User Interface for Confirming Unreliable Group Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in accurately tracking and identifying users within facilities, particularly in determining group membership and handling situations where automated systems experience low confidence or loss of tracking, leading to unreliable output.
Innovation Solution
The implementation of a facility management system that uses sensors and computer vision algorithms to track users, with the assistance of human associates to verify identification and group membership through image gallery data and user interfaces, ensuring accurate user tracking and interaction data recording.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated systems are used to track users, then productivity is improved, but reliability deteriorates due to low confidence or loss of tracking
Solution Approach 1:
The patent introduces an intermediary verification process where human associates review image gallery data to confirm user identities and group memberships. This intermediary step bridges the gap between automated tracking (which provides speed but suffers from reliability issues) and manual verification (which provides accuracy but is time-consuming). The system automatically triggers human review only when confidence thresholds are not met, maintaining productivity while improving reliability for uncertain cases.
2Reliability
If human associates are used to verify user identification, then reliability is improved, but device complexity increases
Solution Approach 1:
The system implements self-service automation where the automated tracking system handles routine, high-confidence cases independently without human intervention. Human associates are automatically engaged only when the system determines that confidence thresholds are not met, allowing the system to serve itself for most operations while selectively involving human resources when needed. This reduces the perceived complexity by automating the decision-making process for when human verification is required.
Solution Approach 2:
The verification process is segmented into automated handling for high-confidence cases and manual review for low-confidence cases. The system divides the user tracking workflow into distinct segments based on confidence levels, with different processing paths for each segment. This segmentation allows the complex system to manage complexity by handling different types of cases through appropriate channels.
3Measurement precision
If manual verification is implemented, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The system applies manual verification partially, only when necessary, rather than universally. Automated systems perform verification for the majority of cases where confidence is sufficient, and human associates perform verification only for the partial subset of cases where automated confidence thresholds are not met. This partial application of manual verification maintains measurement precision for uncertain cases while minimizing time loss by avoiding unnecessary manual review for confident cases.
Data Source
AI summary
A system may generate image data of users within a facility. Such users may be part of a group that is unknown to the system. The system can predict group data for two or more users based on a resemblance or the users being within a threshold distance of each other. However, if a confidence level associated with the predicted group data is below a threshold value, the group data is deemed unreliable and assistance from an associate is deemed necessary. A user interface that includes a portion of the image data, information about the predicted group data, and other interface elements is presented to the associate via a display. Based on the input data received from the associate, the group data can be confirmed or rejected. If the group data is confirmed, an association is made between the users and a group identifier.