Automated Anchor Image Selection for Video Search

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Manual gathering of metadata and representative images for videos in search engines is time-consuming, costly, and prone to human error, affecting the accuracy and precision of search results in video search engines.

Innovation Solution

Automated anchor image identification through Web crawling, where candidate images are filtered using rules to select a representative image for each video, ensuring accuracy and precision in search results.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual gathering of metadata and representative images is performed, then search results can be provided, but time consumption and cost increase significantly

Engineering Contradiction:
Improveaccuracy of search resultsVSAvoidtime for gathering metadata and images
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent applies preliminary action by automatically gathering and storing metadata and representative images during the web crawling phase before search queries are executed. The system pre-processes video content by extracting metadata (titles, descriptions, tags) and selecting representative images (thumbnails, key frames) during the indexing process, so that when a search is performed, the results are immediately available without requiring manual gathering at query time.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements self-service by enabling the video search system to automatically extract metadata and select representative images without human intervention. The system uses automated algorithms to crawl video content, extract relevant metadata fields, and identify suitable representative images based on predefined criteria, thereby serving itself rather than requiring manual processing for each video entry.

Inventive Principle:
Principle #25Self-service

2Reliability

If manual gathering of metadata and representative images is performed, then search results can be provided, but costs increase significantly

Engineering Contradiction:
Improveaccuracy of search resultsVSAvoidcost of gathering metadata and images
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The patent implements self-service by enabling the video search system to automatically extract metadata and select representative images without human intervention. The system uses automated algorithms to crawl video content, extract relevant metadata fields, and identify suitable representative images based on predefined criteria, thereby serving itself rather than requiring manual processing for each video entry.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent applies mechanics substitution by replacing the manual mechanical process of gathering and processing video metadata and images with automated computer-based systems. The system uses software algorithms to perform web crawling, metadata extraction, and image selection tasks that would otherwise require human operators, thereby eliminating labor costs and associated energy consumption.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If manual gathering of metadata and representative images is performed, then search results can be provided, but human error increases affecting accuracy and precision

Engineering Contradiction:
Improvespeed of providing search resultsVSAvoidaccuracy and precision of search results
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The patent implements self-service by enabling the video search system to automatically extract metadata and select representative images without human intervention. The system uses automated algorithms to crawl video content, extract relevant metadata fields, and identify suitable representative images based on predefined criteria, thereby serving itself rather than requiring manual processing for each video entry.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent applies mechanics substitution by replacing the manual mechanical process of gathering and processing video metadata and images with automated computer-based systems. The system uses software algorithms to perform web crawling, metadata extraction, and image selection tasks that would otherwise require human operators, thereby eliminating labor costs and associated energy consumption.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS9430478B2Anchor image identification for vertical video search
Publication Date: 2016.08.30 MICROSOFT TECHNOLOGY LICENSING LLC
  • US9430478B2 patent drawing
  • US9430478B2 patent drawing
  • US9430478B2 patent drawing

AI summary

Anchor images and information associated therewith are accumulated during a Web crawling operation. One or more rules are applied to the accumulated candidate anchor images to filter out candidate anchor images that are not appropriate for use as the anchor image for a particular target video. The remaining candidate anchor image is then selected as the anchor image for the particular video.