y02D10/00
Inventor 尹磊邓小兵张春雨
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