Image-Video Association for Relevant E-Commerce Listing Playback

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Users on e-commerce platforms face frustration when viewing irrelevant or excessively long videos uploaded with item listings, as they struggle to easily access relevant information.

Innovation Solution

A method and system that processes image and video data using machine-learning models to determine similarity values, linking relevant video portions with images, allowing users to navigate between images and video frames or clips seamlessly.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If a video is uploaded with an item listing to provide additional information, then the information completeness is improved, but the video may become irrelevant or too long causing user frustration

Engineering Contradiction:
Improveinformation completenessVSAvoiduser experience
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The patent segments the video into multiple clips based on detected key moments that correspond to different images of the item. This segmentation allows users to access only relevant portions of the video associated with specific images, rather than playing through the entire video, thus maintaining information completeness while improving ease of operation.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary system that automatically analyzes video content, identifies key moments, and creates links between video clips and images. This intermediary process resolves the contradiction by automatically organizing the video content to match user viewing patterns, eliminating the need for users to manually navigate irrelevant content.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Loss of information

If the entire video is displayed to users viewing an item, then all video information is available, but users must watch the complete video even for brief moments of interest

Engineering Contradiction:
Improvevideo information availabilityVSAvoidvideo viewing time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The patent performs preliminary analysis of the video content before user viewing, automatically detecting key moments and segmenting the video into relevant clips. This preliminary action prepares the video content in advance, allowing users to directly access specific segments without watching the entire video, thus preserving all video information while significantly reducing viewing time.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent implements dynamic video playback where the video player adapts to user interactions by jumping to specific segments based on image context. This dynamic approach allows the video playback behavior to change based on user needs, maintaining full video information availability while optimizing viewing time through intelligent segment navigation.

Inventive Principle:
Principle #15Dynamics

3Measurement precision

If users must view the complete video to find relevant moments, then all video content is reviewed, but user time and patience are significantly consumed

Engineering Contradiction:
Improvevideo relevance accuracyVSAvoidtime to find relevant content
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments the video into multiple clips based on detected key moments that correspond to different images of the item. This segmentation allows users to access only relevant portions of the video associated with specific images, rather than playing through the entire video, thus maintaining information completeness while improving ease of operation.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary analysis of the video content before user viewing, automatically detecting key moments and segmenting the video into relevant clips. This preliminary action prepares the video content in advance, allowing users to directly access specific segments without watching the entire video, thus preserving all video information while significantly reducing viewing time.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP4177846B1Image and video instance association for an e-commerce applications
Publication Date: 2025.12.03 EBAY INC
  • EP4177846B1 patent drawingFigure 1
  • EP4177846B1 patent drawingFigure 2
  • EP4177846B1 patent drawingFigure 3

AI summary

A process for linking related images and videos is disclosed. The process can include receiving listing information including the images and the video, processing the images using an image processor to determine one or more image descriptors, processing the video using a video processor to determine video descriptors, comparing the image descriptors to the video descriptors, calculating a similarity value for each of the image descriptors in relation to each of the video descriptors, and linking the videos and the images based upon the calculated similarity value. The method can also include causing the display of a user interface including a video linking user interface element operable to cause playback of a relevant portion of the video linked with the displayed image and an image linking user interface element operable to cause display of a relevant image linked with a portion of the video playback.