Microsoft technology licensing, llc (20240202240). GRAPH-BASED VIDEO INDEXING TO SUPPORT QUERYING WITH IMPLICIT RELATIONS simplified abstract
Contents
GRAPH-BASED VIDEO INDEXING TO SUPPORT QUERYING WITH IMPLICIT RELATIONS
Organization Name
microsoft technology licensing, llc
Inventor(s)
Ika Bar-menachem of Herzeliya (IL)
GRAPH-BASED VIDEO INDEXING TO SUPPORT QUERYING WITH IMPLICIT RELATIONS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240202240 titled 'GRAPH-BASED VIDEO INDEXING TO SUPPORT QUERYING WITH IMPLICIT RELATIONS
The abstract describes a video indexing system that generates descriptive metadata for a video, including identifiers for multiple detections corresponding to different subjects in the video. The system creates a relational graph data for the video based on these detections, with nodes representing each subject. A knowledge graph is queried with unique identifiers for the subjects to retrieve implicit relational data, which is then merged with the relational graph data to create a merged relational graph. A search engine uses this merged graph to identify relevant video content based on implicit relations and presents search results on a user device.
- Simplified Explanation:
- A system indexes videos by generating metadata for different subjects in the video and creating a relational graph. - It queries a knowledge graph to retrieve implicit relational data for the subjects and merges it with the relational graph. - A search engine uses this merged graph to identify relevant video content based on implicit relations.
- Key Features and Innovation:
- Descriptive metadata generation for videos. - Creation of relational graph data based on detections. - Querying a knowledge graph for implicit relational data. - Merging implicit relational data with the relational graph. - Search engine utilization for identifying relevant video content.
- Potential Applications:
- Video content organization and search optimization. - Enhanced video recommendation systems. - Improved video content understanding and analysis.
- Problems Solved:
- Efficient video indexing and metadata generation. - Enhanced search capabilities for video content. - Better organization and categorization of video data.
- Benefits:
- Improved user experience in searching for video content. - More accurate and relevant video recommendations. - Enhanced understanding of video content relationships.
- Commercial Applications:
- "Advanced Video Indexing System for Enhanced Search and Recommendation" - Potential use in video streaming platforms, content management systems, and video analytics tools.
- Questions about Video Indexing System:
1. How does the system differentiate between different subjects in a video? 2. What are the implications of merging implicit relational data with the relational graph for search engine optimization?
Original Abstract Submitted
a video indexing system generates descriptive metadata for a video including identifiers for each of multiple detections that each correspond to a select one of multiple subjects that appear in the video. these detections are used to create relational graph data for the video, where the relational graph data includes nodes corresponding to each of the multiple subjects that appear in the video. a knowledge graph is queried with unique identifiers corresponding to the multiple subjects of the video to retrieve implicit relational data for each of the multiple subjects, and a merged relational graph is created by merging the implicit relational data retrieved from the knowledge graph with the relational graph data created for the video. a search engine uses the merged relational graph to identify video content relevant to a user query that is based on an implicit relation. search results identifying the relevant content are presented on a user device.
