Audience Estimation via Iterative Capture-Recapture

The patent changes the mathematical parameters and computational approach by using iterative algorithms with convergence criteria rather than traditional direct calculation methods. This allows the system to achieve accurate population estimates through progressive approximation, stopping when sufficient precision is reached without requiring exhaustive computation, thus resolving the contradiction between accuracy and computational time.

The patent applies partial action by using iterative methods that perform computations progressively rather than all at once. The algorithm continues iterating only until convergence criteria are met, performing just enough computational steps to achieve the required accuracy level, thereby avoiding excessive computational time and memory consumption while maintaining estimation precision.

The patent transforms the memory-intensive traditional methods into a parameter-based iterative approach that stores only essential convergence criteria and current iteration values rather than maintaining large datasets in memory. This parameter transformation enables accurate estimation while dramatically reducing memory footprint, resolving the contradiction between precision and memory consumption.

The patent extracts the essential computational requirements from the traditional capture-recapture methodology, separating the core estimation function from memory-intensive data storage requirements. By formulating the problem in terms of iterative parameter updates rather than data accumulation, the system achieves accurate population estimation with minimal memory consumption, effectively taking out the memory burden while preserving measurement precision.