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

A method, device, and storage medium for feature representation of a topic

A technology of questions and electronic devices, which is applied in the field of question feature representation methods, devices and storage media, can solve problems such as excavation, and achieve the effect of improving accuracy

Active Publication Date: 2022-06-21
PINGAN INT SMART CITY TECH CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this semantic relationship is difficult to be discovered by traditional methods (topic models, word vectors)

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
  • A method, device, and storage medium for feature representation of a topic
  • A method, device, and storage medium for feature representation of a topic
  • A method, device, and storage medium for feature representation of a topic

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] Embodiments of the subject feature representation method, device and storage medium according to the present invention will be described below with reference to the accompanying drawings. As those of ordinary skill in the art would realize, the described embodiments may be modified in various different ways or combinations thereof, all without departing from the spirit and scope of the present invention. Accordingly, the drawings and description are illustrative in nature and are not intended to limit the scope of protection of the claims. Furthermore, in this specification, the drawings are not drawn to scale, and the same reference numerals refer to the same parts.

[0024] figure 1 A flow chart showing the method for expressing topic features in this embodiment, the method for expressing topic features includes the following steps:

[0025] In step S1, a plurality of knowledge points in the topic are acquired, a knowledge graph is formed through the relationship be...

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

This solution involves artificial intelligence and provides a feature representation method for the topic, including: obtaining multiple knowledge points in the topic, and forming a knowledge map through the relationship between the knowledge points: using a custom thesaurus to clean the text content, so that The text content only retains the words in the custom thesaurus; each word in the text content is converted into a word vector through the word vector algorithm; the formula is converted into a character vector through the character vector algorithm; through convolution-deconvolution The self-encoder converts the image into a pixel matrix; combines the entity vector, word vector, character vector, and pixel matrix of the knowledge map to form a topic information matrix. The feature data of the questions extracted by the present invention include all information such as text, formulas, images, characters, etc., and can improve the accuracy of math topic recommendation and math topic classification.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, and in particular, to a method, device and storage medium for characterizing a topic. Background technique [0002] At present, most of the topic feature extraction only extracts the text content in the topic, but does not extract the relationship between knowledge points, the content in the image, and the content in the formula. In mathematics, there are usually a large number of knowledge points, and the semantic relationship between the knowledge points can effectively expand the feature representation of the topic. However, this semantic relationship is difficult to be discovered by traditional methods (topic model, word vector). SUMMARY OF THE INVENTION [0003] In order to solve the above technical problems, the present invention provides a method for representing the characteristics of a topic, which is applied to an electronic device, including: [0004] Obtain multiple ...

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): G06F16/9032G06F16/907G06F16/33G06F16/36
CPCG06F16/9032G06F16/907G06F16/367G06F16/3344
Inventor 张家新
Owner PINGAN INT SMART CITY 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