20240046122. CROSS-MEDIA CORRESPONDING KNOWLEDGE GENERATION METHOD AND APPARATUS simplified abstract (ZHEJIANG LAB)

From WikiPatents
Jump to navigation Jump to search

CROSS-MEDIA CORRESPONDING KNOWLEDGE GENERATION METHOD AND APPARATUS

Organization Name

ZHEJIANG LAB

Inventor(s)

Feng Lin of Hangzhou (CN)

Yunhe Pan of Hangzhou (CN)

CROSS-MEDIA CORRESPONDING KNOWLEDGE GENERATION METHOD AND APPARATUS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240046122 titled 'CROSS-MEDIA CORRESPONDING KNOWLEDGE GENERATION METHOD AND APPARATUS

Simplified Explanation

The patent application describes a method and apparatus for generating knowledge units across different media formats. The method involves generating a second knowledge unit based on a first knowledge unit from a predefined medium. It also includes generating feature parameter vectors for both knowledge units and mapping them onto a two-dimensional spherical feature surface. The method further involves indexing the feature points on the surface and establishing a bidirectional index corresponding relationship between the first and second knowledge units.

  • The method generates a second knowledge unit based on a first knowledge unit from a different medium.
  • Feature parameter vectors are generated for both knowledge units.
  • The feature parameter vectors are mapped onto a two-dimensional spherical feature surface.
  • The feature points on the surface are indexed to establish a corresponding relationship between the knowledge units.

Potential applications of this technology:

  • Cross-media content generation and adaptation.
  • Knowledge transfer and integration between different media formats.
  • Enhanced search and retrieval of information across different media.

Problems solved by this technology:

  • Difficulty in transferring knowledge between different media formats.
  • Lack of efficient indexing and retrieval methods for cross-media content.
  • Limited ability to adapt and generate content across different media.

Benefits of this technology:

  • Improved knowledge transfer and integration across different media formats.
  • Enhanced search and retrieval capabilities for cross-media content.
  • Increased efficiency in generating and adapting content across different media.


Original Abstract Submitted

a method and an apparatus for cross-media corresponding knowledge generation. the method comprises: generating a second knowledge unit of a second medium according to a first knowledge unit of a predefined first medium; generating a first feature parameter vector corresponding to the first knowledge unit and a second feature parameter vector corresponding to the second knowledge unit; mapping the first feature parameter vector and the second feature parameter vector to a corresponding two-dimensional spherical feature surface to obtain a first feature point of the first feature parameter vector on the corresponding two-dimensional spherical feature surface and a second feature point of the second feature parameter vector on the corresponding two-dimensional spherical feature surface; indexing the first feature point and the second feature point to obtain a first index and a second index; and generating a bidirectional index corresponding relationship between the first knowledge unit and the second knowledge unit.