Intuitive Computing Platform for Smartphone AR Overlays
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies face challenges in enabling smartphones to autonomously understand and respond to their environment due to the complexity of processing vast amounts of visual and auditory data, particularly in identifying relevant stimuli and determining appropriate user desires without excessive resource consumption or time delays.
Innovation Solution
The implementation of an intuitive computing platform that employs local device processing in conjunction with cloud resources, utilizing image processing arrangements, context information, and recognition agents to progressively understand and respond to user stimuli, with features like baubles for visual object interaction and dynamic resource allocation based on success and user interest.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If cloud computing resources are used to process image recognition, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The patent segments the image processing workload between local device (portable system) and cloud resources. The local device performs initial image capture and basic processing, while cloud resources handle more computationally intensive recognition tasks. This segmentation allows the system to balance processing time and accuracy by distributing tasks appropriately across different processing locations.
Solution Approach 2:
The system performs preliminary image processing and analysis on the portable device before submitting to cloud resources. This preliminary action includes initial frame capture, basic feature extraction, and pre-processing that prepares the data for more advanced cloud-based recognition, thereby reducing the time cloud resources need to process the complete task.
2Measurement precision
If extensive image processing is performed, then measurement precision is improved, but use of energy increases
Solution Approach 1:
The patent divides processing tasks between the portable device and cloud resources to reduce local energy consumption. Energy-intensive tasks such as complex image recognition and analysis are offloaded to cloud servers, while the portable device performs lighter local processing. This segmentation allows accurate environmental stimulus identification without excessive power consumption.
Solution Approach 2:
The system applies partial processing locally and partial processing in the cloud, rather than performing all processing on the portable device. This partial action approach achieves the necessary measurement precision for environmental stimulus identification while avoiding the excessive energy consumption that would result from complete local processing.
3Productivity
If more processing resources are allocated, then productivity is improved, but device complexity increases
Solution Approach 1:
The patent introduces cloud resources as an intermediary to handle complex processing tasks. Instead of requiring the portable device to have extensive local processing capabilities (which would increase device complexity), the system uses cloud-based processing power as an intermediary resource. This allows high productivity in responding to user stimuli while keeping the portable device itself relatively simple.
Solution Approach 2:
The system employs a multi-functional architecture where the portable device can operate with varying levels of local processing capability depending on cloud availability. The same device can function with minimal local processing when cloud resources are accessible, and with enhanced local processing when cloud resources are unavailable. This universality allows high productivity without permanently increasing device complexity.
4Reliability
If comprehensive data processing is performed, then reliability is improved, but loss of time increases
Solution Approach 1:
The system performs preliminary analysis of captured images and sensor data on the portable device to quickly identify obvious patterns and user intents. This preliminary action allows the system to provide reliable user desire inference for straightforward cases without requiring time-consuming comprehensive cloud processing, thereby maintaining both reliability and responsiveness.
Solution Approach 2:
The patent segments data processing into multiple stages: initial local analysis for quick reliability assessment, followed by selective cloud-based comprehensive processing only when needed. This segmentation allows the system to achieve reliable user desire inference for common scenarios quickly, while reserving comprehensive processing for more complex or uncertain cases where additional time is acceptable.
Data Source
AI summary
A smart phone receives imagery depicting a scene, and overlays indicia (augmentations) corresponding to supplemental data that relate to one or more features in the scene. The overlaid indicia are narrowed from a larger universe of options based on two criteria. A first criterion comprises factors such as actions previously taken by the user or third parties expressing interest or disinterest in presented indicia, time of day, and topical preference data for the user. A second criterion comprises a setting of a user-settable visual verbosity control. A user can thereby vary how much information, identified using the first criteria, is overlaid on the displayed scene, by varying the setting of the visual verbosity control. A great number of other features and arrangements are also detailed.