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

Multi-dimensional visualization multi-source heterogeneous data multi-layer drnn deep fusion method

A technology of multi-source heterogeneous data and fusion method, which is applied in the field of deep fusion of multi-source heterogeneous data and multi-layer DRNN, can solve the problems that the direct display of heterogeneous data cannot be guaranteed

Active Publication Date: 2022-02-22
沈阳瑞初科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current visualization technology for heterogeneous information cannot guarantee the direct display of heterogeneous data

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
  • Multi-dimensional visualization multi-source heterogeneous data multi-layer drnn deep fusion method
  • Multi-dimensional visualization multi-source heterogeneous data multi-layer drnn deep fusion method
  • Multi-dimensional visualization multi-source heterogeneous data multi-layer drnn deep fusion method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] like figure 1 , figure 2 and image 3 As shown, the multi-dimensional visualized multi-source heterogeneous data multi-layer DRNN deep fusion method is characterized in that: the method steps include:

[0041] Step 1: Establish DRNN neural network;

[0042] For multi-source heterogeneous data, establish a recursive self-learning network based on deep neural network; establish a deep learning model, and form a recursive network at each layer. The recursive network uses deep self-learning to generate a DRNN network; build a DRNN network close to the underlying data There is no link between the nodes in the layer, and fuzzy fusion judgment is used in the farthest part, and the corresponding generation model is obtained by increasing the number of hidden layers through forward self-encoding.

[0043] The specific method of establishing a recursive self-learning network based on deep warp network is:

[0044] Using a layered architecture, each layer adaptively establish...

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 belongs to the field of artificial intelligence education, and in particular relates to a multi-dimensional visualized multi-source heterogeneous data multi-layer DRNN deep fusion method. The steps of the method include: step 1: establishing a DRNN neural network; inputting multi-source heterogeneous data into the DRNN neural network to form a DRNN training template; step 3: establishing the forward output of a single-layer neuron individual of the DRNN network; wherein the single-layer network serves as Activated fusion function; Step 4: Establish the weight reconstruction and correction of the DRNN network; the correction exists as a fusion function; Step 5: In the data fusion layer of the DRNN network, the feature output is obtained through data feature fusion. The present invention proposes a fusion framework, which can perform feature-level fusion for different multi-source heterogeneous data.

Description

Technical field: [0001] The invention belongs to the field of artificial intelligence education, and in particular relates to a multi-dimensional visualized multi-source heterogeneous data multi-layer DRNN deep fusion method. Background technique: [0002] Visualization is the theory, method and technology of using computer graphics and image processing technology to convert data into graphics or images and display them on the screen for interactive processing. It involves many fields such as computer graphics, image processing, computer vision, and computer-aided design, and has become a comprehensive technology for studying a series of issues such as data representation, data processing, and decision analysis. The virtual reality technology that is currently developing rapidly is also based on the visualization technology of graphics and images. [0003] The development of computer graphics in recent years has led to the formation of three-dimensional representation techn...

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): G06K9/62G06V10/80G06V10/82G06N3/04G06N3/08
CPCG06N3/08G06N3/044G06N3/045G06F18/253
Inventor 罗晓东
Owner 沈阳瑞初科技有限公司
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

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