Context-Aware Content Display for Electronic Screens
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Electronic displays often waste resources by presenting content that is not consumed by targets due to incorrect timing or lack of relevance, as existing systems fail to dynamically adjust content based on the environment and target characteristics.
Innovation Solution
A content control platform that uses image recognition models and machine learning to identify objects and targets in an environment, determining relationships and selecting appropriate content for display, thereby optimizing content presentation to match the audience and context.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If content is displayed continuously on electronic displays, then the display remains active and visible, but resources are wasted by presenting content that is not consumed by targets
Solution Approach 1:
The system dynamically adjusts content display based on real-time environmental analysis using image capture devices and machine learning models. Content presentation is adapted according to detected objects, targets, and contextual relationships, transitioning from static continuous display to dynamic context-aware display that activates only when relevant content and targets are present.
Solution Approach 2:
The system changes display parameters (content selection, timing, duration) based on environmental parameters detected by image analysis. Machine learning models analyze image streams to determine optimal display parameters including what content to show, when to show it, and to whom, thereby eliminating wasteful continuous display of irrelevant content.
2Measurement precision
If multiple object recognition models are used to identify objects and targets, then content selection accuracy is improved, but system complexity increases
Solution Approach 1:
The system segments the content selection task into multiple specialized machine learning models, each trained to identify specific object types or characteristics in the environment. This segmentation allows each model to focus on specific recognition tasks, improving overall accuracy while maintaining manageable complexity through modular architecture.
Solution Approach 2:
Multiple object recognition models work together within a unified content selection system that integrates their outputs. The system universally applies environmental analysis results to determine content presentation decisions, combining the capabilities of multiple specialized models into a single multi-functional content delivery system.
Data Source
AI summary
A device may receive an image stream of an environment of an electronic display. The device may detect that a target is in the environment, wherein the target is detected based on the image stream including an image associated with the target. The device may identify that a first object is associated with the target, wherein the first object is identified based on the object recognition model being trained to recognize the first object. The device may determine a characteristic of the first object and may determine that a second object is in the environment. The device may generate content that is to be displayed via the electronic display, wherein the content is generated based on the characteristic of the first object and a characteristic of the second object. The device may cause the content to be displayed via the electronic display to permit the target to access the content.