AR Interface for ML Model Selection and Consent
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users are often unaware of the machine learning models used in computations, leading to sub-optimal analysis and inefficient resource usage, as they cannot select or understand the models employed, resulting in potential misuse of unwanted or less preferred models.
Innovation Solution
A computing platform that utilizes augmented reality (AR) to illustrate machine learning model operations and allows users to consent to model applications, with the option to select alternative models, and records consent information on a distributed ledger, ensuring transparency and efficient resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If machine learning models are applied without user awareness or selection capability, then processing resources are consumed and outputs are produced, but users cannot understand or control which models are used leading to sub-optimal analysis
Solution Approach 1:
The patent introduces an augmented reality interface as an intermediary between the machine learning model and the user. This AR interface visually represents the model's structure, inputs, and outputs, allowing users to understand and interact with the model without requiring deep technical knowledge. The AR representation acts as a mediator that translates complex model operations into comprehensible visual forms, enabling informed user decisions while maintaining processing efficiency.
Solution Approach 2:
The system performs preliminary actions by presenting multiple model options to the user through the AR interface before actual processing begins. Users can review model characteristics, inputs, and expected outputs in advance, making informed selections before resources are committed. This preliminary review process prevents sub-optimal model selection while maintaining efficient resource utilization by only processing chosen models.
2Loss of information
If multiple machine learning models are presented for user selection, then model selection transparency is improved, but system complexity and user interaction requirements increase
Solution Approach 1:
The AR interface applies local quality by providing detailed, context-specific information about each model component only when relevant. Instead of overwhelming users with all possible model details simultaneously, the system presents information locally - showing specific model attributes, inputs, and outputs based on user focus and interaction. This selective information presentation maintains transparency while reducing perceived complexity.
Solution Approach 2:
The patent transitions the model selection interface from traditional two-dimensional screens to three-dimensional augmented reality space. This dimensional change allows complex model information to be spatially organized and manipulated, enabling users to navigate and understand model relationships more intuitively. The AR environment provides depth and spatial context that reduces the cognitive load of processing complex model selections.
3Reliability
If users can select and understand machine learning models through AR representation, then model preference and analysis quality improve, but processing time and computational overhead increase
Solution Approach 1:
The system performs preliminary model evaluation and AR representation generation before final model selection and processing. By pre-computing model characteristics, inputs, and visual representations, the system enables rapid user decision-making without sacrificing analysis quality. This preliminary preparation ensures that when users make selections, the actual processing can begin immediately with the chosen model, minimizing overall processing time.
Solution Approach 2:
The AR interface creates simplified copies or representations of the complex machine learning models rather than requiring users to interact with the full computational complexity. These AR representations capture the essential characteristics and behavior of the models in an accessible format, allowing users to make informed selections without the computational overhead of running actual model executions during the selection phase.
Data Source
AI summary
Aspects of the disclosure relate to computing hardware and software for ML model selection and AR. A computing platform may select a ML model. The computing platform may send, to an AR client device, an AR representation of the ML model that illustrates operation of the ML model. The computing platform may receive, from the AR client device, consent information indicating whether or not consent is provided to apply the ML model. Once consent is received, the computing platform may: 1) write, to a distributed ledger, the consent information and a identifier of the ML model, 2) apply the ML model to produce a ML output customized based on a user of the AR client device, and 3) send, to the AR client device, commands directing the AR client device to display the ML output, which may cause the AR client device to display the ML output.