Live Streaming Video Interaction via Gesture Recognition and Special Effects

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current live video interaction methods are limited by a simple mode of presentation, resulting in a restricted sense of participation for users interacting with live streamers, primarily relying on text and images in a fixed interface.

Innovation Solution

An interaction method that captures and displays both live streaming video and user images in the same video play box, recognizes user gestures, and applies corresponding video special effects by matching gestures with a preset table, enhancing interaction through seamless stitching and dynamic video effects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If interaction is presented in real time using text and images in a fixed area, then the interaction can be implemented, but the mode of presentation is simple and the sense of participation is limited

Engineering Contradiction:
Improveinteraction modeVSAvoidinterface structure
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent transitions from traditional text/image interaction in a fixed area to a spatial dimension approach by displaying the user's video feed alongside the live streamer's video in the same video play box. This dimensional change allows gestures to be visually connected with the streamer, creating a more immersive and versatile interaction mode without significantly complicating the interface structure

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The patent captures the user's video image in real-time and displays it as a copy within the video play box next to the live streamer's video. This copying approach enables gesture recognition and visual connection effects without requiring complex hardware modifications, maintaining interface simplicity while enhancing interaction versatility

Inventive Principle:
Principle #26Copying

2Adaptability or versatility

If user video and live streamer video are displayed in the same video play box, then the sense of participation is strengthened, but the interface complexity increases

Engineering Contradiction:
Improveinteraction presentationVSAvoidvideo display system
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent merges the user's video feed with the live streamer's video feed into a single video play box, displaying both videos simultaneously in different regions. This merging approach strengthens the sense of participation by visually connecting the user with the streamer, while the unified video play box structure avoids significant interface complexity increases

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The video play box is segmented into different regions: one region displays the live streamer's video and another region displays the user's captured video. This segmentation allows both videos to coexist in the same play box without conflict, enabling enhanced interaction presentation while maintaining a manageable video display system structure

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS11778263B2Live streaming video interaction method and apparatus, and computer device
Publication Date: 2023.10.03 SHANGHAI HODE INFORMATION TECH CO LTD
  • US11778263B2 patent drawing
  • US11778263B2 patent drawing
  • US11778263B2 patent drawing

AI summary

The present application discloses techniques of interacting with live videos. The techniques comprise obtaining a streaming video of a live streamer and images of a user captured in real time by a user terminal, and displaying the streaming video and the image of the user in a same video play box; obtaining and recognizing a first gesture of a user in the images of the user, and comparing the first gesture with a second gesture included in a preset table, wherein the preset table comprises information indicating corresponding relationships between gestures and special effects; obtaining a first special effect corresponding to the second gesture by querying the preset table when the first gesture matches with the second gesture; and displaying the first special effect in the video play box.