Image-text content duplication judgment method and device
A technology of graphics, text and content, applied in the field of information processing, can solve the problems of low similarity judgment accuracy, difficult choice, and low recall rate, so as to improve the overall efficiency and judgment effect, improve the keyword extraction effect, and improve the recall rate. rate effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0057] Embodiment 1 of the present invention provides a method for judging repetition of graphic content, figure 1 An implementation flowchart of a method for judging repetition of graphic and text content provided by an embodiment of the present invention, as shown in figure 1 As shown, the method includes the following steps:
[0058] S1: Establish a word weight model.
[0059] S2: Generate a graphic-text comparison data set: collect sample graphic content, use the word weight model to extract the first preset number of article keywords in each sample graphic content, and calculate the second preset number of images in the sample graphic content The image comparison value of each sample is constructed to construct a graphic-text comparison data set including article keywords and image comparison values of each sample graphic content.
[0060] In this embodiment, the first preset number may be 18, and the second preset number may be 3, which can be adaptively changed acco...
Embodiment 2
[0111] This embodiment provides a device for judging repetition of graphic and text content, which is used to implement the method described in Embodiment 1, such as Image 6 As shown, it is a structural block diagram of the device for judging repetition of graphic and text content in this embodiment, including:
[0112] Word weight model building module 10: for setting up word weight model;
[0113] Generating graphic-text comparison data set module 20: used to collect sample graphic content, use the word weight model to extract the first preset number of article keywords in each sample graphic content, and calculate the second preset number of sample graphic content The image comparison value of the number of images, constructing a graphic comparison data set including article keywords and image comparison values of each sample graphic content;
[0114] Carry out image-text similarity comparison module 30: used to obtain the first preset number of target article keywords ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


