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

A learnable mass information high-dimensional graph interactive display method

A high-dimensional graphics and interactive technology for information, applied in the field of human-computer interaction, can solve problems such as user information overload, and achieve the effect of improving accuracy

Active Publication Date: 2019-06-21
集智学园(北京)科技有限公司 +1
View PDF7 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The influx of a large amount of target information has led to information overload for users, so they have to screen and filter the information and only choose the information they are interested in

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 learnable mass information high-dimensional graph interactive display method
  • A learnable mass information high-dimensional graph interactive display method
  • A learnable mass information high-dimensional graph interactive display method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] Below, we take the example of displaying a large number of courses, each of which has certain text description data, and use this system method to display. We hope to display multiple such courses in a two-dimensional space. The technical solution of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0060] The basic process of the inventive method is as figure 1 As shown, it specifically includes the following steps:

[0061] Step 1: Feature extraction of target information (here, the information of each course).

[0062] 1.1) Extract the keyword (text) feature information of the target.

[0063] This part uses text segmentation technology, TF-IDF and other technologies to extract the keyword feature information of the text.

[0064] Take one of the lessons "Machine Learning Thinking" as an example:

[0065]

[0066]

[0067]

[0068] 1.2) Process the information features of the target into a position r...

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

According to a learnable mass information high-dimensional graph interactive display method provided by the invention, an idea of displaying information in a high-dimensional space in a graphical manner is provided, so that information of larger size and higher effectiveness is transmitted in the high-dimensional space. In order to avoid generation of informationized load in the high-dimensionalspace, a hierarchical display mode is introduced, different detail information of a target can be organized into multi-scale features in a graph form, and the multi-scale features are dynamically displayed in a graph zooming process. In the information display mode, the representation learning technology and the natural language processing technology are creatively used for extracting target features, and different weight modes are given to the features according to indexes such as the importance degree of the features, so that a traditional character introduction mode is replaced, and a target is comprehensively and accurately displayed to a user. Interactive behaviors of a user and a system can be captured, and a displayed graphical interface is automatically optimized in combination with behavior data of the user and inherent characteristics of a to-be-displayed target, so that an unsupervised reinforcement learning system is formed.

Description

technical field [0001] The invention belongs to the innovation of human-computer interaction technology in the form of mass information display, and specifically involves representation learning and feature extraction of content and interrelated structures, NLP technology such as automatic text summarization, front-end visualization technology, and hierarchical display technology based on canvas. Compared with the traditional one-dimensional display form, the high-dimensional information display method of the present invention can provide rich information and interaction. Background technique [0002] With the ultra-high-speed development of the Internet industry in recent years, APPs are rampantly occupying the desktops of mobile phones; various PC sites are also emerging one after another, forming one after another increasingly large systems on the Internet. These platforms cover a wide range of content and have touched almost all the details of human life, from shopping, ...

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): G06F9/451G06F3/0487
Inventor 张江陶如意林意灵张章
Owner 集智学园(北京)科技有限公司
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