Contact Tracing Analytics for At-Risk Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current contact tracing methods are inadequate in efficiently identifying at-risk individuals during the spread of communicable diseases, particularly in complex interaction environments, due to the volume and disparity of interaction data and concerns over privacy.
Innovation Solution
A method and system that determine community interaction information by correlating times and physical locations of individuals across clusters, using processors to identify at-risk individuals based on this data, while ensuring compliance with privacy regulations through proper data sourcing and processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If contact tracing is conducted on all individuals in complex interaction environments, then identification accuracy of at-risk individuals is improved, but data processing complexity and time consumption increase significantly
Solution Approach 1:
The patent segments the contact tracing process by dividing individuals into different risk groups based on their interaction patterns and exposure levels. This segmentation allows the system to focus processing resources on high-risk individuals rather than treating all individuals uniformly, thereby maintaining identification accuracy while reducing overall data processing complexity.
Solution Approach 2:
The patent extracts and isolates critical interaction data elements that are most relevant to disease transmission risk. By extracting only the essential data points (such as close-contact duration, proximity metrics, and interaction frequency) from the broader dataset, the system maintains identification accuracy while significantly reducing the volume of data that requires complex processing.
2Measurement precision
If comprehensive interaction data is collected for contact tracing, then identification accuracy of at-risk individuals is improved, but privacy concerns and data security risks worsen
Solution Approach 1:
The patent extracts only the minimum necessary data elements required for contact tracing effectiveness. By extracting specific interaction metrics (such as proximity, duration, and contact frequency) while excluding personally identifiable information and sensitive personal data, the system maintains identification accuracy while mitigating privacy concerns and data security risks.
Solution Approach 2:
The patent introduces data aggregation and anonymization as intermediary processing steps between data collection and analysis. These intermediaries transform raw interaction data into aggregated statistical patterns that preserve identification accuracy while removing direct links to individual identities, thereby addressing privacy concerns without sacrificing tracing effectiveness.
3Speed
If real-time contact tracing is implemented during disease spread, then response speed is improved, but computational resource consumption increases
Solution Approach 1:
The patent performs preliminary processing and pre-computation of interaction data as it is collected, organizing it into structured formats and pre-calculating basic risk metrics. This preliminary action enables the system to provide real-time responses during disease spread without requiring intensive computational resources at the moment of analysis, as much of the heavy lifting has already been done in advance.
Solution Approach 2:
The patent implements a tiered processing approach where only a subset of interaction data requiring immediate analysis is processed in real-time, while other data is processed asynchronously or in batches. This partial action approach maintains critical response speed for high-priority cases while reducing overall computational resource consumption by avoiding unnecessary real-time processing of all data.
Data Source
AI summary
Contact tracing during an event is provided. Community interaction information for one or more clusters is determined. The community interaction information for a cluster correlates times and physical locations of one or more individuals within an area corresponding to the cluster. It is determined that a first individual has traveled from a first area corresponding to a first cluster to a second area corresponding to a second cluster. The determination is based, at least in part, on correlated times and physical locations of the first individual. One or more at-risk individuals is identified based, at least in part, on the community interaction information of the second cluster.