Interactive Video Layers for Object Lookup During Video Conferences

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional video conferencing systems do not enable interactions with objects depicted within video streams, leading to inefficiencies such as disrupted discussions and delayed or missed responses when participants want to learn more about objects in the background.

Innovation Solution

An interactive video layer system that allows interactions with objects within video layers of video streams during a conference, enabling pop-up information, hyperlinks, or separate communication modalities based on object interactions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If participants verbally discuss objects in the background during video conferences, then information about objects can be shared, but the discussion is disrupted and responses are delayed

Engineering Contradiction:
Improveinformation accessibilityVSAvoiddiscussion efficiency
Core Design Contradiction:
Loss of informationVSProductivity

Solution Approach 1:

The patent introduces an intermediary system (interactive video layer with object detection and pop-up information) that mediates between participants and background objects. When a participant wants information about an object, the system automatically detects the object, retrieves relevant information, and displays it in a pop-up window, eliminating the need for verbal discussion and maintaining discussion flow while providing instant information access.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If conventional video conferencing systems display only video streams, then system complexity is low, but interactions with objects are not enabled

Engineering Contradiction:
Improveobject interaction capabilityVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the video stream into multiple interactive video layers, where each layer can be independently processed for object detection and interaction. This segmentation allows the system to add interactive capabilities to specific regions or objects within the video stream without requiring complete system redesign, thereby enabling object interaction while managing complexity through modular processing.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary interactive video layer system that sits between the conventional video conferencing system and the user interface. This intermediary layer handles object detection, information retrieval, and pop-up display functions, allowing the core video conferencing system to remain relatively simple while gaining enhanced adaptability and object interaction capabilities.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Loss of information

If participants manually search for object information during conferences, then information can be found, but time is lost and discussion flow is interrupted

Engineering Contradiction:
Improveinformation completenessVSAvoidresponse time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The patent implements preliminary action by pre-processing video streams to detect and identify objects in advance, and pre-retrieving information about detected objects before they are queried. When a participant interacts with an object, the information is already prepared and ready for immediate display in a pop-up window, eliminating search time and maintaining discussion flow while ensuring complete information availability.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS20250286980A1Object Interaction During A Contact Center Engagement Video Conference
Publication Date: 2025.09.11 ZOOM COMMUNICATIONS INC
  • US20250286980A1 patent drawing
  • US20250286980A1 patent drawing
  • US20250286980A1 patent drawing

AI summary

Interactions with objects depicted within video streams displayed during a video conference are detected to cause information associated with the interacted objects to be presented. During a video conference, multiple video layers of a video stream obtained from a first participant device connected to the video conference are identified. An interaction with an object within one of those multiple video layers is detected during the video conference, in which the interaction is from a second participant device connected to the video conference. Based on the interaction, information associated with the object is presented during the video conference within a graphical user interface associated with the video conference. The video stream may, for example, initially include a background layer, a foreground layer, and an overlay layer. Interactive video layers corresponding to each of those initial layers may be introduced to receive interactions with objects depicted therein.